CN107346553A - The determination method and apparatus of stripe information in a kind of image - Google Patents
The determination method and apparatus of stripe information in a kind of image Download PDFInfo
- Publication number
- CN107346553A CN107346553A CN201610296958.9A CN201610296958A CN107346553A CN 107346553 A CN107346553 A CN 107346553A CN 201610296958 A CN201610296958 A CN 201610296958A CN 107346553 A CN107346553 A CN 107346553A
- Authority
- CN
- China
- Prior art keywords
- stripe
- image
- color
- component image
- determined
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000012545 processing Methods 0.000 claims description 32
- 238000001914 filtration Methods 0.000 claims description 21
- 230000008569 process Effects 0.000 claims description 14
- 239000007787 solid Substances 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 9
- 230000009467 reduction Effects 0.000 claims description 6
- 241001463139 Vitta Species 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 12
- 230000000694 effects Effects 0.000 description 8
- 238000012360 testing method Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 5
- 238000013461 design Methods 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B30/00—Optical systems or apparatus for producing three-dimensional [3D] effects, e.g. stereoscopic images
- G02B30/20—Optical systems or apparatus for producing three-dimensional [3D] effects, e.g. stereoscopic images by providing first and second parallax images to an observer's left and right eyes
- G02B30/26—Optical systems or apparatus for producing three-dimensional [3D] effects, e.g. stereoscopic images by providing first and second parallax images to an observer's left and right eyes of the autostereoscopic type
- G02B30/27—Optical systems or apparatus for producing three-dimensional [3D] effects, e.g. stereoscopic images by providing first and second parallax images to an observer's left and right eyes of the autostereoscopic type involving lenticular arrays
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Optics & Photonics (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the present invention discloses a kind of determination method of stripe information in image, is related to display technology field, more can accurately obtain the stripe information in image.Methods described includes:The first image is obtained, described first image includes stripe pattern;The stripe pattern is extracted from described first image;The stripe pattern is converted into tone saturation degree lightness HSV images, and isolates chrominance component image;The stripe direction in the chrominance component image is determined, according to the stripe direction of the determination, determines the central point of the first color stripe in the chrominance component image;Belong to the central point of the color stripe of same first;According to the central point for ranging the color stripe of same first, fitting a straight line is carried out;According to the striped linear equation after the fitting, the stripe information of stripe pattern described in described first image is determined.The present invention can be used for bore hole 3D display technology.
Description
Technical field
The present invention relates to a kind of determination method of stripe information in stereo display technique field, more particularly to image
And device.
Background technology
People generally watch object simultaneously by eyes, due to eye spacing, right and left eyes between the eyes of people be present
Between be about separated by 65mm, therefore, the gaze angle of eyes is different when watching object, causes right and left eyes to connect
There is a certain degree of difference in the visual pattern received, because the visual pattern that right and left eyes receive is different, greatly
The information that brain combines right and left eyes two images is overlapped to image and lived again so that beholder produce it is three-dimensional
Sense.At present, bore hole 3D (3-dimensional) display device of main flow is exactly using above-mentioned principle, by commonly showing
Show and special grating is superimposed on device, the grating can be to different directions refraction image, and allow left eye and right eye can
Separated depending on picture, so as to allow user to see 3D images.
Bore hole 3D equipment is when being shown, it is necessary to which left eye picture and right eye picture are arranged according to certain rule
Row display over the display (i.e. row's figure), coordinates the light splitting of grating to act on, forms right and left eyes vision area, accomplish
Left eye picture is sent into the left eye of user, right eye picture is sent into the right eye of user, so that user watches
3D images.Cooperated because row's figure must act on the light splitting of grating, therefore, grating parameter is row's figure
The key parameter used needed for algorithm, that is, grating parameter is that bore hole 3D display equipment carries out imaging and shown
Call parameter, directly decide the imaging effect of 3D display equipment.Specifically, grating parameter may include
Grating inclination angle, grating pitch, grating place distance, grating relative to display screen displacement (also referred to as grating with
The horizontal relative dislocation of display screen panel) etc..Influenceed by factors such as manufacturing process and rigging errors, grating ginseng
Several actual values and ideal design value are normally present certain deviation, if directly carried out using design load
Row's figure is shown, the adjustment for right and left eyes vision area for causing bore hole 3D display equipment is inaccurate, Jin Erying
Ring the display effect of bore hole 3D display equipment.Therefore, in order to the aobvious of bore hole 3D display equipment is effectively ensured
Show effect, before sales is dispatched from the factory, it is necessary to join to the grating of bore hole 3D display equipment in bore hole 3D display equipment
Number is corrected, that is, need extremely accurate to obtain the grating parameter actual value of bore hole 3D display equipment so as to
It is applied in row's nomography, ensures the stereo display effect of bore hole 3D display equipment.
In the prior art, it is generally pre- in order to be accurately obtained very much the grating parameter of bore hole 3D display equipment
First set the span of the grating parameter of bore hole 3D display equipment, periodic transformation's grating parameter, from
And utilize and arrange nomography periodic cycle display test pictures, the test pictures are usually striped picture, such as
Red an IOU issued by a post office paints face, gathers these test pictures and carries out analysis calculating to these test pictures, according to test
The stripe information of picture information such as the cycle of striped and angle of inclination and row's graph parameter, draw preferably
Grating parameter, that is, more accurately grating parameter actual value is obtained, so that bore hole 3d display devices were using should
Actual value is shown, ensures stereo display effect.
Due to needing to get the stripe information of striped test pictures and obtaining grating parameter using stripe information
Actual value, therefore, the degree of accuracy of stripe information necessarily affects the degree of accuracy of grating parameter actual value, such as
The stripe information what accurately gets test pictures is a urgent problem to be solved.
The content of the invention
Have in view of that, the embodiment of the present invention provides a kind of determination method and apparatus of stripe information in image, energy
Enough stripe informations more accurately got in image.
In a first aspect, the embodiment of the present invention provides a kind of determination method of stripe information in image, including:
The first image is obtained, described first image includes the stripe pattern that the first equipment is generated and shown, institute
Stating stripe pattern includes the first color stripe and the second color stripe of alternate setting;
The stripe pattern is extracted from described first image;
The stripe pattern is converted into tone saturation degree lightness HSV images, and from the HSV images
Isolate chrominance component image;
The stripe direction in the chrominance component image is determined, according to the stripe direction of the determination, scans institute
Chrominance component image is stated, so that it is determined that going out the central point of the first color stripe in the chrominance component image;
The central point of first color stripe determined is clustered, same is belonged to so as to sort out
The central point of first color stripe;
According to the central point for ranging the color stripe of same first, fitting a straight line is carried out, is fitted
Striped linear equation afterwards;
According to the striped linear equation after the fitting, the bar of stripe pattern described in described first image is determined
Line information, the stripe information include at least one of fringe period and striped slope.
With reference in a first aspect, in the first embodiment of first aspect, it is described by the stripe pattern from
Extracted in described first image including:
Described first image is converted into tone saturation degree lightness HSV images, and from the HSV images
Isolate lightness component image;
According to the gray value of the pixel of the lightness component image, bar described in the lightness component image is determined
The edge contour of print image;
The edge contour of stripe pattern, determines the stripe pattern according to the lightness component image
Corner location;
According to the corner location of the determination, the stripe pattern is partitioned into from described first image.
It is described in second of embodiment of first aspect with reference to the first embodiment of first aspect
The edge contour of stripe pattern according to the lightness component image, determine the angle point of the stripe pattern
Position includes:
Fitting a straight line is carried out to the edge contour, obtains the linear equation on each bar side of the edge contour;
Structure and the solid background image of described first image same shape and size, and according to the straight of the side
Line equation, the line segment on the side, the color of the line segment and the back of the body are drawn in the solid background image
The color of scape is different;
According to the color of the line segment and the color of the background, the background image for having the line segment is drawn in scanning,
So that it is determined that go out the intersection point of the line segment, wherein, in the neighborhood territory pixel point of the intersection point, at least two pairs are relative
Neighborhood territory pixel point color value be the line segment color value;
According to the intersection point of the determination, the corner location of the stripe pattern is determined.
With reference to the first or second of embodiment of first aspect or first aspect, the of first aspect
In three kinds of embodiments, it is described isolate chrominance component image from the HSV images after, it is described
According to the stripe direction of the determination, the chrominance component image is scanned, so that it is determined that going out the chrominance component
In image before the central point of the first color stripe, methods described also includes:
According to the stripe direction of the determination, at least one-row pixels point for choosing the chrominance component image is carried out
Scanning, it is determined that the central point of the first color stripe described at least one-row pixels point;
It is determined that gone together described at least one-row pixels point in the central point of the first color stripe it is adjacent in
The distance between heart point;
According to the distance between adjacent central point of the colleague, the estimation width of the striped is determined;
According to the estimation width of the striped, it is determined that convolution kernel is filtered, and according to the filtering convolution kernel, to institute
State chrominance component image and be filtered processing;
The stripe direction according to the determination, the chrominance component image is scanned, so that it is determined that going out described
The central point of the first color stripe includes in chrominance component image:
According to the stripe direction of the determination, the chrominance component image after the filtering process is scanned, so as to really
Make the central point of the first color stripe in the chrominance component image.
It is described in the 4th kind of embodiment of first aspect with reference to the third embodiment of first aspect
According to the stripe direction of the determination, the chrominance component image after the filtering process is scanned, so that it is determined that going out
The central point of the first color stripe includes in the chrominance component image:
According to the stripe direction of the determination, the chrominance component image after the filtering process is scanned, searches institute
State the absolute of tone value and the tone value of first color in the first color stripe in chrominance component image
The minimum pixel of difference, and it is minimum from the absolute difference of the tone value and the tone value of first color
Pixel in filter out datum mark;
Search corresponding to the datum mark the absolute of tone value and the tone value of the datum mark in presumptive area
Difference is less than the pixel of predetermined threshold value;
According to the position coordinates of the datum mark, and the tone value and the tone value of the datum mark is absolute
Difference is less than the position coordinates of the pixel of predetermined threshold value, determines the first color bar in the chrominance component image
The position coordinates of the central point of line.
It is described in the 5th kind of embodiment of first aspect with reference to the 4th kind of embodiment of first aspect
The central point of first color stripe determined is clustered, same first is belonged to so as to sort out
The central point of color stripe includes:
If two points in the central point determined while meeting following three condition, it is determined that this two
Individual point belongs to the color stripe of same first:
Condition 1:Δ x >=-1 or Δ y >=-1
Condition 2:| Δ y | < f*MaxLen
Condition 3:| Δ x | < f*MaxLen
Wherein, Δ x be described two points abscissa difference, Δ y be described two points ordinate difference, f
To be less than 1 preset constant more than 0, MaxLen is the estimation width.
With reference in a first aspect, in the 6th kind of embodiment of first aspect, it is described by the stripe pattern from
It is described that the stripe pattern is converted into tone saturation degree lightness HSV after being extracted in described first image
Image, and before isolating chrominance component image from the HSV images, methods described also includes:
Rotated and/or stretched processing to the stripe pattern extracted;
It is described the stripe pattern is converted into tone saturation degree lightness HSV images to include:
The stripe pattern after the flexible processing is converted into tone saturation degree lightness HSV images;
In the striped linear equation according to after the fitting, bar graph described in described first image is determined
After the stripe information of picture, methods described also includes:
According to the rotation and/or flexible processing, reduction treatment is carried out to the stripe information of the determination, with
The stripe information is set to match with original described first image.
Second aspect, the embodiment of the present invention provide a kind of determining device of stripe information in image, including:
Acquiring unit, for obtaining the first image, described first image includes the first equipment and generates and show
Stripe pattern, the stripe pattern includes the first color stripe and the second color stripe of alternate setting;
Extraction unit, for the stripe pattern to be extracted from described first image;
Separative element, for the stripe pattern to be converted into tone saturation degree lightness HSV images, and from
Chrominance component image is isolated in the HSV images;
First determining unit, for determining the stripe direction in the chrominance component image, according to the determination
Stripe direction, the chrominance component image is scanned, so that it is determined that going out the first face in the chrominance component image
The central point of vitta line;
Sort out unit, for being clustered to the central point of first color stripe determined, so as to return
Class belongs to the central point of the color stripe of same first;
Fitting unit, for ranging the central point of the color stripe of same first according to, carry out straight line
Fitting, the striped linear equation after being fitted;
Second determining unit, for according to the striped linear equation after the fitting, determining described first image
Described in stripe pattern stripe information, the stripe information includes in fringe period and striped slope at least
It is a kind of.
With reference to second aspect, in the first embodiment of second aspect, the extraction unit is specifically used for:
Described first image is converted into tone saturation degree lightness HSV images, and from the HSV images
Isolate lightness component image;
According to the gray value of the pixel of the lightness component image, bar described in the lightness component image is determined
The edge contour of print image;
The edge contour of stripe pattern, determines the stripe pattern according to the lightness component image
Corner location;
According to the corner location of the determination, the stripe pattern is partitioned into from described first image.
It is described in second of embodiment of second aspect with reference to the first embodiment of second aspect
Extraction unit is specifically used for:
Fitting a straight line is carried out to the edge contour, obtains the linear equation on each bar side of the edge contour;
Structure and the solid background image of described first image same shape and size, and according to the straight of the side
Line equation, the line segment on the side, the color of the line segment and the back of the body are drawn in the solid background image
The color of scape is different;
According to the color of the line segment and the color of the background, the background image for having the line segment is drawn in scanning,
So that it is determined that go out the intersection point of the line segment, wherein, in the neighborhood territory pixel point of the intersection point, at least two pairs are relative
Neighborhood territory pixel point color value be the line segment color value;
According to the intersection point of the determination, the corner location of the stripe pattern is determined.
With reference to the first or second of embodiment of second aspect or first aspect, the of second aspect
In three kinds of embodiments:
Described device also includes filter unit, is used for:
According to the stripe direction of the determination, at least one-row pixels point for choosing the chrominance component image is carried out
Scanning, it is determined that the central point of the first color stripe described at least one-row pixels point;
It is determined that gone together described at least one-row pixels point in the central point of the first color stripe it is adjacent in
The distance between heart point;
According to the distance between adjacent central point of the colleague, the estimation width of the striped is determined;
According to the estimation width of the striped, it is determined that convolution kernel is filtered, and according to the filtering convolution kernel, to institute
State chrominance component image and be filtered processing;
First determining unit is specifically used for:
According to the stripe direction of the determination, the chrominance component image after the filtering process is scanned, so as to really
Make the central point of the first color stripe in the chrominance component image.
It is described in the 4th kind of embodiment of second aspect with reference to the third embodiment of second aspect
First determining unit is specifically used for:
According to the stripe direction of the determination, the chrominance component image after the filtering process is scanned, searches institute
State the absolute of tone value and the tone value of first color in the first color stripe in chrominance component image
The minimum pixel of difference, and it is minimum from the absolute difference of the tone value and the tone value of first color
Pixel in filter out datum mark;
Search corresponding to the datum mark the absolute of tone value and the tone value of the datum mark in presumptive area
Difference is less than the pixel of predetermined threshold value;
According to the position coordinates of the datum mark, and the tone value and the tone value of the datum mark is absolute
Difference is less than the position coordinates of the pixel of predetermined threshold value, determines the first color bar in the chrominance component image
The position coordinates of the central point of line.
It is described in the 5th kind of embodiment of second aspect with reference to the 4th kind of embodiment of second aspect
Sort out unit to be specifically used for:
If two points in the central point determined while meeting following three condition, it is determined that this two
Individual point belongs to the color stripe of same first:
Condition 1:Δ x >=-1 or Δ y >=-1
Condition 2:| Δ y | < f*MaxLen
Condition 3:| Δ x | < f*MaxLen
Wherein, Δ x be described two points abscissa difference, Δ y be described two points ordinate difference, f
To be less than 1 preset constant more than 0, MaxLen is the estimation width.
With reference to second aspect, in the 6th kind of embodiment of second aspect:
Described device also includes rotary extension unit, for being rotated to the stripe pattern extracted
And/or flexible processing;
The separative element is specifically used for:
The stripe pattern after the flexible processing is converted into tone saturation degree lightness HSV images;
The rotary extension unit is additionally operable to:
According to the rotation and/or flexible processing, reduction treatment is carried out to the stripe information of the determination, with
The stripe information is set to match with original described first image.
The determination method and apparatus of stripe information in image provided in an embodiment of the present invention, will from the first image
Stripe pattern extracts, and then using the chrominance component image of stripe pattern, determines stripe pattern first
The central point of color stripe, fitting a straight line is carried out using central point, and then obtains the stripe information of stripe pattern,
It more can accurately get the stripe information in the first image.
Brief description of the drawings
Fig. 1 is the flow chart of the determination method of stripe information in a kind of image provided in an embodiment of the present invention;
Fig. 2 is the illustrative diagram of the first image in method shown in Fig. 1;
Fig. 3 is the effect diagram after edge contour detection in method shown in Fig. 1;
The effect diagram of line segment is drawn during the angle point that edge contour is determined in Fig. 4 methods shown in Fig. 1;
Fig. 5 is pixel eight neighborhood schematic diagram in method shown in Fig. 1;
Fig. 6 is the effect diagram of the stripe pattern after rotary extension in method shown in Fig. 1;
Fig. 7 is the structural representation of the determining device of stripe information in a kind of image provided in an embodiment of the present invention
Figure;
Fig. 8 is the structural representation of the determining device of stripe information in a kind of image provided in an embodiment of the present invention
Figure;
Fig. 9 is the structural representation of the determining device of stripe information in a kind of image provided in an embodiment of the present invention
Figure.
Embodiment
To make the technical problem to be solved in the present invention, technical scheme and advantage clearer, below in conjunction with attached
Figure and specific embodiment are described in detail.
As shown in figure 1, in a kind of image provided in an embodiment of the present invention stripe information determination method, specifically
Flow includes:
Step 101, the first image is obtained, the first image includes the bar graph that the first equipment is generated and shown
Picture, stripe pattern include the first color stripe and the second color stripe of alternate setting.
Firstly the need of explanation, information provided in an embodiment of the present invention determines that method can be held by the second equipment
OK, in the method, the first equipment generates and shows stripe pattern, and the second equipment, which obtains, includes the striped
First image of image, and determine the stripe information of stripe pattern in the first image.Specifically, the second equipment
Can by image acquiring device, such as by camera shooting show stripe pattern the first equipment photograph
Piece, so as to get the first image of stripe pattern for including the first equipment and generating and showing, stripe pattern
Include the first color stripe and the second color stripe of alternate setting.
In practical application, the first equipment can be bore hole 3D display equipment, and it includes display screen and is arranged on
Grating on display screen.First equipment can arrange the first face on a display screen according to certain row's nomography
Color pixel and the second colored pixels, the light splitting of grating is coordinated to act on, so that the display device shows one
Stripe pattern, wherein, the stripe pattern can be red an IOU issued by a post office print image, i.e. the first color stripe to be red and
A kind of striped of color in green color stripe, and the second color stripe is the another kind in red and green color stripe
The striped of color.Second equipment shoots the full face of the first equipment so as to obtaining the first image, it is preferred that
In order to protrude stripe pattern, the first equipment can be placed in dark space, and be highlighted stripe pattern, so as to
So that in the first image, stripe pattern can protrude presentation, and other parts are dark background.
For example, Fig. 2 shows the illustrative diagram of first image, as shown in Fig. 2 the figure
Include stripe pattern in the middle part of picture.First image can consider to be made up of two parts, respectively stripe pattern
And background.
Step 102, stripe pattern is extracted from the first image.
In order to obtain the stripe information of stripe pattern, it is necessary first to which stripe pattern is isolated from the first image
Come.The embodiment of the present invention does not limit for how to extract stripe pattern from the first image, ability
Field technique personnel can be by the way of any reasonable, for example, conventional stingy nomography in the prior art.
For example, optionally, in one embodiment of the invention, can be in the following way by striped
Image extracts from the first image:
First, the first image is converted into tone saturation degree lightness HSV images, and from HSV images
Isolate lightness component image hsv_v.
Then, according to the gray value of the pixel of lightness component image, stripe pattern in lightness component image is determined
Edge contour.For example, specifically, as shown in Figure 2, in the first image, the profile of stripe pattern
The pixel grey scale of outside (i.e. background) and inner side is different, therefore, can preset a threshold value, respectively from
Left-to-right, hsv_v images are scanned from the top down, from right to left, from the bottom up, according to former and later two
The gray scale difference of pixel is compared with presetting given threshold value, so that it is determined that going out the edge contour of stripe pattern
Pixel (i.e. pixel point coordinates) set, edge contour detection design sketch can be found in Fig. 3.
It should be understood that after edge contour determines, it is understood that there may be some noise spots, these noise spots will influence
The precision of subsequent treatment, therefore, processing can be further optimized, remove noise spot.Remove noise spot
Method it is unlimited, those skilled in the art can be according to the common knowledge reasonable selection of this area.For example,
For every a line of edge contour, fitting a straight line is carried out to the pixel point set (point set) on the side first,
Then distance of the point all on the side to straight line will be calculated, distance is finally more than several times average distance
Point is deleted from a concentration.
After edge contour is obtained, next, according to the edge contour of stripe pattern in lightness component image,
Determine the corner location of stripe pattern.It should be understood that how the step specifically performs same unlimited, ability
Field technique personnel can have multiple choices.Optionally, in order to be further ensured that operational precision, can use such as
Under type:
Fitting a straight line is carried out to edge contour, for example, fitting a straight line is carried out to the point set of above-mentioned removal noise spot,
Obtain the linear equation on each bar side of edge contour;Then, structure with the first image same shape and size (i.e.
With hsv_v images same shape and size) solid background image, for example, background pure black image, and root
According to the linear equation on side, the line segment on drafting side, the color of line segment and the color of background in solid background image
Difference, line segment can be white, and background is black, and line segment is preferably extended over to whole image, after drawing line segment
Design sketch can be found in Fig. 4.Because the color of line segment color and background is different, next, according to line segment
The color of color and background, the background image for having line segment is drawn in scanning, so that it is determined that go out the intersection point of line segment, its
In, in the neighborhood territory pixel point of intersection point, the color value of at least two pairs relative neighborhood territory pixel points is the color of line segment
Value.Then according to the intersection point of determination, the corner location of stripe pattern is determined.Illustrate, can be from upper past
Under, scan whole image from left to right, when running into for example white pixel of a line segment color, observation
The pixel of its 8 neighborhood.Referring to Fig. 5, it is assumed that pixel 5 is the pixel of line segment colours white, at this
In 8 neighborhood territory pixels 1 to 4,6 to 9 of pixel 5, in 1 and 9,2 and 8,4 and 7,4 and 6,
Have at least that 2 pairs of pixels are all white point, then the white pixel point 5 is an angle point.
It is understood that identified four angle points are probably unordered, it is necessary to resequence.If striped
Image is quadrangle, and 4 angle points should be upper left angle point, upper right angle point, bottom right angle point, lower-left angle point.
So in identified four angle points, Transverse coordinates upper left angle point less than normal, lower-left angle point can be first looked for out, it is horizontal
Coordinate larger upper right angle point and bottom right angle point, then carry out ordinate comparison again, you can four points of discharge
Sequentially.
After angle point determination, next shaping can be split from the first image according to the corner location of determination
Print image.
It should be noted that in actual implementation, stripe pattern is probably inclined, for example, bore hole 3D shows
Show the possible fuselage of equipment and out of plumb, but there is certain angle of inclination with vertical direction, cause screen simultaneously
Out of plumb, has certain inclination, and stripe pattern may have certain anglec of rotation.Moreover, for simplification
Computing, lift operation efficiency, stripe pattern can also be carried out it is appropriate it is flexible after carry out follow-up processing again,
Such as stripe pattern is reduced into certain proportion.Therefore, in one embodiment of the invention, can be to extracting
The stripe pattern come is rotated and/or flexible processing, so as to by stripe pattern be stretched to a suitable size and
Keep positive stripe pattern.Specifically, primative streak image may refer to Fig. 2, the bar after rotary extension
Print image may refer to Fig. 6.
Step 103, stripe pattern is converted into tone saturation degree lightness HSV images, and from HSV images
In isolate chrominance component image hsv_h.
Obviously, HSV images are converted the image into, and isolates chrominance component from HSV images, satisfy
It is routine techniques with degree component and transparency component image, the present invention is not being repeated this.
Step 104, the stripe direction in chrominance component image is determined, according to the stripe direction of determination, scanning
Chrominance component image, so that it is determined that going out the central point of the first color stripe in tone component image.
Stripe direction in stripe pattern may be vertically oriented, it is also possible to horizontal direction, in order to simplify fortune
Calculate, lifting operation efficiency is pre-processed, roughly really first to find central point in the embodiment of the present invention
The stripe direction in stripe pattern is fixed, then according to identified stripe direction, is scanned to obtain center
Point.Specifically, can first enter row threshold division (binary conversion treatment) to chrominance component image, then utilize
Known Hough Hough transform carries out straight-line detection to the image of binaryzation, is estimated according to the straight line of detection
Determine stripe direction in the inclination angle of straight line.
, optionally, can be according to the stripe direction of determination, you can it is determined that scanning side after stripe direction is determined
To, for example, striped is horizontal stripe, then scanning direction is vertical direction, if striped is vertical striped,
Scanning direction is horizontal direction, scans chrominance component image according to the scanning direction of determination, searches the tone
The absolute difference of tone value and the tone value of first color is (i.e. poor in the first color stripe in component image
The absolute value of value) minimum pixel, and filter out datum mark from these pixels.Next, search
The absolute difference of tone value and the tone value of the datum mark is less than in presumptive area corresponding to the datum mark
The pixel of predetermined threshold value.Then, according to the position coordinates of the datum mark, and the tone value with it is described
The absolute difference of the tone value of datum mark is less than the position coordinates of the pixel of predetermined threshold value, determines the tone
The position coordinates of the central point of first color stripe in component image.Wherein, presumptive area corresponding to datum mark
It is pre-set, for example, centered on datum mark, the region of each 10 pixels in left and right.
Generally, the central distribution of the first color stripe the pixel closest to the first color, and along
Center is to the first color stripe both sides, and the color of pixel is more and more far away from the first color.Based on this, search
The absolute difference of tone value and the tone value of the first color is minimum in the first color stripe in chrominance component image
Pixel, generally these point positioned at the first color stripe center, but it is understood that, due to color
Color distortion and scanning accuracy etc. limit, it is possible to can find some inaccurate noise spots, therefore, pin
To first color stripe, the absolute of some tone values and the tone value of first color may be found
The minimum pixel of difference in these points found, it is necessary to carry out lower screening, removal noise spot, so as to sieve
Select the datum mark positioned at fringe center.Specific screening process, for example, in the pixel found,
Determine that the tone value of the pixel of the pixel both sides preset range on scanning direction changes in one direction
Point on the basis of the point of (gradually increaseing or decreasing), and remove on scanning direction at least one in the pixel both sides
The pixel of the tone value fluctuations of the pixel of the preset range of side.
So that stripe pattern is red an IOU issued by a post office print image as an example, pure red corresponding hue angle is 0 degree, can scan picture
Plain color tone pitch, find tone value and the pixel (datum mark) of 0 absolute difference minimum, such as 3 degree
Pixel, the pixel is closely red, is pixel most red in striped, is usually located at red streak
Core.For a red streak, some 3 degree of pixels may be found, therefore, be at this
Datum mark is determined in a little 3 degree of pixels.Next, due in the stripe pattern in the first image it is red not
Must be pure red, so also to set a rational deviation, i.e., a default threshold value, the threshold value is for example
Can be 5, it is assumed that datum mark tone value is 3, along scanning direction by the pixel point range of datum mark both sides 20
Interior tone value is found out with 3 difference less than 5 pixel.According to these points and benchmark found out
Point, X, the Y-coordinate average of these points and datum mark are calculated, the average is defined as red streak central point
Position coordinates.
Explanation is needed further exist for, in order to which the precision of processing, and simplified operation is effectively ensured, lifts computing
Efficiency is to find central point, after chrominance component image is isolated from HSV images, according to determination
Stripe direction, chrominance component image is scanned, so that it is determined that going out in tone component image in the first color stripe
Before heart point, processing can be first filtered to chrominance component image, row's impurity point interference, then, is being filtered
The first color stripe central point is determined in chrominance component image after processing.Specifically, it can carry out in advance thick
Approximation is calculated and estimates a filtering convolution kernel, and then according to the filtering convolution kernel, chrominance component image is filtered
Processing.For example, at least a line picture of chrominance component image can according to the stripe direction of determination, be chosen
Vegetarian refreshments is scanned, it is determined that at least in a line (can be a line) pixel the first color stripe central point,
Such as the minimum or maximum point of tone value is found, then, it is determined that the first color stripe at least in one-row pixels point
Central point in go together the distance between adjacent central point, according to the distance between adjacent central point of going together,
The estimation width of striped is determined, according to the estimation width of striped, it is determined that filtering convolution kernel.
Step 105, the central point of the first color stripe to determining clusters, and is belonged to so as to sort out
The central point of the color stripe of same first.
In order to which operational precision is effectively ensured, since it is determined that the central point come is not necessarily continuously, therefore this
These points are clustered in step, them is revert on respective streak line.
In one embodiment of the invention, in this step, if it is determined that two points in the central point gone out are same
When meet following three condition, it is determined that the two point belong to the color stripe of same first:
Condition 1:Δ x >=-1 or Δ y >=-1
Condition 2:| Δ y | < f*MaxLen
Condition 3:| Δ x | < f*MaxLen
Wherein, Δ x is the difference of the abscissa of two points, and Δ y is the difference of the ordinate of two points, and f is more than 0
Preset constant less than 1, MaxLe are the estimation width of striped, when foregoing calculating filters convolution kernel,
The determination mode of estimation width is described, is repeated no more here.
Step 106, according to the central point for ranging the color stripe of same first, fitting a straight line is carried out, is obtained
Striped linear equation after fitting.
Fitting a straight line can use existing conventional method, such as least square method, no longer do here specifically
It is bright.In order to which the efficiency of calculating is effectively ensured, and error is reduced, can be in the color stripe of same first
Some points that striped interlude is chosen in central point are fitted, such as 100 points of interlude.
Step 107, according to the striped linear equation after fitting, the striped of stripe pattern in the first image is determined
Information, stripe information include at least one of fringe period and striped slope.
Specifically, according to the striped linear equation after fitting, the slope of each striped straight line can be obtained, can be asked
Go out the average value of the slope of each striped straight line, as the striped slope in stripe information.
And for fringe period, can by being fitted obtained linear equation above, try to achieve some rows (if or
Dry row) the institute on striped a little, the cycle size of striped is then calculated according to these points.For example,
Several y-coordinates are set, that is, take some rows of image, corresponding striped is tried to achieve by the linear equation after fitting
X coordinate on straight line, thus a series of coordinate points can be obtained.Next, pass through a series of coordinate points
In adjacent two x coordinate xi, xi+1Distance can easily draw adjacent the first color stripe or the second color
The step-length of striped, the step-length of all consecutive points of some rows can be calculated according to this.Then all step-lengths are asked
Value obtained by average is fringe period.
Explanation is needed further exist for, if after stripe pattern is extracted from the first image, by bar
Print image is converted to tone saturation degree lightness HSV images, and chrominance component figure is isolated from HSV images
As before, the stripe pattern extracted is rotated and/or flexible processing, in this case, it is necessary to according to
Rotation and/or flexible processing, pair stripe information determined carry out reduction treatment, it is necessary to the fringe period that will be obtained
With the anglec of rotation relation and/or scaling relation of striped slope image according to before and after, original image is reverted to
Size so that stripe information matches with the first original image.
The determination method of stripe information in image provided in an embodiment of the present invention, by bar graph from the first image
As extracting, then using the chrominance component image of stripe pattern, the color bar of stripe pattern first is determined
The central point of line, fitting a straight line is carried out using central point, and then obtain the stripe information of stripe pattern, can
More accurately get the stripe information in the first image.
Corresponding with preceding method embodiment, the embodiment of the present invention also provides in a kind of image stripe information really
Determine device, as shown in fig. 7, comprises:
Acquiring unit 10, for obtaining the first image, described first image includes the generation of the first equipment simultaneously
The stripe pattern of display, the stripe pattern include the first color stripe and the second color bar of alternate setting
Line;
Extraction unit 11, for the stripe pattern to be extracted from described first image;
Separative element 12, for the stripe pattern to be converted into tone saturation degree lightness HSV images, and
Chrominance component image is isolated from the HSV images;
First determining unit 13, for determining the stripe direction in the chrominance component image, according to described
The stripe direction of determination, the chrominance component image is scanned, so that it is determined that going out in the chrominance component image
The central point of one color stripe;
Sort out unit 14, for being clustered to the central point of first color stripe determined, from
And belong to the central point of the color stripe of same first;
Fitting unit 15, for ranging the central point of the color stripe of same first according to, carry out
Fitting a straight line, the striped linear equation after being fitted;
Second determining unit 16, for according to the striped linear equation after the fitting, determining described first
The stripe information of stripe pattern described in image, the stripe information are included in fringe period and striped slope
It is at least one.
The determination method of stripe information in image provided in an embodiment of the present invention, by bar graph from the first image
As extracting, then using the chrominance component image of stripe pattern, the color of stripe pattern first is determined
The central point of striped, fitting a straight line is carried out using central point, and then obtain the stripe information of stripe pattern, energy
Enough stripe informations more accurately got in the first image.
Optionally, in one embodiment of the invention, extraction unit 11 is specifically used for:
Described first image is converted into tone saturation degree lightness HSV images, and from the HSV images
Isolate lightness component image;
According to the gray value of the pixel of the lightness component image, bar described in the lightness component image is determined
The edge contour of print image;
The edge contour of stripe pattern, determines the stripe pattern according to the lightness component image
Corner location;
According to the corner location of the determination, the stripe pattern is partitioned into from described first image.
Optionally, in one embodiment of the invention, extraction unit 11 is specifically used for:
Fitting a straight line is carried out to the edge contour, obtains the linear equation on each bar side of the edge contour;
Structure and the solid background image of described first image same shape and size, and according to the straight of the side
Line equation, the line segment on the side, the color of the line segment and the back of the body are drawn in the solid background image
The color of scape is different;
According to the color of the line segment and the color of the background, the background image for having the line segment is drawn in scanning,
So that it is determined that go out the intersection point of the line segment, wherein, in the neighborhood territory pixel point of the intersection point, at least two pairs are relative
Neighborhood territory pixel point color value be the line segment color value;
According to the intersection point of the determination, the corner location of the stripe pattern is determined.
Optionally, in one embodiment of the invention, as shown in figure 8, described device also includes filtering list
Member 17, is used for:
According to the stripe direction of the determination, at least one-row pixels point for choosing the chrominance component image is carried out
Scanning, it is determined that the central point of the first color stripe described at least one-row pixels point;
It is determined that gone together described at least one-row pixels point in the central point of the first color stripe it is adjacent in
The distance between heart point;
According to the distance between adjacent central point of the colleague, the estimation width of the striped is determined;
According to the estimation width of the striped, it is determined that convolution kernel is filtered, and according to the filtering convolution kernel, to institute
State chrominance component image and be filtered processing;
Then, the first determining unit 13 is specifically used for:
According to the stripe direction of the determination, the chrominance component image after the filtering process is scanned, so as to really
Make the central point of the first color stripe in the chrominance component image.
Optionally, in one embodiment of the invention, the first determining unit 13 is specifically used for:
According to the stripe direction of the determination, the chrominance component image after the filtering process is scanned, searches institute
State the absolute of tone value and the tone value of first color in the first color stripe in chrominance component image
The minimum pixel of difference, and it is minimum from the absolute difference of the tone value and the tone value of first color
Pixel in filter out datum mark;
Search corresponding to the datum mark the absolute of tone value and the tone value of the datum mark in presumptive area
Difference is less than the pixel of predetermined threshold value;
According to the position coordinates of the datum mark, and the tone value and the tone value of the datum mark is absolute
Difference is less than the position coordinates of the pixel of predetermined threshold value, determines the first color bar in the chrominance component image
The position coordinates of the central point of line.
Optionally, in one embodiment of the invention, sort out unit 14 to be specifically used for:
If two points in the central point determined while meeting following three condition, it is determined that this two
Individual point belongs to the color stripe of same first:
Condition 1:Δ x >=-1 or Δ y >=-1
Condition 2:| Δ y | < f*MaxLen
Condition 3:| Δ x | < f*MaxLen
Wherein, Δ x be described two points abscissa difference, Δ y be described two points ordinate difference, f
To be less than 1 preset constant more than 0, MaxLen is the estimation width.
Optionally, in one embodiment of the invention, as shown in figure 9, described device is also stretched including rotation
Contracting unit 18, for the processing that rotated and/or stretched to the stripe pattern extracted;
Then, separative element 12 is specifically used for:
The stripe pattern after the flexible processing is converted into tone saturation degree lightness HSV images;
Rotary extension unit 18 is additionally operable to:
According to the rotation and/or flexible processing, reduction treatment is carried out to the stripe information of the determination, with
The stripe information is set to match with original described first image.
The present invention is produced with reference to method according to embodiments of the present invention, equipment (system) and computer program
The flow chart and/or block diagram of product describes.It should be understood that can by computer program instructions implementation process figure and
/ or each flow in block diagram and/or square frame and flow in flow chart and/or block diagram and/
Or the combination of square frame.These computer program instructions can be provided to all-purpose computer, special-purpose computer, insertion
Formula processor or the processor of other programmable data processing devices are to produce a machine so that pass through calculating
The instruction of the computing device of machine or other programmable data processing devices is produced for realizing in flow chart one
The device for the function of being specified in individual flow or multiple flows and/or one square frame of block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable datas to handle and set
In the standby computer-readable memory to work in a specific way so that be stored in the computer-readable memory
Instruction produce and include the manufacture of command device, command device realization is in one flow or multiple of flow chart
The function of being specified in one square frame of flow and/or block diagram or multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices, made
Obtain and series of operation steps is performed on computer or other programmable devices to produce computer implemented place
Reason, so as to which the instruction that is performed on computer or other programmable devices is provided for realizing in flow chart one
The step of function of being specified in flow or multiple flows and/or one square frame of block diagram or multiple square frames.
Although preferred embodiments of the present invention have been described, but those skilled in the art once know base
This creative concept, then other change and modification can be made to these embodiments.So appended right will
Ask and be intended to be construed to include preferred embodiment and fall into having altered and changing for the scope of the invention.
Obviously, those skilled in the art can carry out various changes and modification without departing from this hair to the present invention
Bright spirit and scope.So, if the present invention these modifications and variations belong to the claims in the present invention and
Within the scope of its equivalent technologies, then the present invention is also intended to comprising including these changes and modification.
Claims (14)
1. a kind of determination method of stripe information in image, it is characterised in that including:
The first image is obtained, described first image includes the stripe pattern that the first equipment is generated and shown, institute
Stating stripe pattern includes the first color stripe and the second color stripe of alternate setting;
The stripe pattern is extracted from described first image;
The stripe pattern is converted into tone saturation degree lightness HSV images, and from the HSV images
Isolate chrominance component image;
The stripe direction in the chrominance component image is determined, according to the stripe direction of the determination, scans institute
Chrominance component image is stated, so that it is determined that going out the central point of the first color stripe in the chrominance component image;
The central point of first color stripe determined is clustered, same is belonged to so as to sort out
The central point of first color stripe;
According to the central point for ranging the color stripe of same first, fitting a straight line is carried out, is fitted
Striped linear equation afterwards;
According to the striped linear equation after the fitting, the bar of stripe pattern described in described first image is determined
Line information, the stripe information include at least one of fringe period and striped slope.
2. the method as described in claim 1, it is characterised in that it is described by the stripe pattern from described
Extracted in first image including:
Described first image is converted into tone saturation degree lightness HSV images, and from the HSV images
Isolate lightness component image;
According to the gray value of the pixel of the lightness component image, bar described in the lightness component image is determined
The edge contour of print image;
The edge contour of stripe pattern, determines the stripe pattern according to the lightness component image
Corner location;
According to the corner location of the determination, the stripe pattern is partitioned into from described first image.
3. method as claimed in claim 2, it is characterised in that
The edge contour of the stripe pattern according to the lightness component image, determines the bar graph
The corner location of picture includes:
Fitting a straight line is carried out to the edge contour, obtains the linear equation on each bar side of the edge contour;
Structure and the solid background image of described first image same shape and size, and according to the straight of the side
Line equation, the line segment on the side, the color of the line segment and the back of the body are drawn in the solid background image
The color of scape is different;
According to the color of the line segment and the color of the background, the background image for having the line segment is drawn in scanning,
So that it is determined that go out the intersection point of the line segment, wherein, the color value of the intersection point is the color value of the line segment,
And in the neighborhood territory pixel point of the intersection point, the color value of at least two pairs relative neighborhood territory pixel points is the line segment
Color value;
According to the intersection point of the determination, the corner location of the stripe pattern is determined.
4. the method as described in any one of claims 1 to 3, it is characterised in that described from the HSV
After chrominance component image is isolated in image, the stripe direction according to the determination, the color is scanned
Component image is adjusted, so that it is determined that going out in the chrominance component image before the central point of the first color stripe, institute
Stating method also includes:
According to the stripe direction of the determination, at least one-row pixels point for choosing the chrominance component image is carried out
Scanning, it is determined that the central point of the first color stripe described at least one-row pixels point;
It is determined that gone together described at least one-row pixels point in the central point of the first color stripe it is adjacent in
The distance between heart point;
According to the distance between adjacent central point of the colleague, the estimation width of the striped is determined;
According to the estimation width of the striped, it is determined that convolution kernel is filtered, and according to the filtering convolution kernel, to institute
State chrominance component image and be filtered processing;
The stripe direction according to the determination, the chrominance component image is scanned, so that it is determined that going out described
The central point of the first color stripe includes in chrominance component image:
According to the stripe direction of the determination, the chrominance component image after the filtering process is scanned, so as to really
Make the central point of the first color stripe in the chrominance component image.
5. method as claimed in claim 4, it is characterised in that the striped side according to the determination
To the chrominance component image after the filtering process being scanned, so that it is determined that going out in the chrominance component image
The central point of one color stripe includes:
According to the stripe direction of the determination, the chrominance component image after the filtering process is scanned, searches institute
State the absolute of tone value and the tone value of first color in the first color stripe in chrominance component image
The minimum pixel of difference, and it is minimum from the absolute difference of the tone value and the tone value of first color
Pixel in filter out datum mark;
Search corresponding to the datum mark the absolute of tone value and the tone value of the datum mark in presumptive area
Difference is less than the pixel of predetermined threshold value;
According to the position coordinates of the datum mark, and the tone value and the tone value of the datum mark is absolute
Difference is less than the position coordinates of the pixel of predetermined threshold value, determines the first color bar in the chrominance component image
The position coordinates of the central point of line.
6. method as claimed in claim 4, it is characterised in that described to first face determined
The central point of vitta line is clustered, and is belonged to the central point of the color stripe of same first so as to sort out and is included:
If two points in the central point determined while meeting following three condition, it is determined that this two
Individual point belongs to the color stripe of same first:
Condition 1:Δ x >=-1 or Δ y >=-1
Condition 2:| Δ y | < f*MaxLen
Condition 3:| Δ x | < f*MaxLen
Wherein, Δ x be described two points abscissa difference, Δ y be described two points ordinate difference, f
To be less than 1 preset constant more than 0, MaxLen is the estimation width.
7. the method as described in claim 1, it is characterised in that it is described by the stripe pattern from described
It is described that the stripe pattern is converted into tone saturation degree lightness HSV figures after being extracted in first image
Picture, and before isolating chrominance component image from the HSV images, methods described also includes:
Rotated and/or stretched processing to the stripe pattern extracted;
It is described the stripe pattern is converted into tone saturation degree lightness HSV images to include:
The stripe pattern after the rotation and/or flexible processing is converted into tone saturation degree lightness HSV
Image;
In the striped linear equation according to after the fitting, bar graph described in described first image is determined
After the stripe information of picture, methods described also includes:
According to the rotation and/or flexible processing, reduction treatment is carried out to the stripe information of the determination, with
The stripe information is set to match with original described first image.
A kind of 8. determining device of stripe information in image, it is characterised in that including:
Acquiring unit, for obtaining the first image, described first image includes the first equipment and generates and show
Stripe pattern, the stripe pattern includes the first color stripe and the second color stripe of alternate setting;
Extraction unit, for the stripe pattern to be extracted from described first image;
Separative element, for the stripe pattern to be converted into tone saturation degree lightness HSV images, and from
Chrominance component image is isolated in the HSV images;
First determining unit, for determining the stripe direction in the chrominance component image, according to the determination
Stripe direction, the chrominance component image is scanned, so that it is determined that going out the first face in the chrominance component image
The central point of vitta line;
Sort out unit, for being clustered to the central point of first color stripe determined, so as to return
Class belongs to the central point of the color stripe of same first;
Fitting unit, for ranging the central point of the color stripe of same first according to, carry out straight line
Fitting, the striped linear equation after being fitted;
Second determining unit, for according to the striped linear equation after the fitting, determining described first image
Described in stripe pattern stripe information, the stripe information includes in fringe period and striped slope at least
It is a kind of.
9. device as claimed in claim 8, it is characterised in that the extraction unit is specifically used for:
Described first image is converted into tone saturation degree lightness HSV images, and from the HSV images
Isolate lightness component image;
According to the gray value of the pixel of the lightness component image, bar described in the lightness component image is determined
The edge contour of print image;
The edge contour of stripe pattern, determines the stripe pattern according to the lightness component image
Corner location;
According to the corner location of the determination, the stripe pattern is partitioned into from described first image.
10. device as claimed in claim 9, it is characterised in that
The extraction unit is specifically used for:
Fitting a straight line is carried out to the edge contour, obtains the linear equation on each bar side of the edge contour;
Structure and the solid background image of described first image same shape and size, and according to the straight of the side
Line equation, the line segment on the side, the color of the line segment and the back of the body are drawn in the solid background image
The color of scape is different;
According to the color of the line segment and the color of the background, the background image for having the line segment is drawn in scanning,
So that it is determined that go out the intersection point of the line segment, wherein, in the neighborhood territory pixel point of the intersection point, at least two pairs are relative
Neighborhood territory pixel point color value be the line segment color value;
According to the intersection point of the determination, the corner location of the stripe pattern is determined.
11. the device as described in any one of claim 8 to 10, it is characterised in that described device is also wrapped
Filter unit is included, is used for:
According to the stripe direction of the determination, at least one-row pixels point for choosing the chrominance component image is carried out
Scanning, it is determined that the central point of the first color stripe described at least one-row pixels point;
It is determined that gone together described at least one-row pixels point in the central point of the first color stripe it is adjacent in
The distance between heart point;
According to the distance between adjacent central point of the colleague, the estimation width of the striped is determined;
According to the estimation width of the striped, it is determined that convolution kernel is filtered, and according to the filtering convolution kernel, to institute
State chrominance component image and be filtered processing;
First determining unit is specifically used for:
According to the stripe direction of the determination, the chrominance component image after the filtering process is scanned, so as to really
Make the central point of the first color stripe in the chrominance component image.
12. device as claimed in claim 11, it is characterised in that first determining unit is specifically used
In:
According to the stripe direction of the determination, the chrominance component image after the filtering process is scanned, searches institute
State the absolute of tone value and the tone value of first color in the first color stripe in chrominance component image
The minimum pixel of difference, and it is minimum from the absolute difference of the tone value and the tone value of first color
Pixel in filter out datum mark;
Search corresponding to the datum mark the absolute of tone value and the tone value of the datum mark in presumptive area
Difference is less than the pixel of predetermined threshold value;
According to the position coordinates of the datum mark, and the tone value and the tone value of the datum mark is absolute
Difference is less than the position coordinates of the pixel of predetermined threshold value, determines the first color bar in the chrominance component image
The position coordinates of the central point of line.
13. device as claimed in claim 12, it is characterised in that the classification unit is specifically used for:
If two points in the central point determined while meeting following three condition, it is determined that this two
Individual point belongs to the color stripe of same first:
Condition 1:Δ x >=-1 or Δ y >=-1
Condition 2:| Δ y | < f*MaxLen
Condition 3:| Δ x | < f*MaxLen
Wherein, Δ x be described two points abscissa difference, Δ y be described two points ordinate difference, f
To be less than 1 preset constant more than 0, MaxLen is the estimation width.
14. device as claimed in claim 8, it is characterised in that described device also includes rotary extension list
Member, for the processing that rotated and/or stretched to the stripe pattern extracted;
The separative element is specifically used for:
The stripe pattern after the flexible processing is converted into tone saturation degree lightness HSV images;
The rotary extension unit is additionally operable to:
According to the rotation and/or flexible processing, reduction treatment is carried out to the stripe information of the determination, with
The stripe information is set to match with original described first image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610296958.9A CN107346553A (en) | 2016-05-06 | 2016-05-06 | The determination method and apparatus of stripe information in a kind of image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610296958.9A CN107346553A (en) | 2016-05-06 | 2016-05-06 | The determination method and apparatus of stripe information in a kind of image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107346553A true CN107346553A (en) | 2017-11-14 |
Family
ID=60253246
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610296958.9A Withdrawn CN107346553A (en) | 2016-05-06 | 2016-05-06 | The determination method and apparatus of stripe information in a kind of image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107346553A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110926339A (en) * | 2018-09-19 | 2020-03-27 | 山东理工大学 | Real-time three-dimensional measurement method based on one-time projection structured light parallel stripe pattern |
CN113137937A (en) * | 2021-03-25 | 2021-07-20 | 武汉锐科光纤激光技术股份有限公司 | Method for extracting central line of structured light stripe |
CN113409221A (en) * | 2021-06-30 | 2021-09-17 | 深圳市斯博科技有限公司 | Image color matting method, system, computer equipment and storage medium |
CN116778232A (en) * | 2023-06-01 | 2023-09-19 | 自然资源部国土卫星遥感应用中心 | SAR image vertical stripe detection method, device, equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1512455A (en) * | 2002-12-27 | 2004-07-14 | 中国科学院自动化研究所 | Object three-dimensional model quick obtaining method based on active vision |
CN103292741A (en) * | 2013-05-29 | 2013-09-11 | 哈尔滨工程大学 | Structured light vision measurement method for 3D surface profiles of objects on the basis of K-means color clustering |
CN104504710A (en) * | 2014-12-30 | 2015-04-08 | 中国科学技术大学 | Moore stripe recognition method and device for X-ray grating phase-contrast imaging |
US20150362740A1 (en) * | 2014-06-16 | 2015-12-17 | Samsung Display Co., Ltd. | Stereoscopic image display device |
CN105204173A (en) * | 2015-08-31 | 2015-12-30 | 重庆卓美华视光电有限公司 | View synthesis correction method and device |
-
2016
- 2016-05-06 CN CN201610296958.9A patent/CN107346553A/en not_active Withdrawn
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1512455A (en) * | 2002-12-27 | 2004-07-14 | 中国科学院自动化研究所 | Object three-dimensional model quick obtaining method based on active vision |
CN103292741A (en) * | 2013-05-29 | 2013-09-11 | 哈尔滨工程大学 | Structured light vision measurement method for 3D surface profiles of objects on the basis of K-means color clustering |
US20150362740A1 (en) * | 2014-06-16 | 2015-12-17 | Samsung Display Co., Ltd. | Stereoscopic image display device |
CN104504710A (en) * | 2014-12-30 | 2015-04-08 | 中国科学技术大学 | Moore stripe recognition method and device for X-ray grating phase-contrast imaging |
CN105204173A (en) * | 2015-08-31 | 2015-12-30 | 重庆卓美华视光电有限公司 | View synthesis correction method and device |
Non-Patent Citations (2)
Title |
---|
吴玲玲 等: "组合测量在莫尔条纹中心亚像素定位的应用", 《西安工业大学学报》 * |
李瑜芳: "彩色结构光条纹中心线提取方法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110926339A (en) * | 2018-09-19 | 2020-03-27 | 山东理工大学 | Real-time three-dimensional measurement method based on one-time projection structured light parallel stripe pattern |
CN113137937A (en) * | 2021-03-25 | 2021-07-20 | 武汉锐科光纤激光技术股份有限公司 | Method for extracting central line of structured light stripe |
CN113409221A (en) * | 2021-06-30 | 2021-09-17 | 深圳市斯博科技有限公司 | Image color matting method, system, computer equipment and storage medium |
CN113409221B (en) * | 2021-06-30 | 2023-12-12 | 深圳万兴软件有限公司 | Image color matting method, system, computer equipment and storage medium |
CN116778232A (en) * | 2023-06-01 | 2023-09-19 | 自然资源部国土卫星遥感应用中心 | SAR image vertical stripe detection method, device, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9773302B2 (en) | Three-dimensional object model tagging | |
EP3355104B2 (en) | Method and device and computer program for determining a representation of a spectacle glass rim | |
CN107347152B (en) | The determination method, apparatus and electronic equipment at the grating inclination angle of naked eye 3D display equipment | |
CN107346041B (en) | Method and device for determining grating parameters of naked eye 3D display equipment and electronic equipment | |
TW201724026A (en) | Generating a merged, fused three-dimensional point cloud based on captured images of a scene | |
US8285002B2 (en) | Image processing apparatus and method, image sensing apparatus, and program | |
CN104597057B (en) | A kind of column Diode facets defect detecting device based on machine vision | |
US9332247B2 (en) | Image processing device, non-transitory computer readable recording medium, and image processing method | |
CN107346040B (en) | Method and device for determining grating parameters of naked eye 3D display equipment and electronic equipment | |
KR20100038168A (en) | Composition analysis method, image device having composition analysis function, composition analysis program, and computer-readable recording medium | |
CN109711268B (en) | Face image screening method and device | |
CN107346553A (en) | The determination method and apparatus of stripe information in a kind of image | |
CN112581904B (en) | Moire compensation method for brightness gray scale image of OLED (organic light emitting diode) screen | |
CN106218409A (en) | A kind of can the bore hole 3D automobile instrument display packing of tracing of human eye and device | |
US10091490B2 (en) | Scan recommendations | |
JP3993029B2 (en) | Makeup simulation apparatus, makeup simulation method, makeup simulation program, and recording medium recording the program | |
JP3798161B2 (en) | Fundus measurement device and recording medium recording fundus measurement program | |
WO2016026238A1 (en) | Image border recognition method, device and display panel | |
CN107507137A (en) | A kind of image repair method and system | |
CN109190617A (en) | A kind of rectangle detection method of image, device and storage medium | |
CN113139557A (en) | Feature extraction method based on two-dimensional multivariate empirical mode decomposition | |
CN109410197B (en) | Method and device for positioning detection area of liquid crystal display | |
CN109493293A (en) | A kind of image processing method and device, display equipment | |
KR101513931B1 (en) | Auto-correction method of composition and image apparatus with the same technique | |
CN107181938B (en) | Image display method and equipment, image analysis method, equipment and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20180726 Address after: 518000 Room 201, building A, No. 1, Qian Wan Road, Qianhai Shenzhen Hong Kong cooperation zone, Shenzhen, Guangdong (Shenzhen Qianhai business secretary Co., Ltd.) Applicant after: Shenzhen super Technology Co., Ltd. Address before: 518053 East Guangdong H-1 East 101, overseas Chinese town, Nanshan District, Shenzhen. Applicant before: Shenzhen SuperD Photoelectronic Co., Ltd. |
|
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20171114 |