KR101373471B1 - Apparatus and method for compensation of stereo image - Google Patents

Apparatus and method for compensation of stereo image Download PDF

Info

Publication number
KR101373471B1
KR101373471B1 KR1020120114205A KR20120114205A KR101373471B1 KR 101373471 B1 KR101373471 B1 KR 101373471B1 KR 1020120114205 A KR1020120114205 A KR 1020120114205A KR 20120114205 A KR20120114205 A KR 20120114205A KR 101373471 B1 KR101373471 B1 KR 101373471B1
Authority
KR
South Korea
Prior art keywords
color
image
histogram
color gamut
target
Prior art date
Application number
KR1020120114205A
Other languages
Korean (ko)
Inventor
이성주
이동준
Original Assignee
세종대학교산학협력단
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 세종대학교산학협력단 filed Critical 세종대학교산학협력단
Priority to KR1020120114205A priority Critical patent/KR101373471B1/en
Application granted granted Critical
Publication of KR101373471B1 publication Critical patent/KR101373471B1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N13/10—Processing, recording or transmission of stereoscopic or multi-view image signals
    • H04N13/106—Processing image signals
    • H04N13/122—Improving the 3D impression of stereoscopic images by modifying image signal contents, e.g. by filtering or adding monoscopic depth cues
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N13/10—Processing, recording or transmission of stereoscopic or multi-view image signals
    • H04N13/106—Processing image signals
    • H04N13/133—Equalising the characteristics of different image components, e.g. their average brightness or colour balance
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
    • H04N13/10—Processing, recording or transmission of stereoscopic or multi-view image signals
    • H04N13/106—Processing image signals
    • H04N13/15—Processing image signals for colour aspects of image signals

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Image Processing (AREA)

Abstract

The present invention relates to a stereo image correction apparatus and a method thereof, and a stereo image correction apparatus according to an embodiment of the present invention includes an image acquisition unit for acquiring a reference image and a target image photographed from different angles with respect to a target object; A matching histogram generator for generating a color histogram for each of the acquired images, a color gamut dividing unit for dividing the generated color histogram into one or more color gamuts, and a color gamut of the target image and the reference image And an image corrector configured to correct the target image using RGB average values of pixels corresponding to the same color gamut.
Accordingly, by dividing the image using the color histogram for the two images of the target object to correct the color only between the same color region, it is possible to perform a more accurate color correction while maintaining the inherent brightness difference between the regions.

Description

Stereo image correction device and method thereof {APPARATUS AND METHOD FOR COMPENSATION OF STEREO IMAGE}

The present invention relates to a stereo image correction apparatus and a method thereof, and more particularly, a technique of correcting color by dividing an image into a plurality of regions is disclosed.

The stereo image is an image captured using a stereo camera. Substantially, two images obtained by photographing a target object from different angles through two cameras are generated as one stereoscopic image. In this case, the stereo image is to correct the color in the process of generating two images as one image.

In the conventional color correction method of the stereo image, the color is corrected by comparing the average brightness of pixels for the entire image. That is, a method of correcting an error based on an average brightness is used by comparing the brightness of all pixels of the first image and the brightness of all pixels of the second image of the target object.

However, in the conventional color correction method, since the color is corrected only by considering the brightness of the entire image to remove noise components, there is a problem in that it is not effective to correct the color difference of the image itself.

The background technology of the present invention is disclosed in Republic of Korea Patent Publication No. 10-0886323 (2009. 02. 23 registration).

The technical problem to be solved by the present invention is to provide a stereo image correction apparatus and method for correcting color by dividing an image using a color histogram for two images of the target object.

An apparatus for compensating stereo images according to an exemplary embodiment of the present invention may include an image acquisition unit configured to acquire a reference image and a target image of a stereo image photographed at different angles with respect to a target object, and the obtained reference image and target image. A histogram generator for generating a color histogram, a color gamut divider for dividing the generated color histogram into one or more color gamuts, a color gamut of the target image and a color gamut of the reference image, and the same color gamut And an image corrector configured to correct the target image by using an RGB average value of pixels corresponding to.

In addition, the histogram generator, converts the RGB (Red Green Blue) value for each pixel of the image to the CIE (Commission Internationale de I'Eclairage) LCH (Lightness Chroma, Hue) coordinates, and the converted CIE LCH Color histograms can be created using the color values of the coordinates.

The color gamut dividing unit may set a color gamut included in a preset area around each maxima of the plurality of maxima of the color histogram to the same color gamut as the maxima.

The image corrector may match the same color gamut by comparing the width or width of the color gamut of the reference image with the color gamut of the target image.

The apparatus may further include a filtering unit which removes noise of the generated color histogram.

In accordance with another aspect of the present invention, there is provided a method of compensating a stereo image, the method comprising: obtaining a reference image and a target image of a stereo image photographed at different angles with respect to a target object; Generating a histogram, dividing the generated color histogram into one or more color gamuts, matching a color gamut of the target image with a color gamut of the reference image, and matching the RGB of pixels corresponding to the same color gamut; Correcting the target image using an average value.

Accordingly, by dividing the image using the color histogram for the two images of the target object to correct the color only between the same color region, it is possible to perform a more accurate color correction while maintaining the inherent brightness difference between the regions.

1 is a block diagram of a stereo image correction apparatus according to an embodiment of the present invention,
2 is a flowchart of a stereo image correcting method of the stereo image correcting apparatus according to FIG. 1;
FIG. 3 is an exemplary diagram illustrating segmenting a color gamut using a color histogram of the stereo image correcting method according to FIG. 2;
FIG. 4 is an exemplary diagram for describing matching of a color gamut of a color histogram of a reference image and a target image in the stereo image correcting method according to FIG. 2.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. The terms used are terms selected in consideration of the functions in the embodiments, and the meaning of the terms may vary depending on the user, the intention or the precedent of the operator, and the like. Therefore, the meaning of the terms used in the following embodiments is defined according to the definition when specifically defined in this specification, and unless otherwise defined, it should be interpreted in a sense generally recognized by those skilled in the art.

1 is a block diagram of a stereo image correction apparatus according to an embodiment of the present invention, Figure 2 is a flow chart of a stereo image correction method of the stereo image correction apparatus according to FIG.

1 and 2, the stereo image correcting apparatus 100 according to an embodiment of the present invention includes an image acquisition unit 110, a histogram generator 120, a color gamut division unit 130, and an image correction unit. 140.

First, the image acquirer 110 acquires a reference image and a target image of a stereo image photographed at different angles with respect to a target object (S200). Here, the stereo image means an image photographed using a 3D stereo camera such as a stereo camera. In addition, the reference image is an image that is a reference for image correction, and the target image refers to an image whose image is to be corrected. The reference image and the target image are photographed with different parallaxes for the same object, and the photographing angle of the target object is different.

Next, the histogram generator 120 generates a color histogram for each of the reference image and the target image (S210). Here, the color histogram refers to a histogram in which a color value of a pixel is represented by a value between 0 and 360. For example, the histogram generator 120 converts a red green blue (RGB) value of a pixel included in each of a reference image and a target image into a coordinate internationale de l'eclairage (CIE) lightness chroma (hue) coordinate. A color histogram is generated using the color values of the converted CIE LCH coordinates. Accordingly, the RGB value of the pixel in which the color information is represented by the tertiary domain of the x-axis, the y-axis, and the z-axis may be expressed in the one-dimensional domain between 0 and 360.

Next, the color gamut divider 130 divides each color histogram of the reference image and the target image into one or more color gamuts (S220). Here, the color gamut refers to an area that is considered to have the same color (Hue) value. That is, the color histogram for each image has various color values between 0 and 360, but the same color value is set for the same object component.

For example, the color gamut divider 130 may set a color gamut included in a preset area around each maxima among a plurality of maxima of the color histogram as the same color gamut as the maxima. When the color histogram of the image has a maximum point at the color value 100, the neighboring color values 97, 98, 99, 101, 102, and 103 may be set to be the same color gamut as the color value 100.

More specifically, the color gamut divider 130 may divide the color gamut by using a maximum point climbing technique. In the example above, the number of pixels of color value 97 is compared with the number of pixels of color value 98, and if the number of pixels of color value 98 is large, the maximum value is searched while increasing the color value, and the number of pixels of color value 97 is the color value. If it is less than 98 pixels, the maximum value is searched while reducing the color value. In this case, when the number of pixels of the color value 97 is larger than the number of pixels of the color value 96 and the color value 98, the number of pixels of the color value 97 is set to the maximum point. Therefore, the color histogram of each image may be divided into a plurality of color regions centered on the plurality of maximum points.

Next, the image corrector 140 matches the color gamut of the target image with the color gamut of the reference image, and corrects the target image by using RGB average values of pixels corresponding to the same color gamut (S230). Pixels set to the same color gamut in the color histogram are considered to be the same object component in the actual image. Therefore, the RGB average value between the color gamut 1 of the reference image and the pixel included in the color gamut 1 of the target image is calculated, and the error is corrected by using the calculated RGB average value of the pixel of the target image.

For example, the image corrector 140 may match the same color area by comparing the width or width of the color area of the reference image with the color area of the target image. That is, color regions having the same size or the same width for the range of color values among the color regions may be matched with each other. This compares the color gamut of the reference image with the color gamut of the target image.

On the other hand, the stereo image correction device 100 according to another embodiment of the present invention further includes a filtering unit (not shown). For example, the filtering unit may use a low pass filter (LPF). The filtering unit is used to reduce the number of maximum points and to reduce the number of color regions when the maximum points are excessively increased due to the noise component of the image in the color histogram.

FIG. 3 is an exemplary diagram for describing segmentation of a color gamut using a color histogram of the stereo image correction method according to FIG. 2.

Referring to FIG. 3, in the color histogram, the x-axis represents the color value and the y-axis represents the number of pixels. In this case, the area of color values around the maximum point (a, b, c, d, e) of the color histogram is set to the same color area as the maximum point (a, b, c, d, e) by the maximum point tracking technique. do. Therefore, since the maximum points a, b, c, d, and e are five, the color gamuts to be divided are also set to five. In addition, the widths of the color gamuts, which are range sizes of the x-axis values of the respective color gamuts, may be different. The color gamut serves as a criterion for distinguishing an area for correcting an RGB value of a pixel in a process of later correcting an RGB value. Therefore, the error is not corrected by calculating the average value of the RGB values for the entire region of the reference image and the target image, but the error is corrected by calculating the RGB average value between the divided images of each image included in the same color region.

FIG. 4 is an exemplary diagram for describing matching of a color gamut of a color histogram of a reference image and a target image in the stereo image correcting method according to FIG. 2.

Referring to FIG. 4, since the stereo image uses the reference image and the target image photographed at different angles with respect to the target object, the color regions of the color histograms are not the same with respect to the color values. In this case, the width or width of the color gamut of each color histogram may be used to match the color gamut. For example, the plurality of color regions set from the color histogram of the reference image are a, b, c, d, and e, and the plurality of color regions set from the color histogram of the target image are a ', b', c ', d. In the case of ', e', a-a ', b-b', c-c ', d-d', and e-e 'are color regions corresponding to each other and their widths are the same. Therefore, the color area a 'of the target image and a of the plurality of color areas a, b, c, d, and e of the reference image are matched with a.

In the above example, the average value of the RGB value of the pixel is calculated for each color gamut pair of a-a ', b-b', c-c ', d-d', and e-e ', and the RGB value of the target image is calculated. The target image is generated as a final color-corrected image by correcting an error based on the calculated RGB average value.

Meanwhile, embodiments of the present invention can be implemented by computer readable codes on a computer readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored.

Examples of the computer-readable recording medium include a ROM, a RAM, a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device and the like, and also a carrier wave (for example, transmission via the Internet) . In addition, the computer-readable recording medium may be distributed over network-connected computer systems so that computer readable codes can be stored and executed in a distributed manner. And functional programs, codes, and code segments for implementing the present invention can be easily deduced by programmers skilled in the art to which the present invention pertains.

As described above, according to an exemplary embodiment of the present invention, two images of a target object are divided by using a color histogram to correct colors only between the same color areas, thereby maintaining more accurate color correction while maintaining inherent brightness differences between the areas. can do.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, Therefore, the present invention should be construed as a description of the claims which are intended to cover obvious variations that can be derived from the described embodiments.

100: stereo image correction device
110: image acquisition unit
120: histogram generator
130: color gamut divider
140: image correction unit

Claims (10)

An image obtaining unit obtaining a reference image and a target image of the stereo image photographed at different angles with respect to the target object;
A histogram generator which generates a color histogram with respect to the obtained reference image and the target image;
A color gamut dividing unit dividing the generated color histogram into one or more color gamuts; And
And an image corrector configured to match the color gamut of the target image and the color gamut of the reference image to correct the target image by using RGB average values of pixels corresponding to the same color gamut. The method of claim 1,
The histogram generator,
The RGB (Red Green Blue) value of each obtained pixel of the image is converted into a CIE (Commission Internationale de I'Eclairage) LCH (Lightness Chroma, Hue) coordinate, and the color value of the converted CIE LCH coordinate is used. Stereo image correction device for generating color histograms. The method of claim 1,
The color gamut division unit,
An area of color values adjacent to each other among the plurality of maximum points of the color histogram is set to the same color area as the maximum point, and the boundaries between the divided color areas are located at the minimum points between the adjacent maximum points. Corresponding stereo image correction device. The method of claim 1,
Wherein the image correction unit comprises:
And matching the same color gamut by comparing the width or width of the color gamut of the reference image with the color gamut of the target image. The method of claim 1,
And a filtering unit to remove noise of the generated color histogram. In the image correction method of the stereo image correction device,
Obtaining a reference image and a target image of the stereo image photographed at different angles with respect to the target object;
Generating a color histogram of the obtained reference image and the target image;
Dividing the generated color histogram into one or more color regions; And
And matching the color gamut of the target image with the color gamut of the reference image, and correcting the target image using RGB average values of pixels corresponding to the same color gamut. The method according to claim 6,
Generating the color histogram,
The RGB (Red Green Blue) value of each obtained pixel of the image is converted into a CIE (Commission Internationale de I'Eclairage) LCH (Lightness Chroma, Hue) coordinate, and the color value of the converted CIE LCH coordinate is used. Stereo image correction method to generate color histogram. The method according to claim 6,
The dividing into one or more color spaces may include:
An area of color values adjacent to each other among the plurality of maximum points of the color histogram is set to the same color area as the maximum point, and the boundaries between the divided color areas are located at the minimum points between the adjacent maximum points. Corresponding stereo image correction method. The method according to claim 6,
Correcting the target image,
And matching the same color gamut by comparing the width or width of the color gamut of the reference image with the color gamut of the target image. The method according to claim 6,
And removing noise of the generated color histogram.
KR1020120114205A 2012-10-15 2012-10-15 Apparatus and method for compensation of stereo image KR101373471B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020120114205A KR101373471B1 (en) 2012-10-15 2012-10-15 Apparatus and method for compensation of stereo image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020120114205A KR101373471B1 (en) 2012-10-15 2012-10-15 Apparatus and method for compensation of stereo image

Publications (1)

Publication Number Publication Date
KR101373471B1 true KR101373471B1 (en) 2014-03-13

Family

ID=50648469

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020120114205A KR101373471B1 (en) 2012-10-15 2012-10-15 Apparatus and method for compensation of stereo image

Country Status (1)

Country Link
KR (1) KR101373471B1 (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20150125244A (en) * 2014-04-30 2015-11-09 주식회사 이에스엠연구소 Color correcting method for image of multiview cameras and color correction system for image of multiview cameras
US9449252B1 (en) * 2015-08-27 2016-09-20 Sony Corporation System and method for color and brightness adjustment of an object in target image
KR20170125859A (en) * 2015-05-22 2017-11-15 후아웨이 테크놀러지 컴퍼니 리미티드 Apparatus and method for color correction
CN117094966A (en) * 2023-08-21 2023-11-21 青岛美迪康数字工程有限公司 Tongue image identification method and device based on image amplification and computer equipment

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20060045441A (en) * 2004-04-01 2006-05-17 마이크로소프트 코포레이션 Luminance correction
KR20060063575A (en) * 2004-12-06 2006-06-12 한국전자통신연구원 Apparatus and method for correction of the image distortion of stereo-camera
JP2007110638A (en) 2005-10-17 2007-04-26 Nikon Corp Object analyzing apparatus, imaging apparatus, and image processing program
JP2010016803A (en) 2008-06-04 2010-01-21 Toa Corp Apparatus and method for adjusting colors among multiple color cameras

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20060045441A (en) * 2004-04-01 2006-05-17 마이크로소프트 코포레이션 Luminance correction
KR20060063575A (en) * 2004-12-06 2006-06-12 한국전자통신연구원 Apparatus and method for correction of the image distortion of stereo-camera
JP2007110638A (en) 2005-10-17 2007-04-26 Nikon Corp Object analyzing apparatus, imaging apparatus, and image processing program
JP2010016803A (en) 2008-06-04 2010-01-21 Toa Corp Apparatus and method for adjusting colors among multiple color cameras

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20150125244A (en) * 2014-04-30 2015-11-09 주식회사 이에스엠연구소 Color correcting method for image of multiview cameras and color correction system for image of multiview cameras
KR101633436B1 (en) * 2014-04-30 2016-06-24 주식회사 이에스엠연구소 Color correcting method for image of multiview cameras and color correction system for image of multiview cameras
KR20170125859A (en) * 2015-05-22 2017-11-15 후아웨이 테크놀러지 컴퍼니 리미티드 Apparatus and method for color correction
KR101944208B1 (en) 2015-05-22 2019-01-30 후아웨이 테크놀러지 컴퍼니 리미티드 Apparatus and method for color correction
US10291823B2 (en) 2015-05-22 2019-05-14 Huawei Technologies Co., Ltd. Apparatus and method for color calibration
US9449252B1 (en) * 2015-08-27 2016-09-20 Sony Corporation System and method for color and brightness adjustment of an object in target image
CN117094966A (en) * 2023-08-21 2023-11-21 青岛美迪康数字工程有限公司 Tongue image identification method and device based on image amplification and computer equipment
CN117094966B (en) * 2023-08-21 2024-04-05 青岛美迪康数字工程有限公司 Tongue image identification method and device based on image amplification and computer equipment

Similar Documents

Publication Publication Date Title
KR101125765B1 (en) Apparatus and method for registration between color channels based on depth information of image taken by multiple color filter aperture camera
US10003779B2 (en) Multi-area white-balance control device, multi-area white-balance control method, multi-area white-balance control program, computer in which multi-area white-balance control program is recorded, multi-area white-balance image-processing device, multi-area white-balance image-processing method, multi-area white-balance image-processing program, computer in which multi-area white-balance image-processing program is recorded, and image-capture apparatus
US9489751B2 (en) Image processing apparatus and image processing method for color correction based on pixel proximity and color similarity
WO2015165222A1 (en) Method and device for acquiring panoramic image
US9378564B2 (en) Methods for color correcting digital images and devices thereof
US10248843B2 (en) Image processing apparatus and method for removing a facial object
US20170091909A1 (en) Image processing method and device
KR101373471B1 (en) Apparatus and method for compensation of stereo image
KR101364860B1 (en) Method for transforming stereoscopic images for improvement of stereoscopic images and medium recording the same
CN112887693B (en) Image purple border elimination method, equipment and storage medium
US20140043434A1 (en) Image processing apparatus
JP6825617B2 (en) Image processing equipment, imaging equipment, and image processing methods, and programs
WO2012159586A1 (en) Color distortion correction method and device for imaging systems and image output systems
KR101874538B1 (en) Method and Apparatus for Processing Image to Simultaneously Enhance Contrast and Saturation of Image
US20110205390A1 (en) Signal processing device and imaging device
KR101477736B1 (en) Apparatus and method for white point estimation based dark channel prior for auto white balance
KR101227082B1 (en) Apparatus and method for color balancing of multi image stitch
WO2014050689A1 (en) Image processing device
Rosenthal et al. Preserving dynamic range by advanced color histogram matching in stereo vision
EP3740932A1 (en) Image demosaicing system and method
JP2004274482A (en) Image processing apparatus and imaging system
KR102315200B1 (en) Image processing apparatus for auto white balance and processing method therefor
JP7278234B2 (en) Image processing device
Moriyama et al. Illuminant color estimation method based on pseudo-detection of specular reflection
JP7308051B2 (en) Multi-view video color matching device and its program

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E90F Notification of reason for final refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 20170209

Year of fee payment: 4

FPAY Annual fee payment

Payment date: 20180220

Year of fee payment: 5

LAPS Lapse due to unpaid annual fee