CN104933390B - Generate the method, apparatus and electronic equipment of skin image - Google Patents
Generate the method, apparatus and electronic equipment of skin image Download PDFInfo
- Publication number
- CN104933390B CN104933390B CN201410102423.4A CN201410102423A CN104933390B CN 104933390 B CN104933390 B CN 104933390B CN 201410102423 A CN201410102423 A CN 201410102423A CN 104933390 B CN104933390 B CN 104933390B
- Authority
- CN
- China
- Prior art keywords
- image
- value
- lighting condition
- skin
- pixel
- 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.)
- Expired - Fee Related
Links
Abstract
The embodiment of the present invention provides a kind of method, apparatus and electronic equipment for generating skin image.The device of the generation skin image of the embodiment of the present invention includes：First determining unit, it is used to determine lighting condition during shooting image；First image generation unit, it uses processing mode corresponding with the lighting condition to generate skin image corresponding with described image.According to an embodiment of the invention, skin image can be generated using different processing modes, thus, clearly skin image can be generated under different lighting conditions according to lighting condition during shooting image.
Description
Technical field
The present invention relates to image processing field, more particularly to a kind of method, apparatus for generating skin image and electronics to set
It is standby.
Background technology
Skin image is the image generated according to the pixel for corresponding to human body skin in image, right in skin image
It should can be highlighted in the pixel of human body skin.With the popularization of video image acquisition equipment, the application of skin image also day
Become extensive.Include recognition of face and detection, Expression Recognition, gesture identification, human body detection, new people than more typical application at present
Machine interfacing etc..
In the remote control technology based on gesture identification, gesture identification equipment first turns the picture of shot by camera
Corresponding skin image is turned to, and detects the hand region of people in skin image, and then by the hand region detected and gesture
Template is matched, and the gesture of people is identified according to matching result, is finally exported by control device according to the gesture of people corresponding
Control signal.
Wherein, the gesture identification equipment of prior art uses below equation（1）Generate skin image,
Skin (x, y)=r (x, y)-((g (x, y)+b (x, y)) ＞ ＞ 1) (1)
In formula（1）In, Skin (x, y) be in the skin image position coordinates for (x, y) pixel pixel value, r (x,
Y), g (x, y), b (x, y) represent respectively position coordinates in the picture of shot by camera as the pixel of (x, y) color-values R values,
G values, B values, " ＞ ＞ 1 " refer to move right the bit number of result of calculation 1；
In the prior art, gesture identification equipment can use below equation（2）Calculate the sum of the absolute value of difference（Sum of
Absolute Differences, SAD）, and the region with minimum SAD is defined as to the hand region of the skin image,
In formula（2）In, Skincurrent(x, y) represents in current skin image position coordinates as the picture of the pixel of (x, y)
Element value, wherein, the position coordinates of pixel in the region of search of the current skin images of (x, y) ∈；Skinprev(x0,y0) represent it is previous
Position coordinates is (x in skin image0,y0) pixel pixel value, wherein, (x0,y0) the previous skin images of ∈ hand region
The position coordinates of middle pixel；Abs represents the computing of " taking absolute value ".
It should be noted that the introduction to technical background above be intended merely to it is convenient technical scheme is carried out it is clear,
Complete explanation, and facilitate the understanding of those skilled in the art and illustrate.Can not merely because these schemes the present invention
Background section is set forth and thinks that above-mentioned technical proposal is known to those skilled in the art.
The content of the invention
At present,, can be according to prior art for the image obtained under normal lighting conditions when generating skin image
Generation clearly skin picture, but the image for being obtained under backlight or low lighting condition, then can not according to prior art
Generate clearly skin image.
The embodiment of the present invention provide it is a kind of generate skin image method, apparatus and electronic equipment, its object is to
Clearly skin image can be generated under different lighting conditions.
First aspect according to embodiments of the present invention, there is provided a kind of device for generating skin image, the device include：
First determining unit, it is used to determine lighting condition during shooting image；
First image generation unit, its use with the lighting condition corresponding to processing mode generation it is corresponding with described image
Skin image.
Second aspect according to embodiments of the present invention, it has the generation skin as described in the first aspect of the embodiment of the present invention
The device of skin image.
The third aspect according to embodiments of the present invention, there is provided a kind of method for generating skin image, this method include：
Determine lighting condition during shooting image；
Skin image corresponding with described image is generated using processing mode corresponding with the lighting condition.
The beneficial effects of the present invention are：Can be according to lighting condition during shooting image, using different processing modes
Skin image is generated, thus, clearly skin image can be generated under different lighting conditions.
With reference to following explanation and accompanying drawing, only certain exemplary embodiments of this invention is disclose in detail, specifies the original of the present invention
Reason can be in a manner of adopted.It should be understood that embodiments of the present invention are not so limited in scope.In appended power
In the range of the spirit and terms that profit requires, embodiments of the present invention include many changes, modifications and are equal.
The feature for describing and/or showing for a kind of embodiment can be in a manner of same or similar one or more
Used in individual other embodiment, it is combined with the feature in other embodiment, or substitute the feature in other embodiment.
It should be emphasized that term "comprises/comprising" refers to the presence of feature, one integral piece, step or component when being used herein, but simultaneously
It is not excluded for the presence or additional of one or more further features, one integral piece, step or component.
Brief description of the drawings
Included accompanying drawing is used for providing being further understood from the embodiment of the present invention, which constitutes one of specification
Point, for illustrating embodiments of the present invention, and the principle for the explaination present invention that comes together with word description.Under it should be evident that
Accompanying drawing in the description of face is only some embodiments of the present invention, for those of ordinary skill in the art, is not paying wound
On the premise of the property made is laborious, other accompanying drawings can also be obtained according to these accompanying drawings.In the accompanying drawings：
Fig. 1 is the composition structure schematic diagram of the device of the generation skin image of the embodiment of the present invention 1；
Fig. 2 is the composition schematic diagram of the first determining unit of the embodiment of the present invention 1；
Fig. 3 is the composition schematic diagram of the first image generation unit of the embodiment of the present invention 2；
Fig. 4 is corresponding skin image under the conditions of the low lighting shooting generated by the way of embodiment 2；
Fig. 5 is corresponding skin image under the conditions of the low lighting shooting using prior art generation；
Fig. 6 is the schematic block diagram that the system of the electronic equipment of the embodiment of the present invention 3 is formed；
Fig. 7 is the method flow diagram of the generation skin image of the embodiment of the present invention 4；
The method flow diagram of lighting condition when Fig. 8 is the determination shooting image of the embodiment of the present invention 4；
Fig. 9 be the embodiment of the present invention 4 low lighting shooting under the conditions of generate skin image method flow diagram
Embodiment
Referring to the drawings, will be apparent by following specification, foregoing and further feature of the invention.In specification
In accompanying drawing, only certain exemplary embodiments of this invention is specifically disclosed, which show the portion for the principle that can wherein use the present invention
Divide embodiment, it will thus be appreciated that the invention is not restricted to described embodiment, on the contrary, the present invention includes falling into appended power
Whole modification, modification and equivalents in the range of profit requirement.
Embodiment 1
Fig. 1 is the composition schematic diagram of the device of the generation skin image of the embodiment of the present invention 1.As shown in figure 1, device 100
Including the first determining unit 101 and the first image generation unit 102.
Wherein, the first determining unit 101 is for determining lighting condition during shooting image, the first image generation unit 102
Skin image corresponding with the image is generated using processing mode corresponding with the lighting condition.
According to an embodiment of the invention 1, the processing mode of image can be determined according to lighting condition, so as in different photographs
Clearly skin image can be generated under the conditions of bright, solves problems of the prior art.
Fig. 2 is the composition schematic diagram of the first determining unit of the embodiment of the present invention 1.As shown in Fig. 2 the first determining unit
101 include the first conversion unit 201, the second determining unit 202, the 3rd determining unit 203 and the 4th determining unit 204.
Wherein, the first conversion unit 201 is used to the image being converted into corresponding gray level image；Second determining unit 202
For the gray value according to pixel in the gray level image, the first parameter K is determined；3rd determining unit 203 is used for according to the gray scale
The gray value of pixel in the first object region of image, determines the second parameter L；4th determining unit is used for according to first parameter
K and the second parameter L and the relation of default threshold value, determine lighting condition.
In the present embodiment, image can be converted into gray-scale map by the first conversion unit 201 by the way of prior art
Picture, the present embodiment repeat no more.
Second determining unit 202 can be according to preceding N1 pixel when gray value arranges from big to small in the gray level image
The average value of gray value, the first parameter K is determined, for example, using formula below（3）First parameter K is determined,
Wherein, gray (x, y) represents the gray value of coordinate in the gray level image as the pixel at (x, y) place, and (x, y) ∈
The coordinate of preceding N1 pixel when gray value arranges from big to small in the gray level image, N1 is positive integer, and N1 can be ash
The 3%-5% of total number of pixels in image is spent, for example, N1 can be 5% of total number of pixels in gray level image；Maximum gradation value can
It is different with the attribute according to the gray level image, for example, the maximum gradation value can be 255 or 128.
When 3rd determining unit 203 can arrange from big to small according to gray value in the first object region of the gray level image
Preceding N2 pixel gray value, determine the second parameter L.For example, the 3rd determining unit 203 can use formula below（5）
Second parameter L is determined,
Wherein, gray (x, y) represents the gray value of coordinate in the gray level image as the pixel at (x, y) place, and (x, y) ∈
The coordinate of N2 pixel, N2 are positive integers before when gray value arranges from big to small in the first object region of the gray level image, and
And N2 can be the 40%-60% of pixel quantity in the first object region；The first object region is included in the gray level image
The region of target subject, for example, the target subject can be human hand or face etc.；N3 is positive integer, and N3 can be
The 20%-30% of pixel quantity in the first object region, such as N3 can be 20% of pixel quantity in the first object region.
4th determining unit 204 can by the first parameter K and/or the second parameter L compared with default threshold value, according to
Comparative result determines the lighting condition.
For example, when first parameter K is less than or equal to first threshold K1, and second parameter L is less than or equal to the 3rd
During threshold value L1, it is backlight to determine the lighting condition, wherein, first threshold K1 can be any value in 1.1-1.3, example
Such as, first threshold K1 can be 1.2, and the 3rd threshold value L1 can be any value in 70-90, for example, the 3rd threshold value
L1 can be 80；
When first parameter K is more than Second Threshold K2, it is low illumination to determine the lighting condition, wherein, second threshold
Value K2 can be any value in 1.5-2.5, for example, Second Threshold K2 can be 2；
When first parameter K is more than the 4th threshold k 3, and is less than or equal to five threshold ks 4, determine that the lighting condition is
Normal illumination, wherein, the 4th threshold k 3 can be any value in 0.9-1.1, for example, the 4th threshold k 3 can be 1,
5th threshold k 4 can be any value in 1.8-2.2, for example, the 5th threshold k 4 can be 2.
Certainly, the 4th determining unit 204 determine lighting condition mode not limited to this, can also basis be actually needed, if
Other criterions are put to determine the lighting condition.
In the present embodiment, the first image generation unit 102 uses the processing mode corresponding with lighting condition to image
Handled, so as to generate skin image corresponding with the image.
Wherein, when it is normal illumination that the first determining unit 101, which determines the lighting condition, the first image generation unit 102
Can be according to the color-values of pixel in the image, skin image corresponding to generation, for example, the first image generation unit 102 can be with
Using above-mentioned formula（1）It is the pixel value Skin (x, y) of the pixel of (x, y) to generate position coordinates in skin image.
When it is backlight that the first determining unit 101, which determines the lighting condition, the first image generation unit 102 can be according to this
The gray value of pixel in the color-values of pixel in image, and gray level image corresponding with the image, generation are corresponding with the image
Skin image.For example, the first image generation unit 102 can use below equation（6）-（7）Generate position in skin image
Coordinate is the pixel value Skin_backlight (x, y) of the pixel of (x, y),
Skin_backlight(x,y)=Skin(x,y)+compensate(x,y) （6）,
Wherein,
Wherein, gray (x, y) represents in the gray level image coordinate as the gray value of the pixel at (x, y) place；N4 is compensation system
Number, wherein, N4 can be any value in 25-35, such as N4 can be 30；Skin (x, y) implication refers to above-mentioned public affairs
Formula（1）.
According to an embodiment of the invention, can be given birth to according to lighting condition during shooting image using different processing modes
Into skin image, thus, clearly skin image can be generated under different lighting conditions.
Embodiment 2
The embodiment of the present invention 2 provides a kind of device for generating skin image.Based on embodiment 1, in the present embodiment, with low
Illustrated under lighting condition exemplified by the structure of the first image generation unit 102, for content same as Example 1 herein not
Repeat, for being described in detail with the different content of embodiment 1.
Fig. 3 is the composition schematic diagram of the first image generation unit of the embodiment of the present invention 2.As shown in figure 3, the first image is given birth to
Include the second conversion unit 301, the 5th determining unit 302 and the second image generation unit 303 into unit 102.
Wherein, the image being continuously shot for being able to detect that target subject is converted into accordingly by the second conversion unit 301
YCbCr images；5th determining unit 302 is according to other frames beyond the first frame of chroma reference value and the YCbCr images
Chromatic value, determine the output chromatic values of other frames；Second image generation unit 303 is according to the output chromatic values of other frames
And brightness value, skin image corresponding to generation.
In addition, in the present embodiment, the device 100 for generating skin image can also have the 6th determining unit（Do not scheme
Show）, it is used for the first frame based on the YCbCr images, determines the chroma reference value.
In the present embodiment, the second conversion unit 301 can will be able to detect that target quilt by the way of prior art
The image being continuously shot for taking the photograph body is converted into YCbCr images, and the present embodiment repeats no more.Wherein, the target subject can be
Human hand or face etc..
In addition, the detection to target subject in image, can be by local binary patterns of the prior art（Local
Binary Patterns, LBP）Grader realizes that the embodiment of the present invention repeats no more.
6th determining unit can according to chromatic value in the second target area of the first frame of the YCbCr images from greatly to
The chromatic value of preceding N5 pixel during minispread, determines the chroma reference value, and second target area is included in first frame
The region of target subject.For example, the 5th determining unit can use following formula（8）-（9）Determine chroma reference value Cbr and
Crr,
Wherein, Cb (x, y), Cr (x, y) represent in first frame coordinate as Cb the and Cr colourities of the pixel of (x, y) respectively
It is worth, the coordinate of preceding N5 pixel when chromatic value Cb or Cr are arranged from big to small in the target areas of (x, y) ∈ second, wherein, N5
Can be the 40%-60% of pixel quantity in second target area；N6 and N7 can be pixel quantity in second target area
20%-30%, for example, N6 and N7 can be 20% of pixel quantity in second target area.
5th determining unit 302 can join according to the chromatic value of other frames outside the frame of YCbCr images first with colourity
The poor absolute value of value, and the first reference value R are examined, determines the output chromatic value of other frames.Be more than as the first reference value R or
During equal to the absolute value, difference of the output chromatic value for the first reference value R and the absolute value is determined, when first reference value is less than
During the absolute value, determine that the output chromatic value is zero.
For example, the 5th determining unit 302 can determine the output chromatic value of each frame in other frames in the following way：
The chromatic value input_Cb (x, y) and input_Cr (x, y) and chroma reference value Cbr of other frames are determined respectively
With Crr poor absolute value, i.e.
temp_cb=abs(input_Cb(x,y)-Cbr) (10)
temp_cr=abs(input_Cr(x,y)-Crr) (11)
When the absolute value is more than the first reference value R, the first reference value R is assigned to the absolute value, otherwise, the absolute value is protected
Hold constant, i.e.
temp_cb>R?R:temp_cb (12)
temp_cr>R?R:temp_cr (13)
Using the difference of the first reference value R and the absolute value as the output chromatic value, i.e.
output_Cb(x,y)=R-temp_cb (14)
output_Cr(x,y)=R-temp_cr (15)
Wherein, output_Cb (x, y) and output_Cr (x, y) is represented in each frame of other frames, and coordinate is (x, y)
Pixel output chromatic value；First reference value R can be any value between 25-35.
Certainly, above citing is example, and the 5th determining unit 302 can also determine to export colourity using other modes
Value.
Second image generation unit 303 can generate other frames according to the brightness value and output chromatic value of other frames
Color-values, and the skin image according to corresponding to the color-values generate other frames.
In the present embodiment, the second image generation unit 303 can use either type of the prior art, according to brightness
Value and output chromatic value generation color-values, so as to which other frames are switched into RGB image from YCbCr images.It is for instance possible to use such as
Lower formula generates color-values
r(x,y)=1.164×(Y(x,y)-16)+1.596×(output_Cr(x,y)-128) (16)
b(x,y)=1.164×(Y(x,y)-16)+2.017×(output_Cb(x,y)-128) (18)
Wherein, Y (x, y) is represented in each frame of other frames, and coordinate is the brightness value of the pixel of (x, y)；r(x,y)、g
(x, y), b (x, y) represent color-values R value, G value, B value of the coordinate as the pixel of (x, y) respectively.
In the present embodiment, the second image generation unit 303 can use the above-mentioned formula of embodiment 1（1）To determine
Skin (x, y), so as to generate skin image.
Fig. 4 is corresponding skin image under the conditions of the low lighting shooting generated by the way of embodiment 2, and Fig. 5 is to use
Corresponding skin image under the conditions of the low lighting shooting of prior art generation.From Fig. 4 and Fig. 5, in low lighting shooting condition
Under, relatively sharp skin image can be generated by the way of embodiment 2.
According to an embodiment of the invention, can be given birth to according to lighting condition during shooting image using corresponding processing mode
Into skin image, thus, under the shooting condition of low illumination, clearly skin image can also be generated.
Embodiment 3
The embodiment of the present invention provides a kind of electronic equipment, and the electronic equipment includes the generation skin as described in embodiment 1~2
The device of image.
Fig. 6 is the schematic block diagram that the system of the electronic equipment 600 of the embodiment of the present invention 3 is formed, and the electronic equipment is for example
It can be the gesture identification equipment for gesture identification.As shown in fig. 6, the electronic equipment 600 can include central processing unit 601
With memory 602；Memory 602 is coupled to central processing unit 601.It is worth noting that, the figure is exemplary；It can also make
With other kinds of structure, to supplement or instead of the structure, to realize telecommunications functions or other functions.
In one embodiment, generating the function of the device of skin image can be integrated into central processing unit 601.
Wherein, central processing unit 601 can be configured as：
Lighting condition during for determining shooting image, and using processing mode corresponding with the lighting condition generation with
Skin image corresponding to described image；
Described image is converted into corresponding gray level image, according to when gray value arranges from big to small in the gray level image
Preceding N1 pixel gray value average value, the first parameter is determined, according to grey in the first object region of the gray level image
The gray value of preceding N2 pixel when angle value arranges from big to small, determines the second parameter, and the first object region is the ash
The region of target subject is included in degree image, when first parameter is less than or equal to first threshold, and second ginseng
When number is less than or equal to three threshold values, it is backlight to determine the lighting condition, when first parameter is more than Second Threshold, really
The fixed lighting condition is low illumination, wherein, the first threshold is 1.1-1.3, and the Second Threshold is 1.5-2.5, described
3rd threshold value is 70-90；
When the lighting condition is backlight, according to the gray value of pixel in gray level image corresponding with described image, with
And in described image pixel color-values, generate the skin image；
When the lighting condition is low illumination, the described image being continuously shot for being able to detect that target subject is turned
Corresponding YCbCr images are turned to, the chroma reference value and described determined according to the first frame based on the YCbCr images
The chromatic value of other frames beyond first frame of YCbCr images, the output chromatic value of other frames is determined, according to described other
The brightness value of frame and the output chromatic value, generate skin image corresponding to other frames；
According to preceding N5 when chromatic value arranges from big to small in the second target area of the first frame of the YCbCr images
The chromatic value of pixel, determines the chroma reference value, and second target area is included in the first frame of the YCbCr images
The region of target subject；
The chromatic value of other frames and the poor absolute value of the chroma reference value are determined, when the first reference value is big
In or during the absolute value, the output chromatic value is the first reference value and the difference of the absolute value, when the absolute value is more than
During first reference value, the output chromatic value is zero；
According to the brightness value of other frames and the output chromatic value, the color-values of other frames are generated, and
The skin image according to corresponding to the color-values generate other frames.
In another embodiment, generate skin image device can with the separate configuration of central processing unit 601, such as
The device for generating skin image can be configured to the chip being connected with central processing unit 601, pass through the control of central processing unit
To realize the function of the device of generation skin image.
In addition, central processing unit 601 can be additionally configured to the skin image according to generation, gesture is identified, on identification
The concrete mode of gesture, it may be referred in the application background technology to the explanation of gesture identification equipment..
As shown in fig. 6, electronic equipment 600 can also include：Communication module 603, input block 604, display 605, electricity
Source 606.Wherein, such as picture of shot by camera etc. can be inputted to the electronic equipment via the input block, in addition, should
Electronic equipment 600 can also use image unit（It is not shown）To replace input block 604, it is possible thereby to directly single by imaging
Member shooting picture；In addition, electronic equipment 600 can also export the result of gesture identification by communication module 603 to miscellaneous equipment
Deng；In addition, electronic equipment 600 can also show picture by display 605.It is worth noting that, user equipment 600 is not yet
It is to have to include all parts shown in Fig. 6；In addition, user equipment 600 can also include the portion being not shown in Fig. 6
Part, it may be referred to prior art.
As shown in fig. 6, central processing unit 601 be otherwise referred to as controller or operational controls, can include microprocessor or
Other processor devices and/or logic device, the central processing unit 601, which receives, to be inputted and controls each portion of user equipment 600
The operation of part.
Wherein, memory 602, such as can be buffer, flash memory, hard disk driver, removable medium, volatile memory, non-
One or more in volatile memory or other appropriate devices.The program performed for information about can be stored.And center
Processor 601 can perform the program of the memory 602 storage, to realize information storage or processing etc..The function of miscellaneous part
With existing similar, here is omitted.Each part of user equipment 600 can pass through specialized hardware, firmware, software or its combination
To realize, it is made without departing from the scope of the present invention.
Embodiment 4
The embodiment of the present invention 4 provides a kind of method for generating skin image, corresponding to the generation skin described in embodiment 1-2
The device of image, repeated no more with embodiment 1-2 identical contents.
Fig. 7 is the method flow diagram of the generation skin image of the embodiment of the present invention 4, and as described in Figure 7, this method includes：
Step 701, lighting condition during shooting image is determined；
Step 702, skin image corresponding with described image is generated using processing mode corresponding with the lighting condition.
The method flow diagram of lighting condition when Fig. 8 is the determination shooting image of the embodiment of the present invention 4, as shown in figure 8, should
Method includes：
Step 801, described image is converted into corresponding gray level image；
Step 802, the ash of preceding N1 pixel when being arranged from big to small according to the gray value of pixel in the gray level image
The average value of angle value, determine the first parameter；
Preceding N2 picture when step 803 arranges from big to small according to gray value in the first object region of the gray level image
The gray value of element, determines the second parameter；
Step 804, when first parameter is less than first threshold, and second parameter is less than three threshold values, really
The fixed lighting condition is backlight, and when first parameter is more than Second Threshold, it is low illumination to determine the lighting condition.
Each step 801-804 specific works mode refer to the specific of corresponding units in embodiment 1-2 in the present embodiment
Working method, here is omitted.
Fig. 9 be the embodiment of the present invention 4 low lighting shooting under the conditions of generate skin image method flow diagram, such as Fig. 9 institutes
Show, this method includes：
Step 901, the described image being continuously shot for being able to detect that target subject is converted into corresponding YCbCr to scheme
Picture；
Step 902, according to the chromatic value of other frames beyond the first frame of chroma reference value and the YCbCr images,
Determine the output chromatic value of other frames；
Step 903, according to the brightness value of other frames and the output chromatic value, skin corresponding to other frames is generated
Skin image.
Each step 901-903 specific works mode refer to the specific work of corresponding units in embodiment 2 in the present embodiment
Make mode, here is omitted.
In addition, in the present embodiment, can be according to pixel in image when it is determined that lighting condition is normal lighting conditions
Color-values, skin image corresponding to generation；When it is determined that lighting condition is for backlight, can according to the color-values of pixel in image,
And in gray level image corresponding with the image pixel gray value, skin image corresponding to generation.Specific works mode can join
The specific works mode of corresponding units in embodiment 1 is examined, here is omitted.
According to an embodiment of the invention, can be given birth to according to lighting condition during shooting image using different processing modes
Into skin image, thus, clearly skin image can be generated under different lighting conditions.
The embodiment of the present invention also provides a kind of computer-readable program, wherein when in information processor or user equipment
When performing described program, described program causes computer to perform the institute of embodiment 4 in described information processing unit or user equipment
The method for the generation skin image stated.
The embodiment of the present invention also provides a kind of storage medium for being stored with computer-readable program, wherein the computer can
Reader causes computer to perform the generation skin image method described in embodiment 4 in information processor or user equipment.
The embodiment of the present invention also provides a kind of computer-readable program, wherein being performed when in information processor or base station
During described program, described program causes computer to perform the generation described in embodiment 4 in described information processing unit or base station
The method of skin image.
The embodiment of the present invention also provides a kind of storage medium for being stored with computer-readable program, wherein the computer can
Reader causes the method that computer performs the generation skin image described in embodiment 4 in information processor or base station.
Apparatus and method more than of the invention can be realized by hardware, can also be realized by combination of hardware software.The present invention
It is related to such computer-readable program, when the program is performed by logical block, can realizes the logical block above
Described device or component parts, or the logical block is realized various methods or step described above.The invention further relates to
For storing the storage medium of procedure above, such as hard disk, disk, CD, DVD, flash memory.
Above in association with specific embodiment, invention has been described, it will be appreciated by those skilled in the art that this
A little descriptions are all exemplary, are not limiting the scope of the invention.Those skilled in the art can be according to the present invention
Spirit and principle various variants and modifications are made to the present invention, these variants and modifications are also within the scope of the invention.
On the embodiment including above example, following note is also disclosed：
（Note 1）A kind of device for generating skin image, the device include：
First determining unit, it is used to determine lighting condition during shooting image；
First image generation unit, its use with the lighting condition corresponding to processing mode generation it is corresponding with described image
Skin image.
（Note 2）Device as described in being attached 1, wherein, first determining unit includes：
First conversion unit, it is used to described image being converted into corresponding gray level image；
Second determining unit, it is used for according to preceding N1 pixel when gray value arranges from big to small in the gray level image
Gray value average value, determine the first parameter, N1 is positive integer；
3rd determining unit, it is used for gray value in the first object region according to the gray level image and arranged from big to small
When preceding N2 pixel gray value, determine the second parameter, the first object region is that target is included in the gray level image
The region of subject, N2 are positive integers；
4th determining unit, it is used for when first parameter is less than or equal to first threshold, and second parameter
During less than or equal to three threshold values, it is backlight to determine the lighting condition, when first parameter is more than Second Threshold, it is determined that
The lighting condition is low illumination.
（Note 3）Device as described in being attached 2, wherein, the first threshold is 1.1-1.3, and the Second Threshold is
1.5-2.5, the 3rd threshold value is 70-90.
（Note 4）Device as described in being attached 1, wherein, when first determining unit determines the lighting condition for the back of the body
Light time, described first image generation unit are and described according to the gray value of pixel in gray level image corresponding with described image
The color-values of pixel in image, generate the skin image.
（Note 5）Device as described in being attached 1, wherein, when first determining unit determines that the lighting condition is low
During illumination, described first image generation unit includes：
Second conversion unit, it is used to the described image being continuously shot for being able to detect that target subject being converted into phase
The YCbCr images answered；
5th determining unit, its be used for according to based on the YCbCr images the first frame determine chroma reference value and
The chromatic value of other frames beyond first frame of the YCbCr images, determine the output chromatic value of other frames；
Second image generation unit, it is used for brightness value and the output chromatic value according to other frames, generates institute
State skin image corresponding to other frames.
（Note 6）Device as described in being attached 5, wherein, the device also includes：
6th determining unit, its be used in the second target area according to the first frame of the YCbCr images chromatic value from
The chromatic value of big preceding N5 pixel when arriving minispread, determines the chroma reference value, second target area is described
The region of target subject is included in first frame of YCbCr images, N5 is positive integer.
（Note 7）Device as described in being attached 5, wherein,
5th determining unit is used to determining the poor of the chromatic values of other frames and the chroma reference value
Absolute value, also, when the first reference value is more than or equal to the absolute value, determine that the output chromatic value is the first reference value
With the difference of the absolute value, when first reference value is less than the absolute value, determine that the output chromatic value is zero.
（Note 8）Device as described in being attached 5, wherein,
The brightness value and the output chromatic value of second image generation unit according to other frames, generate institute
State the color-values of other frames, and the skin image according to corresponding to the color-values generate other frames.
（Note 9）A kind of electronic equipment, it has the device of the generation skin image as described in note 1-8.
（Note 10）A kind of method for generating skin image, this method include：
Determine lighting condition during shooting image；
Skin image corresponding with described image is generated using processing mode corresponding with the lighting condition.
（Note 11）Method as described in being attached 10, wherein it is determined that lighting condition during shooting image includes：
Described image is converted into corresponding gray level image；
According to the average value of the gray value of preceding N1 pixel when gray value arranges from big to small in the gray level image, really
Fixed first parameter, N1 is positive integer；
According to the ash of preceding N2 pixel when gray value arranges from big to small in the first object region of the gray level image
Angle value, the second parameter is determined, the first object region is the region that target subject is included in the gray level image, and N2 is just
Integer；
When first parameter is less than or equal to first threshold, and second parameter is less than or equal to the 3rd threshold value
When, it is backlight to determine the lighting condition, and when first parameter is more than Second Threshold, it is low photograph to determine the lighting condition
It is bright.
（Note 12）Method as described in being attached 11, wherein, the first threshold is 1.1-1.3, and the Second Threshold is
1.5-2.5, the 3rd threshold value is 70-90.
（Note 13）Device as described in being attached 10, wherein, when it is determined that the lighting condition is backlight, generation with it is described
Skin image includes corresponding to image：
According to the gray value of pixel in gray level image corresponding with described image, and in described image pixel color
Value, generates the skin image.
（Note 14）Method as described in being attached 10, wherein, when it is determined that the lighting condition is low illumination, generation and institute
Stating skin image corresponding to image includes：
The described image being continuously shot for being able to detect that target subject is converted into corresponding YCbCr images；
The chroma reference value determined according to the first frame based on the YCbCr images and the first of the YCbCr images
The chromatic value of other frames beyond frame, determine the output chromatic value of other frames；
According to the brightness value of other frames and the output chromatic value, skin image corresponding to other frames is generated.
（Note 15）Method as described in being attached 14, wherein, methods described also includes：
According to preceding N5 when chromatic value arranges from big to small in the second target area of the first frame of the YCbCr images
The chromatic value of pixel, determines the chroma reference value, and second target area is included in the first frame of the YCbCr images
The region of target subject, N5 are positive integers.
（Note 16）Method as described in being attached 14, wherein, according to the first of chroma reference value and the YCbCr images
The chromatic value of other frames beyond frame, determining the output chromatic value of other frames includes：
Determine the chromatic value of other frames and the poor absolute value of the chroma reference value；
When the first reference value is more than or equal to the absolute value, determine that the output chromatic value is the first reference value and institute
The difference of absolute value is stated, when first reference value is less than the absolute value, determines that the output chromatic value is zero.
（Note 17）Method as described in being attached 14, wherein, according to the brightness value of other frames and the output colourity
Value, skin image corresponding to generation other frames include：
According to the brightness value of other frames and the output chromatic value, the color-values of generation other frames；
The skin image according to corresponding to the color-values generate other frames.
Claims (9)
1. a kind of device for generating skin image, the device include：
First determining unit, it is used to determine lighting condition during shooting image；
First image generation unit, it uses processing mode corresponding with the lighting condition to generate skin corresponding with described image
Skin image,
Wherein, first determining unit includes：
First conversion unit, it is used to described image being converted into corresponding gray level image；
Second determining unit, it is used for the ash according to preceding N1 pixel when gray value arranges from big to small in the gray level image
The average value of angle value, determines the first parameter, and N1 is positive integer；
3rd determining unit, it is used for when gray value arranges from big to small in the first object region according to the gray level image
The gray value of preceding N2 pixel, determines the second parameter, and the first object region is to be shot in the gray level image comprising target
The region of body, N2 are positive integers；
4th determining unit, it is used for when first parameter is less than or equal to first threshold, and second parameter is less than
Or during equal to three threshold values, it is backlight to determine the lighting condition, when first parameter is more than Second Threshold, it is determined that described
Lighting condition is low illumination.
2. device as claimed in claim 1, wherein, the first threshold is 1.1-1.3, and the Second Threshold is 1.5-2.5,
3rd threshold value is 70-90.
3. device as claimed in claim 1, wherein, when it is backlight that first determining unit, which determines the lighting condition,
Described first image generation unit is according to the gray value of pixel in gray level image corresponding with described image, and in described image
The color-values of pixel, generate the skin image.
4. device as claimed in claim 1, wherein, when first determining unit determines that the lighting condition is low illumination
When, described first image generation unit includes：
Second conversion unit, it is used to the described image being continuously shot for being able to detect that target subject being converted into accordingly
YCbCr images；
5th determining unit, it is used for the chroma reference value and described determined according to the first frame based on the YCbCr images
The chromatic value of other frames beyond first frame of YCbCr images, determine the output chromatic value of other frames；
Second image generation unit, it is used for brightness value and the output chromatic value according to other frames, generation it is described its
Skin image corresponding to its frame.
5. device as claimed in claim 4, wherein, the device also includes：
6th determining unit, its be used in the second target area according to the first frame of the YCbCr images chromatic value from greatly to
The chromatic value of preceding N5 pixel during minispread, determines the chroma reference value, and second target area is the YCbCr figures
The region of target subject is included in first frame of picture, N5 is positive integer.
6. device as claimed in claim 4, wherein, the 5th determining unit is used for the colourity for determining other frames
The poor absolute value of value and the chroma reference value, also, when the first reference value is more than or equal to the absolute value, determine institute
Output chromatic value is stated as the first reference value and the difference of the absolute value, when first reference value is less than the absolute value, really
The fixed output chromatic value is zero.
7. device as claimed in claim 4, wherein,
The brightness value and the output chromatic value of second image generation unit according to other frames, generation it is described its
The color-values of its frame, and the skin image according to corresponding to the color-values generate other frames.
8. a kind of electronic equipment, it has the device of the generation skin image as any one of claim 1-7.
9. a kind of method for generating skin image, this method include：
Determine lighting condition during shooting image；
Skin image corresponding with described image is generated using processing mode corresponding with the lighting condition,
Wherein it is determined that lighting condition during shooting image includes：
Described image is converted into corresponding gray level image；
According to the average value of the gray value of preceding N1 pixel when gray value arranges from big to small in the gray level image, is determined
One parameter, N1 are positive integers；
According to the gray value of preceding N2 pixel when gray value arranges from big to small in the first object region of the gray level image,
The second parameter is determined, the first object region is the region that target subject is included in the gray level image, and N2 is positive integer；
When first parameter is less than or equal to first threshold, and second parameter is less than or equal to three threshold values, really
The fixed lighting condition is backlight, and when first parameter is more than Second Threshold, it is low illumination to determine the lighting condition.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410102423.4A CN104933390B (en) | 2014-03-19 | 2014-03-19 | Generate the method, apparatus and electronic equipment of skin image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410102423.4A CN104933390B (en) | 2014-03-19 | 2014-03-19 | Generate the method, apparatus and electronic equipment of skin image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104933390A CN104933390A (en) | 2015-09-23 |
| CN104933390B true CN104933390B (en) | 2018-02-13 |
Family
ID=54120551
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410102423.4A Expired - Fee Related CN104933390B (en) | 2014-03-19 | 2014-03-19 | Generate the method, apparatus and electronic equipment of skin image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104933390B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106331513B (en) * | 2016-09-06 | 2017-10-03 | 深圳美立知科技有限公司 | The acquisition methods and system of a kind of high-quality skin image |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103262126A (en) * | 2010-12-09 | 2013-08-21 | 三星电子株式会社 | Image processor, lighting processor and method therefor |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8503800B2 (en) * | 2007-03-05 | 2013-08-06 | DigitalOptics Corporation Europe Limited | Illumination detection using classifier chains |
-
2014
- 2014-03-19 CN CN201410102423.4A patent/CN104933390B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103262126A (en) * | 2010-12-09 | 2013-08-21 | 三星电子株式会社 | Image processor, lighting processor and method therefor |
Non-Patent Citations (2)
| Title |
|---|
| Skin detection in video under changing illumination conditions;Maricor Soriano等;《Pattern Recognition, 2000. Proceedings. 15th International Conference on》;20020806;第839-842页 * |
| 基于DSP与CPLD的实时图像采集与处理***的研究;李超纯;《中国优秀硕士学位论文全文数据库信息科技辑》;20071015(第4期);第1-53页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104933390A (en) | 2015-09-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11948282B2 (en) | Image processing apparatus, image processing method, and storage medium for lighting processing on image using model data | |
| JP6993148B2 (en) | Display device that carries out the video processing method | |
| CN106548455B (en) | Apparatus and method for adjusting brightness of image | |
| US9652893B2 (en) | Stabilization plane determination based on gaze location | |
| WO2019137038A1 (en) | Method for determining point of gaze, contrast adjustment method and device, virtual reality apparatus, and storage medium | |
| KR100845969B1 (en) | The Extraction method of moving object and the apparatus thereof | |
| CN107145871B (en) | It is a kind of can gesture operation intelligent home control system | |
| US10462368B1 (en) | Temporal filtering based on motion detection between temporally non-adjacent pictures | |
| KR20100104371A (en) | Digital image processing apparatus, method for tracking, recording medium storing program to implement the method, and digital image processing apparatus adopting the method | |
| KR20190067438A (en) | Method for providing image and electronic device for supporting the same | |
| KR20180031154A (en) | Display apparatus and method for processing image thereof | |
| US8577141B2 (en) | Method of enhancing contrast using bezier curve | |
| US8451211B2 (en) | Dimming control apparatus and method for generating dimming control signal by referring to distribution information/multiple characteristic values derived from pixel values | |
| CN104933390B (en) | Generate the method, apparatus and electronic equipment of skin image | |
| CN113132639B (en) | Image processing method and device, electronic equipment and storage medium | |
| JP6257268B2 (en) | Image processing apparatus and image processing method | |
| CN110473156A (en) | Processing method, device, storage medium and the electronic equipment of image information | |
| KR20120040386A (en) | 2d-3d image conversion method and stereoscopic image display using the same | |
| CN102005035B (en) | Pseudocolor processing method of B/W (Black/White) video system | |
| JPH08272948A (en) | Method and device for face image processing | |
| CN109961473A (en) | Eyes localization method and device, electronic equipment and computer readable storage medium | |
| JP6953184B2 (en) | Image processing device and image processing method | |
| Zhang et al. | Robust luminance and chromaticity for matte regression in polynomial texture mapping | |
| US11776141B1 (en) | Hybrid image registration techniques | |
| Zhi-Hao et al. | Study on vehicle safety image system optimization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180213 Termination date: 20190319 |