KR101582800B1 - Method for detecting edge in color image adaptively and apparatus and computer-readable recording media using the same - Google Patents
Method for detecting edge in color image adaptively and apparatus and computer-readable recording media using the same Download PDFInfo
- Publication number
- KR101582800B1 KR101582800B1 KR1020140116458A KR20140116458A KR101582800B1 KR 101582800 B1 KR101582800 B1 KR 101582800B1 KR 1020140116458 A KR1020140116458 A KR 1020140116458A KR 20140116458 A KR20140116458 A KR 20140116458A KR 101582800 B1 KR101582800 B1 KR 101582800B1
- Authority
- KR
- South Korea
- Prior art keywords
- value
- color image
- edge
- threshold value
- standard deviation
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000003044 adaptive effect Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 2
- 230000003247 decreasing effect Effects 0.000 claims 2
- 238000007670 refining Methods 0.000 claims 1
- 239000003086 colorant Substances 0.000 abstract 1
- 238000003708 edge detection Methods 0.000 description 11
- 230000000694 effects Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
The present invention relates to a method for adaptively detecting an edge in a color image. (A) obtaining a standard deviation of a color value for a specific region that is at least a partial region of the color image and a standard deviation of a distance value for the distance image corresponding to the color image of the specific region; (b) determining whether a standard deviation of the color value is smaller than a first threshold value and a standard deviation of the distance value is greater than a second threshold value, and if the standard deviation is greater than a second threshold value, determining at least a part of the specific region as a target region; And (c) adjusting a third threshold value that is comparable to a gradient value of the color image for the target area, and detecting the edge having a gradient larger than the adjusted third threshold value as an edge A method of detecting an edge in a color image is provided. According to the present invention, it is possible to detect, in an image, the edge of an area where an edge can not be detected when background and object are similar colors.
Description
The present invention relates to a method of adaptively detecting an edge in a color image, an apparatus using the same, and a computer readable recording medium, and more particularly, to a method of detecting an edge in a color image, The standard deviation of the distance value for the distance image corresponding to the color image of the specific region is obtained and it is determined whether the standard deviation of the color value is smaller than the first threshold value and the standard deviation of the distance value is larger than the second threshold value If it is satisfied, determines at least a part of the specific area as a target area, adjusts a third threshold value that can be compared with a gradient value of the color image for the target area, and adjusts a part having a gradient larger than the adjusted third threshold value as an edge And a computer-readable recording medium.
Edge refers to information indicating the boundary of an area in an image. The edge corresponds to the contour of the object in the image and provides a variety of information such as the position, shape, size, surface pattern of the object, etc., and is detected in order to acquire information in various application fields of the image It is one of the elements.
The edge detection method is mainly based on the calculation of the partial differential operator of the image. The edge detection method uses a matrix-like structure for positioning a certain part in the image, and a square matrix such as 3x3, 5x5, 16x16, Can be detected.
One of the techniques for extracting features of image data obtained through edge detection is to treat gray images of binary data as two data, black and white, using a threshold value. The pixel value of the corresponding output image is set to 1 when brightness of the input image is greater than a predetermined value, and is set to 0 otherwise.
Current edge detection methods include Sobel Mask, Prewitt Mask, Robert Mask, Laplacian Mask, Canny Edge Detection, and the like.
However, the current edge detection method has a problem in that the edge can not be detected in a region having a similar color. In addition, there is a problem in that the edge can not be accurately discriminated from the image.
Accordingly, the present inventor proposes a technique capable of detecting an edge in a color image adaptively by solving the above problems.
The present invention aims at solving all of the above problems.
It is another object of the present invention to easily detect an edge through adjustment of a threshold value in a region having a similar color in a color image.
In order to accomplish the objects of the present invention as described above and achieve the characteristic effects of the present invention described below, the characteristic structure of the present invention is as follows.
According to an aspect of the present invention, there is provided a method for calculating a standard deviation of a color image, the method comprising: (a) obtaining a standard deviation of a color value for a specific region that is at least a partial region of the color image and a standard deviation of a distance value for the distance image, (B) determining whether a standard deviation of the color value is smaller than a first threshold value and a standard deviation of the distance value is greater than a second threshold value, and if the standard deviation is greater than a second threshold value, ; And (c) adjusting a third threshold value that is comparable to a gradient value of the color image for the target area, and detecting the edge having a gradient larger than the adjusted third threshold value as an edge A method of detecting an edge in a color image is provided.
According to another aspect of the present invention, there is provided an apparatus for adaptively detecting an edge in a color image, the apparatus comprising: a standard deviation of a color value for a specific area, which is at least a partial area of the color image, A standard deviation of the distance value for the distance image is obtained, and if the standard deviation of the color value is smaller than the first threshold value and the standard deviation of the distance value is greater than the second threshold value, And a third threshold value that can be compared with a gradient value of a color image with respect to the target area, and detects a portion having a gradient larger than the adjusted third threshold value as an edge And an adaptive edge detector for detecting the edge of the image.
In addition, a computer readable recording medium for recording a computer program for executing the method of the present invention is further provided.
The present invention has the effect of accurately detecting an edge even in a region having a similar color in a color image.
1 is a block diagram showing a configuration of an apparatus for adaptively detecting an edge in a color image according to an embodiment of the present invention.
2 is a flow chart illustrating a method for adaptively detecting an edge in a color image in accordance with an embodiment of the present invention.
3 illustrates an exemplary method for adaptively detecting an edge in a color image according to an embodiment of the present invention.
The following detailed description of the invention refers to the accompanying drawings, which illustrate, by way of illustration, specific embodiments in which the invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the invention. It should be understood that the various embodiments of the present invention are different, but need not be mutually exclusive. For example, certain features, structures, and characteristics described herein may be implemented in other embodiments without departing from the spirit and scope of the invention in connection with an embodiment. It is also to be understood that the position or arrangement of the individual components within each disclosed embodiment may be varied without departing from the spirit and scope of the invention. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope of the present invention is to be limited only by the appended claims, along with the full scope of equivalents to which such claims are entitled, if properly explained. In the drawings, like reference numerals refer to the same or similar functions throughout the several views.
Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings, so that those skilled in the art can easily carry out the present invention.
FIG. 1 shows an arrangement of an apparatus for adaptively detecting an edge in a color image according to an embodiment of the present invention. The
The object
The adaptive
Specifically, the
On the other hand, the adaptive
Meanwhile, the blurring application unit may blur the color image by applying a predetermined filter to the color image. This is to reduce the noise of the image and prevent the erroneous edge from being extracted. In general, Gaussian filters are used in many cases, but noise reduction algorithms such as bilateral filters and total variation denoising can also be used in some cases.
Of course, the blurring application unit may provide the blurred color image to the target
Next, the edge refinement section can apply an edge thinning process to the edge portion detected by the adaptive
FIG. 2 illustrates a method of adaptively detecting an edge in a color image according to an embodiment of the present invention.
First, in order to adaptively detect an edge in a color image, a standard deviation of a color value for a specific region (for example, an area of a block unit) which is at least a partial region of the
Of course, prior to step (a), a filter may be applied to the color image to blur the
Next, it is determined whether or not the standard deviation (? C ) of the color value is smaller than the first threshold value (?) And the standard deviation? D of the distance value is greater than the second threshold value (B) at least a part of the specific area is determined as a target area if the above condition is satisfied. This is because an area having a large difference in distance value is selected in an area having a similar color and the area is determined as a target area. Here, when the above condition is satisfied, the specific area itself may be determined as the target area, but a part of the specific area may be determined as the target area (for example, if necessary, only the center area excluding the border part of the specific area It may be assumed that the target area is determined).
Next, the gradation value of the
Of course, when the third threshold value is adjusted, the third threshold value may be set with reference to the maximum value and the minimum value of the gradient in the target area to lower the value. For example, if the average of the maximum value and the minimum value of the gradient is set to the third threshold value in the target area, the average of the maximum value and the minimum value of the gradient is changed each time the target area is changed. Therefore, The threshold value is set to the third threshold value.
At this time,
Expression can be calculated by using the (x, y is a variable), of course, it would also be G is calculated using the angle θ = atan2 (G y, G x) function forms, and the like.On the other hand, when it is determined whether the standard deviation [sigma] c of the color value is smaller than the first threshold value [alpha] and the standard deviation [sigma] d of the distance value is greater than the second threshold value [ The edge may be detected by comparing the third threshold value with the gradient value of the color image for the specific region in a state in which the third threshold value is not adjusted.
Next, an edge thinning process may be applied to the detected edge portion so that the edge detected as bold may be composed of one pixel. Of course, the non-maximum value suppression may be performed.
FIG. 3 shows an example of adaptively detecting an edge in a color image according to an embodiment of the present invention. In FIG. 3, an area of a plurality of blocks in the color image 100 (that is, A
On the other hand, two graphs are shown on the rightmost side of FIG. 3, and the horizontal axis of each graph is a scan direction along a solid line traversing a block located immediately to the left of the graph and a vertical axis is a gradient value measured along the scan direction . More specifically, the graph of the two rightmost graphs in FIG. 3 shows the degree to which the gradient of the color image varies according to the scanning direction, and the graph below shows a gradient of the distance image according to the scanning direction The degree of fluctuation is shown. It should be noted that the degree of variation of the gradient with respect to the distance image in the present invention does not need to be confirmed but is shown for convenience. 3, the dotted line in the line indicated by the third threshold value is a threshold value before the present invention is applied, and the threshold value lowered by applying the present invention, Value is a third threshold value indicated by a solid line. That is, the area where the standard deviation (? C ) of the color value is smaller than the first threshold value (?) And the standard deviation (? D ) of the distance value is larger than the second threshold value (? Since the change of the gradation of the color image will not be large, it is difficult to detect the edge only by the existing third threshold value. Therefore, the third threshold value is lowered (lowered, not unconditionally lowered, So that the edge can be detected accurately.
The embodiments of the present invention described above can be implemented in the form of program instructions that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program commands, data files, data structures, and the like, alone or in combination. The program instructions recorded on the computer-readable recording medium may be those specially designed and constructed for the present invention or may be those known to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tape, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, media, and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like. Examples of program instructions include machine language code such as those generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules for performing the processing according to the present invention, and vice versa.
While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, Those skilled in the art will appreciate that various modifications, additions and substitutions are possible, without departing from the scope and spirit of the invention as disclosed in the accompanying claims.
Therefore, the spirit of the present invention should not be construed as being limited to the above-described embodiments, and all of the equivalents or equivalents of the claims, as well as the following claims, I will say.
10: Edge detection device
100: Color image
200: Street image
Claims (11)
(a) obtaining a standard deviation of a color value for a specific region that is at least a partial region of the color image and a standard deviation of a distance value for the distance image corresponding to the color image of the specific region;
(b) determining whether a standard deviation of the color value is smaller than a first threshold value and a standard deviation of the distance value is greater than a second threshold value, and if the standard deviation is greater than a second threshold value, determining at least a part of the specific region as a target region; And
(c) if a determination is made that at least a portion of the specific region is a target region, reducing a third threshold that is comparable to a gradient value of the color image for the determined target region, and Detecting a portion as an edge
≪ / RTI >
The step (c)
And decreasing the third threshold value to a value set with reference to a maximum value and a minimum value of the gradients in the target area.
In the step (b)
If the standard deviation of the color value is smaller than the first threshold value and the standard deviation of the distance value is greater than the second threshold value,
The step (c)
Wherein the edge is detected by comparing the third threshold value with the gradient value of the color image for the specific region without adjusting the third threshold value.
Before the step (a)
Further comprising applying a filter to the color image to blur the color image.
After the step (c)
And applying an edge thinning process to the detected edge portion.
A standard deviation of a color value for a specific region which is at least a partial region of the color image and a standard deviation of a distance value for a distance image corresponding to the color image of the specific region, Determining a standard deviation of the distance value to be greater than a second threshold value and determining at least a part of the specific region as a target region if the standard deviation is less than a second threshold; And
A third threshold value which can be compared with a gradient value of the color image for the determined target area is reduced when at least a part of the specific area is determined as the target area and a part having a gradient larger than the reduced third threshold value is defined as an edge And an adaptive edge detector
/ RTI >
Wherein the adaptive edge detector comprises:
And decreasing the third threshold value to a value set with reference to a maximum value and a minimum value of the gradients in the target area.
The target area determining unit
If the standard deviation of the color value is smaller than the first threshold value and the standard deviation of the distance value is greater than the second threshold value and it is determined that the standard deviation is not satisfied,
Wherein the adaptive edge detector comprises:
And detects an edge by comparing the third threshold value with the gradient value of the color image for the specific region without adjusting the third threshold value.
Further comprising a blurring application unit for blurring the color image by applying a filter to the color image,
Wherein the blurring application unit provides the blurred color image to the object area determination unit to calculate a standard deviation of the color value and a standard value of a distance value for the distance image corresponding to the color image, And a deviation is obtained.
And an edge refining unit applying an edge thinning process to the detected edge portion.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020140116458A KR101582800B1 (en) | 2014-09-02 | 2014-09-02 | Method for detecting edge in color image adaptively and apparatus and computer-readable recording media using the same |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020140116458A KR101582800B1 (en) | 2014-09-02 | 2014-09-02 | Method for detecting edge in color image adaptively and apparatus and computer-readable recording media using the same |
Publications (1)
Publication Number | Publication Date |
---|---|
KR101582800B1 true KR101582800B1 (en) | 2016-01-19 |
Family
ID=55306191
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020140116458A KR101582800B1 (en) | 2014-09-02 | 2014-09-02 | Method for detecting edge in color image adaptively and apparatus and computer-readable recording media using the same |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR101582800B1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101988555B1 (en) * | 2017-12-05 | 2019-06-12 | 충북대학교 산학협력단 | Simultaneous localization and mapping system using illumination invariant image, and method for mapping pointcloud thereof |
KR102143918B1 (en) * | 2019-08-13 | 2020-08-12 | 숭실대학교산학협력단 | Apparatus and method for detecting LED edge based on adaptive threshold |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR0141308B1 (en) * | 1994-07-29 | 1998-06-15 | 배순훈 | Method for detection the contour and device thereof |
KR20050025927A (en) * | 2003-09-08 | 2005-03-14 | 유웅덕 | The pupil detection method and shape descriptor extraction method for a iris recognition, iris feature extraction apparatus and method, and iris recognition system and method using its |
KR101051459B1 (en) * | 2010-05-31 | 2011-07-22 | 한양대학교 산학협력단 | Apparatus and method for extracting edges of an image |
KR20120014876A (en) * | 2010-08-10 | 2012-02-20 | 삼성전자주식회사 | Image processing apparatus and method |
-
2014
- 2014-09-02 KR KR1020140116458A patent/KR101582800B1/en active IP Right Grant
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR0141308B1 (en) * | 1994-07-29 | 1998-06-15 | 배순훈 | Method for detection the contour and device thereof |
KR20050025927A (en) * | 2003-09-08 | 2005-03-14 | 유웅덕 | The pupil detection method and shape descriptor extraction method for a iris recognition, iris feature extraction apparatus and method, and iris recognition system and method using its |
KR101051459B1 (en) * | 2010-05-31 | 2011-07-22 | 한양대학교 산학협력단 | Apparatus and method for extracting edges of an image |
KR20120014876A (en) * | 2010-08-10 | 2012-02-20 | 삼성전자주식회사 | Image processing apparatus and method |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101988555B1 (en) * | 2017-12-05 | 2019-06-12 | 충북대학교 산학협력단 | Simultaneous localization and mapping system using illumination invariant image, and method for mapping pointcloud thereof |
KR102143918B1 (en) * | 2019-08-13 | 2020-08-12 | 숭실대학교산학협력단 | Apparatus and method for detecting LED edge based on adaptive threshold |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | Image contrast enhancement using adjacent-blocks-based modification for local histogram equalization | |
CN111080661B (en) | Image-based straight line detection method and device and electronic equipment | |
JP4871144B2 (en) | Image processing apparatus, method, and program | |
CN108830873B (en) | Depth image object edge extraction method, device, medium and computer equipment | |
KR101051459B1 (en) | Apparatus and method for extracting edges of an image | |
CN111833366A (en) | Edge detection method based on Canny algorithm | |
US9727984B2 (en) | Electronic device and method for processing an image | |
JP2007140684A (en) | Image processor, method and program | |
US10026156B2 (en) | Information processing apparatus, information processing method, and medium | |
CN111047615B (en) | Image-based straight line detection method and device and electronic equipment | |
JP6254938B2 (en) | Image noise removing apparatus and image noise removing method | |
JP2012038318A (en) | Target detection method and device | |
KR101684990B1 (en) | Method for deblurring vehicle image using sigma variation of Bilateral Filter | |
WO2014069103A1 (en) | Image processing device | |
US9299131B2 (en) | Noise reduction apparatus, noise reduction method, and computer-readable storage medium | |
US8559716B2 (en) | Methods for suppressing structured noise in a digital image | |
US8571343B2 (en) | Methods and systems for document-image correction | |
KR101582800B1 (en) | Method for detecting edge in color image adaptively and apparatus and computer-readable recording media using the same | |
US20190370974A1 (en) | Information processing apparatus, robot system, information processing method, and program | |
JP6198114B2 (en) | Image processing program, image processing method, and image processing apparatus | |
JP6256703B2 (en) | Image processing method and image processing apparatus | |
KR101617551B1 (en) | Image processing method and system for improving face detection | |
CN107862679B (en) | Method and device for determining image detection area | |
KR101881795B1 (en) | Method for Detecting Edges on Color Image Based on Fuzzy Theory | |
Krylov et al. | Image enhancement by non-iterative grid warping |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
E701 | Decision to grant or registration of patent right | ||
GRNT | Written decision to grant | ||
FPAY | Annual fee payment |
Payment date: 20181120 Year of fee payment: 4 |