US20080212843A1 - Pet eye correction - Google Patents
Pet eye correction Download PDFInfo
- Publication number
- US20080212843A1 US20080212843A1 US11/971,988 US97198808A US2008212843A1 US 20080212843 A1 US20080212843 A1 US 20080212843A1 US 97198808 A US97198808 A US 97198808A US 2008212843 A1 US2008212843 A1 US 2008212843A1
- Authority
- US
- United States
- Prior art keywords
- pixels
- pupil
- color
- region
- defect
- 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.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/46—Colour picture communication systems
- H04N1/56—Processing of colour picture signals
- H04N1/60—Colour correction or control
- H04N1/62—Retouching, i.e. modification of isolated colours only or in isolated picture areas only
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/46—Colour picture communication systems
- H04N1/56—Processing of colour picture signals
- H04N1/60—Colour correction or control
- H04N1/62—Retouching, i.e. modification of isolated colours only or in isolated picture areas only
- H04N1/624—Red-eye correction
Definitions
- the invention relates to digital image corrections and more particularly relates to pupil color-corrections.
- red eye and pet eye include the term “eye”, the discoloration from the red eye and pet eye conditions actually occurs in the pupils of humans and animals, respectively. Accordingly, the term “eye” in this art often is intended to refer to “pupil,” as opposed to an entire eye.
- a digital image of a dog may represent the dog's pupils as being green in color.
- Conventional human red eye correction procedures that rely upon detecting pixels of a red color, however, are not useful for correcting these pet eye conditions.
- Another pet eye condition is referred to as a white eye or cue ball condition. In this case the entire pupil appears white or light in color similar to the color of a glint.
- a location in the pupil within the digital image is identified, and a target color to be corrected is computed based at least upon an analysis of pixels within a first region in which the location resides.
- Defect pixels in a second region in which the location resides are identified, the defect pixels being identified as having a pixel color similar to the target color.
- the defect pixels are color-corrected.
- a presumed pupil region is identified, and an appropriately configured pupil image is inserted into the pupil region.
- FIG. 1 illustrates a system for correcting color defects in a pupil represented in a digital image, according to an embodiment of the present invention
- FIG. 2 illustrates a method for correcting color defects in a pupil represented in a digital image, according to an embodiment of the present invention
- FIGS. 3 and 4 illustrate a method for correcting color defects in a pupil represented in a digital image at least by replacing the pupil region with an image of a pupil, according to an embodiment of the present invention.
- Embodiments of the present invention facilitate the color-correction of pupils regardless of the particular color of discoloration present in the pupil in a digital image. Accordingly, such embodiments are useful for, among other things, correcting human red eye conditions, pet eye conditions, or both.
- FIG. 1 illustrates a system 100 for correcting color defects in a pupil represented in a digital image, according to an embodiment of the present invention.
- the system 100 includes a data processing system 110 , an interface system 130 , and a processor-accessible memory system 140 .
- the processor-accessible memory system 140 and the interface system 130 are communicatively connected to the data processing system 110 .
- the data processing system 110 includes one or more data processing devices that implement the processes of the various embodiments of the present invention, including the processes illustrated by FIGS. 2-4 .
- the phrases “data processing device”, “data processor”, or “processor” are intended to include any data processing device, such as a central processing unit (“CPU”), a desktop computer, a laptop computer, a mainframe computer, a personal digital assistant, a BlackberryTM, a digital camera, cellular phone, or any other device for processing data, managing data, or handling data, whether implemented with electrical, magnetic, optical, biological components, or otherwise.
- CPU central processing unit
- BlackberryTM a digital camera
- cellular phone or any other device for processing data, managing data, or handling data, whether implemented with electrical, magnetic, optical, biological components, or otherwise.
- the processor-accessible memory system 140 includes one or more processor-accessible memories configured to store information, including the information needed to execute the processes of the various embodiments of the present invention, including the processes illustrated by FIGS. 2-4 .
- the processor-accessible memory system 140 may be a distributed processor-accessible memory system including multiple processor-accessible memories communicatively connected to the data processing system 110 via a plurality of computers or devices.
- the processor-accessible memory system 140 need not be a distributed processor-accessible memory system and, consequently, may include one or more processor-accessible memories located within a single data processor or device.
- processor-accessible memory is intended to include any processor-accessible data storage device, whether volatile or nonvolatile, electronic, magnetic, optical, or otherwise, including but not limited to, hard disks, Compact Discs, DVDs, flash memories, ROMs, and RAMs.
- the phrase “communicatively connected” is intended to include any type of connection, whether wired or wireless, between devices, data processors, or programs in which data may be communicated. Further, the phrase “communicatively connected” is intended to include a connection between devices or programs within a single data processor, a connection between devices or programs located in different data processors, and a connection between devices not located in data processors at all.
- the processor-accessible memory system 140 is shown separately from the data processing system 110 , one skilled in the art will appreciate that the processor-accessible memory system 140 may be stored completely or partially within the data processing system 110 .
- the interface system 130 is shown separately from the data processing system 110 , one skilled in the art will appreciate that the interface system 130 may be located completely or partially within the data processing system 110 .
- the interface system 130 may include a mouse, a keyboard, another data processor, or any device or combination of devices from which data is input to the data processing system 110 .
- the interface system 130 also may include a display device, a processor-accessible memory, or any device or combination of devices to which data is output by the data processing system 110 .
- the interface system 130 includes a processor-accessible memory or memory system, such memory or memory system may be part of the processor-accessible memory system 140 even though the interface system 130 and the processor-accessible memory system 140 are shown separately in FIG. 1 .
- FIG. 2 illustrates a method for correcting color defects in a pupil represented in a digital image, according to an embodiment of the present invention.
- FIG. 2 represents a digital image 200 of a pet, in this case, a cat.
- the digital image 200 represents two pupils (or pupil regions) 201 , 202 of the cat that have been discolored during the process of acquiring the digital image 200 .
- Such discoloring is represented in FIG. 2 by the dot-shaded regions in the pupils 201 , 202 .
- Each pupil 201 , 202 has a different amount of dot-shading, indicating that each pupil 201 , 202 may be discolored differently.
- Pupil discoloration often is caused by the firing of a light flash by the digital image-acquisition device that captured the digital image 200 .
- specular highlights 203 , 204 also referred to as glint
- Specular highlights 203 , 204 are represented in FIG. 2 as 4 -point stars for illustration purposes.
- specular highlights may take other shapes in a pupil represented in a digital image.
- a location within the pupil is identified.
- the discoloration in the pupil 201 is being corrected, and the identified location within the pupil 201 is marked by the “X” 205 .
- pupil 201 is being corrected in the example of FIG. 2
- pupil 202 may be corrected in the same manner as pupil 201 .
- location 205 is shown merely for illustration purposes, and one of ordinary skill in the art will appreciate that location 205 may be any place where pupil discoloration is located or substantially adjacently located.
- Location 205 in the discolored pupil 201 may be identified based at least upon user input. Alternatively, location 205 may be identified based at least upon a data-processor-executed search for a pupil that exhibits expected discoloration attributes using techniques known in the art.
- a target color to be corrected may be computed based at least upon an analysis of pixels within a first region of pixels in which the identified location resides.
- the first region is shown as rectangle 206 .
- the first region may be a local neighborhood of pixels, such as a 3 ⁇ 3 neighborhood, a 3 ⁇ 4 neighborhood, a 5 ⁇ 5 neighborhood, etc.
- the first region may merely include only a single pixel at which the identified location (e.g., 205 ) resides.
- the first region may include the entire region of pupil discoloration (dot-shaded region 201 , e.g.).
- the invention is not limited to any particular choice of the size and shape of the first region, so long as the first region includes the identified location (e.g., 205 ) and is not too large so as to substantially skew a proper determination of the target color, as discussed below.
- the target color aims to accurately represent the color of the discoloration present in the respective pupil (e.g., 201 ). Accordingly, the target color may be computed in any manner that sufficiently identifies the color of the discoloration to be corrected, such as by analyzing the pixels in a first region in which the identified location ( 205 , e.g.) resides. Such an analysis may include determining an average of pixel color values of at least some of the pixels within the first region. However, one skilled in the art will appreciate that other statistical or mathematical analyses may be performed.
- some embodiments of the present invention exclude pixels representing specular highlights in the analysis of the pixels in the first region. Because specular highlights ( 203 , e.g.) are extremely bright, they may unduly skew the target color towards brighter colors when present in the first region. Similarly, to the extent that the first region ( 205 , e.g.) includes other non-uniformities, such as uncharacteristically dark or uncharacteristically different colors, such other non-uniformities also may be excluded. In the example of FIG. 2 , the first region 206 includes a corner region 208 outside of the pupil 201 . Consequently, corner region 208 may include pixels that exhibit substantially different color characteristics than many or most of the other pixels within the first region 206 . Accordingly, the corner region 208 also may be excluded in the analysis of pixels in the first region 206 when computing the target color.
- defect pixels may be identified in a second region in which the identified location ( 205 , e.g.) resides.
- the defect pixels are the pixels that ultimately undergo color correction.
- the second region is represented by circle 207 , which includes the entire pupil 201 .
- the second region may include less than all of an entire pupil being corrected, such as, for example, a region or regions in or around the pupil that have a significant probability of needing correction.
- the second region may be the same as the first region, or that the second region may entirely include the first region. However, as shown in FIG.
- first region 208 of first region 206 needs to be within the second region ( 207 , e.g.).
- second region 207 in FIG. 2 is shown to be a circle for illustration purposes only, one skilled in the art will appreciate that the second region, as well as pupils, may have other shapes, such as ellipses.
- the defect pixels may be identified as those pixels within the second region exhibiting a difference in color with respect to the target color within a threshold.
- the defect pixels may be identified as those pixels that have a color close to the target color, where the threshold determines the required amount of closeness.
- pixels representing specular highlights may be excluded as defect pixels, so that they remain uncorrected.
- other pixels exhibiting large differences in color from the target color may be excluded as defect pixels, so that they too remain uncorrected.
- a threshold used for identifying defect pixels may be user-defined and may be user-adjustable.
- each defect pixel is corrected to have red, green, and blue color values equal to a minimum of the corresponding defect pixel's pre-corrected red, green, and blue color values. For example, if a defect pixel, prior to correction, exhibits red, green, and blue color values of 15, 10, and 180, respectively, the defect pixel may be corrected so that its red, green, and blue color values are 10, 10, and 10, respectively.
- an optional blending step may be performed, where pixels in a third region in which the second region resides are blended.
- This optional blending step facilitates a more natural appearance of the color-corrected defect pixels within the context of the rest of the digital image ( 200 , e.g.).
- the third region may be the same as the second region. This is true in the example of FIG. 2 , where the third region is the same as the second region 207 and, consequently, is not explicitly shown. Alternatively, the third region may be somewhat larger than the second region. For example, if a kernel, such as a 5 ⁇ 5 pixel kernel, is used to blend pixels, the kernel may be used to cause blending in pixels slightly outside and around the border of the second region.
- FIGS. 3 and 4 illustrate a method for correcting color defects in a pupil represented in a digital image at least by replacing a presumed pupil region with an image of a pupil, according to an embodiment of the present invention.
- This and related embodiments are useful for correcting a pupil that appears all or substantially all white.
- This is a condition referred to as a ‘cue ball.’ Pupils exhibiting a cue ball condition appear to be missing their pupils. The cue ball condition often occurs in pet pupils, but one skilled in the art will appreciate that the following procedure may be used for any pupil experiencing the cue ball condition.
- FIGS. 3 and 4 is similar to the example of FIG. 2 in that it represents a digital image 300 of a cat.
- the cat includes two pupils 301 , 302 that are experiencing the cue ball condition.
- an expected pupil-location is identified.
- the cue ball condition in the pupil 301 is being corrected, and the expected pupil-location is marked by the “X” 303 .
- pupil 301 is being corrected in the example of FIG. 3
- pupil 302 may be corrected in the same manner as pupil 301 .
- the location 303 is shown merely for illustration purposes, and one of ordinary skill in the art will appreciate that location 303 may be anywhere in or substantially adjacent where the pupil 301 was expected to be located.
- Location 303 may be identified based at least upon user input. Alternatively, location 303 may be identified based at least upon a data-processor-executed search for an expected pupil-location in an eye using techniques known in the art.
- the particular region may include the expected pupil-location.
- the particular region is shown as rectangle 304 .
- the particular region may be a local neighborhood of pixels, such as a 3 ⁇ 3 neighborhood, a 3 ⁇ 4 neighborhood, a 5 ⁇ 5 neighborhood, etc.
- the particular region may include the entire eye being evaluated ( 305 , e.g.).
- the invention is not limited to any particular choice of the size and shape of the particular region, so long as the particular region includes the expected pupil-location ( 303 , e.g.) and is not too large so as to substantially skew a proper determination of the cue ball condition.
- a presumed pupil region is identified.
- the presumed pupil region is identified by circle 401 .
- the presumed pupil region ( 401 , e.g.) may be identified based at least upon an analysis of the type of animal or person whose pupil is being corrected, as well as the relative size and shape of the pupil being corrected ( 301 , e.g.).
- an image of a pupil appropriate ( 402 , e.g.) for the animal or person whose pupil is being corrected is identified.
- Such pupil image is appropriately scaled and then inserted into the presumed pupil region to facilitate correcting the cue ball condition.
- an image of an iris also may be included with the pupil image inserted into the presumed pupil region.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
Description
- This application claims the benefit of U.S. Provisional Application No. 60/879,737, filed Jan. 10, 2007, the entire disclosure of which is hereby incorporated herein by reference.
- The invention relates to digital image corrections and more particularly relates to pupil color-corrections.
- Animals, such as pets, often have the equivalent of human red eye in pictures, hereafter also referred to as “pet eye,” but with different colors. Although the phrases red eye and pet eye include the term “eye”, the discoloration from the red eye and pet eye conditions actually occurs in the pupils of humans and animals, respectively. Accordingly, the term “eye” in this art often is intended to refer to “pupil,” as opposed to an entire eye. For example, a digital image of a dog may represent the dog's pupils as being green in color. In addition, sometimes even the two pupils of an animal have different colors. Conventional human red eye correction procedures that rely upon detecting pixels of a red color, however, are not useful for correcting these pet eye conditions. Another pet eye condition is referred to as a white eye or cue ball condition. In this case the entire pupil appears white or light in color similar to the color of a glint.
- It would thus be desirable to provide a solution or improved solution for overcoming or mitigating these pet eye conditions.
- Systems and methods for correcting color defects in a pupil represented in a digital image are disclosed. According to some embodiments of the present invention, a location in the pupil within the digital image is identified, and a target color to be corrected is computed based at least upon an analysis of pixels within a first region in which the location resides. Defect pixels in a second region in which the location resides are identified, the defect pixels being identified as having a pixel color similar to the target color. The defect pixels are color-corrected. By computing a target color, from which the defect pixels are identified and color-corrected, any pupil discoloration color can be corrected, including human red eye and the various other colors that show up in pet eye conditions. In addition, a single process may be used to correct both human red eye and pet eye conditions.
- According to some embodiments of the present invention, for a pupil that appears all white, a presumed pupil region is identified, and an appropriately configured pupil image is inserted into the pupil region.
- The present invention will be more readily understood from the detailed description of exemplary embodiments presented below considered in conjunction with the attached drawings, of which:
-
FIG. 1 illustrates a system for correcting color defects in a pupil represented in a digital image, according to an embodiment of the present invention; -
FIG. 2 illustrates a method for correcting color defects in a pupil represented in a digital image, according to an embodiment of the present invention; and -
FIGS. 3 and 4 illustrate a method for correcting color defects in a pupil represented in a digital image at least by replacing the pupil region with an image of a pupil, according to an embodiment of the present invention. - It is to be understood that the attached drawings are for purposes of illustrating the concepts of the invention and may not be to scale.
- Embodiments of the present invention facilitate the color-correction of pupils regardless of the particular color of discoloration present in the pupil in a digital image. Accordingly, such embodiments are useful for, among other things, correcting human red eye conditions, pet eye conditions, or both.
- It should be noted that the invention is inclusive of combinations of the embodiments described herein. References to a particular embodiment and the like refer to features that are present in at least one embodiment of the invention. Separate references to an embodiment or particular embodiments or the like do not necessarily refer to the same embodiment or embodiments; however, such embodiments are not mutually exclusive, unless otherwise explicitly noted or required by context. The use of singular or plural in referring to the “method” or “methods”, “system” or “systems”, and the like is not limiting. Further, it should be noted that, unless otherwise explicitly noted or required by context, the word “or” is used in this disclosure in a non-exclusive sense.
-
FIG. 1 illustrates asystem 100 for correcting color defects in a pupil represented in a digital image, according to an embodiment of the present invention. Thesystem 100 includes adata processing system 110, aninterface system 130, and a processor-accessible memory system 140. The processor-accessible memory system 140 and theinterface system 130 are communicatively connected to thedata processing system 110. - The
data processing system 110 includes one or more data processing devices that implement the processes of the various embodiments of the present invention, including the processes illustrated byFIGS. 2-4 . The phrases “data processing device”, “data processor”, or “processor” are intended to include any data processing device, such as a central processing unit (“CPU”), a desktop computer, a laptop computer, a mainframe computer, a personal digital assistant, a Blackberry™, a digital camera, cellular phone, or any other device for processing data, managing data, or handling data, whether implemented with electrical, magnetic, optical, biological components, or otherwise. - The processor-
accessible memory system 140 includes one or more processor-accessible memories configured to store information, including the information needed to execute the processes of the various embodiments of the present invention, including the processes illustrated byFIGS. 2-4 . The processor-accessible memory system 140 may be a distributed processor-accessible memory system including multiple processor-accessible memories communicatively connected to thedata processing system 110 via a plurality of computers or devices. On the other hand, the processor-accessible memory system 140 need not be a distributed processor-accessible memory system and, consequently, may include one or more processor-accessible memories located within a single data processor or device. - The phrase “processor-accessible memory” is intended to include any processor-accessible data storage device, whether volatile or nonvolatile, electronic, magnetic, optical, or otherwise, including but not limited to, hard disks, Compact Discs, DVDs, flash memories, ROMs, and RAMs.
- The phrase “communicatively connected” is intended to include any type of connection, whether wired or wireless, between devices, data processors, or programs in which data may be communicated. Further, the phrase “communicatively connected” is intended to include a connection between devices or programs within a single data processor, a connection between devices or programs located in different data processors, and a connection between devices not located in data processors at all. In this regard, although the processor-
accessible memory system 140 is shown separately from thedata processing system 110, one skilled in the art will appreciate that the processor-accessible memory system 140 may be stored completely or partially within thedata processing system 110. Further in this regard, although theinterface system 130 is shown separately from thedata processing system 110, one skilled in the art will appreciate that theinterface system 130 may be located completely or partially within thedata processing system 110. - The
interface system 130 may include a mouse, a keyboard, another data processor, or any device or combination of devices from which data is input to thedata processing system 110. Theinterface system 130 also may include a display device, a processor-accessible memory, or any device or combination of devices to which data is output by thedata processing system 110. In this regard, if theinterface system 130 includes a processor-accessible memory or memory system, such memory or memory system may be part of the processor-accessible memory system 140 even though theinterface system 130 and the processor-accessible memory system 140 are shown separately inFIG. 1 . -
FIG. 2 illustrates a method for correcting color defects in a pupil represented in a digital image, according to an embodiment of the present invention. In this regard,FIG. 2 represents adigital image 200 of a pet, in this case, a cat. In this example, thedigital image 200 represents two pupils (or pupil regions) 201, 202 of the cat that have been discolored during the process of acquiring thedigital image 200. Such discoloring is represented inFIG. 2 by the dot-shaded regions in thepupils pupil pupil digital image 200. Also often caused by such firing of a light flash arespecular highlights 203, 204 (also referred to as glint) inpupils Specular highlights FIG. 2 as 4-point stars for illustration purposes. However, one of ordinary skill in the art will appreciate that specular highlights may take other shapes in a pupil represented in a digital image. - In order to correct the discoloration in a pupil, according to an embodiment of the present invention, a location within the pupil is identified. In the example of
FIG. 2 , the discoloration in thepupil 201 is being corrected, and the identified location within thepupil 201 is marked by the “X” 205. Althoughpupil 201 is being corrected in the example ofFIG. 2 , one of ordinary skill in the art will appreciate thatpupil 202 may be corrected in the same manner aspupil 201. Also, thelocation 205 is shown merely for illustration purposes, and one of ordinary skill in the art will appreciate thatlocation 205 may be any place where pupil discoloration is located or substantially adjacently located. -
Location 205 in thediscolored pupil 201 may be identified based at least upon user input. Alternatively,location 205 may be identified based at least upon a data-processor-executed search for a pupil that exhibits expected discoloration attributes using techniques known in the art. - Upon identification of a location in a discolored pupil, a target color to be corrected may be computed based at least upon an analysis of pixels within a first region of pixels in which the identified location resides. In the example of
FIG. 2 , the first region is shown asrectangle 206. The first region may be a local neighborhood of pixels, such as a 3×3 neighborhood, a 3×4 neighborhood, a 5×5 neighborhood, etc. Alternatively, the first region may merely include only a single pixel at which the identified location (e.g., 205) resides. Alternatively still, the first region may include the entire region of pupil discoloration (dot-shadedregion 201, e.g.). Accordingly, one skilled in the art will appreciate that the invention is not limited to any particular choice of the size and shape of the first region, so long as the first region includes the identified location (e.g., 205) and is not too large so as to substantially skew a proper determination of the target color, as discussed below. - The target color aims to accurately represent the color of the discoloration present in the respective pupil (e.g., 201). Accordingly, the target color may be computed in any manner that sufficiently identifies the color of the discoloration to be corrected, such as by analyzing the pixels in a first region in which the identified location (205, e.g.) resides. Such an analysis may include determining an average of pixel color values of at least some of the pixels within the first region. However, one skilled in the art will appreciate that other statistical or mathematical analyses may be performed.
- To facilitate a proper identification of the target color, some embodiments of the present invention exclude pixels representing specular highlights in the analysis of the pixels in the first region. Because specular highlights (203, e.g.) are extremely bright, they may unduly skew the target color towards brighter colors when present in the first region. Similarly, to the extent that the first region (205, e.g.) includes other non-uniformities, such as uncharacteristically dark or uncharacteristically different colors, such other non-uniformities also may be excluded. In the example of
FIG. 2 , thefirst region 206 includes acorner region 208 outside of thepupil 201. Consequently,corner region 208 may include pixels that exhibit substantially different color characteristics than many or most of the other pixels within thefirst region 206. Accordingly, thecorner region 208 also may be excluded in the analysis of pixels in thefirst region 206 when computing the target color. - After determining the target color, defect pixels may be identified in a second region in which the identified location (205, e.g.) resides. The defect pixels are the pixels that ultimately undergo color correction. In the example of
FIG. 2 , the second region is represented bycircle 207, which includes theentire pupil 201. One of ordinary skill in the art, however, will appreciate that the second region may include less than all of an entire pupil being corrected, such as, for example, a region or regions in or around the pupil that have a significant probability of needing correction. Also, one of ordinary skill in the art will appreciate that the second region may be the same as the first region, or that the second region may entirely include the first region. However, as shown inFIG. 2 , not all of the first region (corner region 208 offirst region 206, e.g.) needs to be within the second region (207, e.g.). In addition, although thesecond region 207 inFIG. 2 is shown to be a circle for illustration purposes only, one skilled in the art will appreciate that the second region, as well as pupils, may have other shapes, such as ellipses. - According to an embodiment of the present invention, the defect pixels may be identified as those pixels within the second region exhibiting a difference in color with respect to the target color within a threshold. In other words, the defect pixels may be identified as those pixels that have a color close to the target color, where the threshold determines the required amount of closeness. In this regard, pixels representing specular highlights may be excluded as defect pixels, so that they remain uncorrected. Similarly, other pixels exhibiting large differences in color from the target color may be excluded as defect pixels, so that they too remain uncorrected. A threshold used for identifying defect pixels may be user-defined and may be user-adjustable.
- After identifying the defect pixels, color correction may be performed on the defect pixels. According to an embodiment of the present invention, the defect pixels are modified so that they are more neutral in color. Or, the defect pixels may be modified so that they are neutral or substantially neutral in color. In some embodiments, each defect pixel is corrected to have red, green, and blue color values equal to a minimum of the corresponding defect pixel's pre-corrected red, green, and blue color values. For example, if a defect pixel, prior to correction, exhibits red, green, and blue color values of 15, 10, and 180, respectively, the defect pixel may be corrected so that its red, green, and blue color values are 10, 10, and 10, respectively.
- After color-correcting the defect pixels, an optional blending step may be performed, where pixels in a third region in which the second region resides are blended. This optional blending step facilitates a more natural appearance of the color-corrected defect pixels within the context of the rest of the digital image (200, e.g.). The third region may be the same as the second region. This is true in the example of
FIG. 2 , where the third region is the same as thesecond region 207 and, consequently, is not explicitly shown. Alternatively, the third region may be somewhat larger than the second region. For example, if a kernel, such as a 5×5 pixel kernel, is used to blend pixels, the kernel may be used to cause blending in pixels slightly outside and around the border of the second region. -
FIGS. 3 and 4 illustrate a method for correcting color defects in a pupil represented in a digital image at least by replacing a presumed pupil region with an image of a pupil, according to an embodiment of the present invention. This and related embodiments are useful for correcting a pupil that appears all or substantially all white. This is a condition referred to as a ‘cue ball.’ Pupils exhibiting a cue ball condition appear to be missing their pupils. The cue ball condition often occurs in pet pupils, but one skilled in the art will appreciate that the following procedure may be used for any pupil experiencing the cue ball condition. - The example of
FIGS. 3 and 4 is similar to the example ofFIG. 2 in that it represents adigital image 300 of a cat. In this example, however, the cat includes twopupils FIG. 3 , the cue ball condition in thepupil 301 is being corrected, and the expected pupil-location is marked by the “X” 303. Althoughpupil 301 is being corrected in the example ofFIG. 3 , one of ordinary skill in the art will appreciate thatpupil 302 may be corrected in the same manner aspupil 301. Also, thelocation 303 is shown merely for illustration purposes, and one of ordinary skill in the art will appreciate thatlocation 303 may be anywhere in or substantially adjacent where thepupil 301 was expected to be located. -
Location 303 may be identified based at least upon user input. Alternatively,location 303 may be identified based at least upon a data-processor-executed search for an expected pupil-location in an eye using techniques known in the art. - Upon identification of an expected pupil-location, it is determined whether all or substantially all of the pixels within a particular region have a white or a substantially white color. This step determines whether a cue ball condition exists in the pupil. The particular region may include the expected pupil-location. In the example of
FIG. 3 , the particular region is shown asrectangle 304. The particular region may be a local neighborhood of pixels, such as a 3×3 neighborhood, a 3×4 neighborhood, a 5×5 neighborhood, etc. Alternatively, the particular region may include the entire eye being evaluated (305, e.g.). Accordingly, one skilled in the art will appreciate that the invention is not limited to any particular choice of the size and shape of the particular region, so long as the particular region includes the expected pupil-location (303, e.g.) and is not too large so as to substantially skew a proper determination of the cue ball condition. - If it is determined that all or substantially all of the pixels within the particular region (304, e.g.) have a white or substantially white color, then a presumed pupil region is identified. In the example of
FIG. 4 , the presumed pupil region is identified bycircle 401. Although the presumed pupil region inFIG. 4 is shown as a circle for purposes of clarity, one skilled in the art will appreciate that cats and other animals have differently shaped pupils and that the invention is not limited to any particularly shaped pupil. The presumed pupil region (401, e.g.) may be identified based at least upon an analysis of the type of animal or person whose pupil is being corrected, as well as the relative size and shape of the pupil being corrected (301, e.g.). - Once the presumed pupil region (401, e.g.) has been identified, an image of a pupil appropriate (402, e.g.) for the animal or person whose pupil is being corrected is identified. Such pupil image is appropriately scaled and then inserted into the presumed pupil region to facilitate correcting the cue ball condition. According to some embodiments, an image of an iris also may be included with the pupil image inserted into the presumed pupil region.
- It is to be understood that the exemplary embodiments are merely illustrative of the present invention and that many variations of the above-described embodiments can be devised by one skilled in the art without departing from the scope of the invention. For example, although the examples of
FIGS. 2-4 pertain to correcting discolored pupils of a cat, one skilled in the art will appreciate that the foregoing processes also may be used to correct discolored pupils of other animals, as well as humans. It is therefore intended that all such variations be included within the scope of the following claims and their equivalents.
Claims (22)
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/971,988 US20080212843A1 (en) | 2007-01-10 | 2008-01-10 | Pet eye correction |
US13/275,631 US8260082B2 (en) | 2007-01-10 | 2011-10-18 | Pet eye correction |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US87973707P | 2007-01-10 | 2007-01-10 | |
US11/971,988 US20080212843A1 (en) | 2007-01-10 | 2008-01-10 | Pet eye correction |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/275,631 Division US8260082B2 (en) | 2007-01-10 | 2011-10-18 | Pet eye correction |
Publications (1)
Publication Number | Publication Date |
---|---|
US20080212843A1 true US20080212843A1 (en) | 2008-09-04 |
Family
ID=39733095
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US11/971,988 Abandoned US20080212843A1 (en) | 2007-01-10 | 2008-01-10 | Pet eye correction |
US13/275,631 Expired - Fee Related US8260082B2 (en) | 2007-01-10 | 2011-10-18 | Pet eye correction |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/275,631 Expired - Fee Related US8260082B2 (en) | 2007-01-10 | 2011-10-18 | Pet eye correction |
Country Status (1)
Country | Link |
---|---|
US (2) | US20080212843A1 (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120242675A1 (en) * | 2011-03-21 | 2012-09-27 | Apple Inc. | Red-Eye Removal Using Multiple Recognition Channels |
US8811683B2 (en) | 2011-06-02 | 2014-08-19 | Apple Inc. | Automatic red-eye repair using multiple recognition channels |
US8818091B2 (en) | 2011-03-21 | 2014-08-26 | Apple Inc. | Red-eye removal using multiple recognition channels |
US8837827B2 (en) | 2011-03-21 | 2014-09-16 | Apple Inc. | Red-eye removal using multiple recognition channels |
CN111915683A (en) * | 2020-07-27 | 2020-11-10 | 湖南大学 | Image position calibration method, intelligent device and storage medium |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8837785B2 (en) | 2011-03-21 | 2014-09-16 | Apple Inc. | Red-eye removal using multiple recognition channels |
US9824271B2 (en) | 2014-06-25 | 2017-11-21 | Kodak Alaris Inc. | Adaptable eye artifact identification and correction system |
CN104463127A (en) * | 2014-12-15 | 2015-03-25 | 三峡大学 | Pupil positioning method and device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5130789A (en) * | 1989-12-13 | 1992-07-14 | Eastman Kodak Company | Localized image recoloring using ellipsoid boundary function |
US20020126893A1 (en) * | 2001-01-31 | 2002-09-12 | Andreas Held | Automatic color defect correction |
US20070098260A1 (en) * | 2005-10-27 | 2007-05-03 | Jonathan Yen | Detecting and correcting peteye |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6631208B1 (en) * | 1998-05-29 | 2003-10-07 | Fuji Photo Film Co., Ltd. | Image processing method |
JP4457586B2 (en) | 2002-07-15 | 2010-04-28 | 株式会社ニコン | Red-eye area correction method, red-eye area correction processing program, recording medium, and image processing apparatus |
JP3945474B2 (en) * | 2003-11-28 | 2007-07-18 | 松下電器産業株式会社 | Eye image input device, authentication device, and image processing method |
JP2005310068A (en) * | 2004-04-26 | 2005-11-04 | Noritsu Koki Co Ltd | Method for correcting white of eye, and device for executing the method |
US8081818B2 (en) * | 2004-09-15 | 2011-12-20 | Adobe Systems Incorporated | Locating a feature in a digital image |
WO2007095553A2 (en) * | 2006-02-14 | 2007-08-23 | Fotonation Vision Limited | Automatic detection and correction of non-red eye flash defects |
-
2008
- 2008-01-10 US US11/971,988 patent/US20080212843A1/en not_active Abandoned
-
2011
- 2011-10-18 US US13/275,631 patent/US8260082B2/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5130789A (en) * | 1989-12-13 | 1992-07-14 | Eastman Kodak Company | Localized image recoloring using ellipsoid boundary function |
US20020126893A1 (en) * | 2001-01-31 | 2002-09-12 | Andreas Held | Automatic color defect correction |
US20070098260A1 (en) * | 2005-10-27 | 2007-05-03 | Jonathan Yen | Detecting and correcting peteye |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120242675A1 (en) * | 2011-03-21 | 2012-09-27 | Apple Inc. | Red-Eye Removal Using Multiple Recognition Channels |
US8786735B2 (en) * | 2011-03-21 | 2014-07-22 | Apple Inc. | Red-eye removal using multiple recognition channels |
US8818091B2 (en) | 2011-03-21 | 2014-08-26 | Apple Inc. | Red-eye removal using multiple recognition channels |
US8837827B2 (en) | 2011-03-21 | 2014-09-16 | Apple Inc. | Red-eye removal using multiple recognition channels |
US8811683B2 (en) | 2011-06-02 | 2014-08-19 | Apple Inc. | Automatic red-eye repair using multiple recognition channels |
CN111915683A (en) * | 2020-07-27 | 2020-11-10 | 湖南大学 | Image position calibration method, intelligent device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
US20120033883A1 (en) | 2012-02-09 |
US8260082B2 (en) | 2012-09-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8260082B2 (en) | Pet eye correction | |
CN110569699B (en) | Method and device for carrying out target sampling on picture | |
US8184900B2 (en) | Automatic detection and correction of non-red eye flash defects | |
US8823830B2 (en) | Method and apparatus of correcting hybrid flash artifacts in digital images | |
US20050219385A1 (en) | Device for preventing red eye, program therefor, and recording medium storing the program | |
US20230017425A1 (en) | System and method for determining damage on crops | |
JP3810776B2 (en) | A method for detecting and correcting red eyes in digital images. | |
US9269155B2 (en) | Region growing method for depth map/color image | |
US8331666B2 (en) | Automatic red eye artifact reduction for images | |
CN108960232A (en) | Model training method, device, electronic equipment and computer readable storage medium | |
KR101631012B1 (en) | Image processing apparatus and image processing method | |
JP2005310124A (en) | Red eye detecting device, program, and recording medium with program recorded therein | |
US9075827B2 (en) | Image retrieval apparatus, image retrieval method, and storage medium | |
WO2009029365A1 (en) | Systems and methods for determination of a camera imperfection for an image | |
CN110189312B (en) | Method and device for evaluating brightness of fundus image, electronic device and storage medium | |
RU2009116641A (en) | DEVICE AND METHOD FOR IDENTIFICATION OF FACIAL REGIONS | |
EP3846114A1 (en) | Animal information management system and animal information management method | |
CN111507298B (en) | Face detection method, device, computer equipment and storage medium | |
US11120530B2 (en) | Image processing apparatus, image processing method, and storage medium | |
CN112102926A (en) | Image processing method, device, equipment and storage medium | |
US10535122B2 (en) | Composite image for flash artifact removal | |
US20050271270A1 (en) | Method of determining color composition of an image | |
KR102444544B1 (en) | Method for image pre-processing and apparatus for the same | |
CN107527011B (en) | Non-contact skin resistance change trend detection method, device and equipment | |
US9721160B2 (en) | Manually-assisted detection of redeye artifacts |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: EASTMAN KODAK COMPANY, NEW YORK Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:RHODA, DAVID K.;COOPER, ANDREW T.;MURRAY, THOMAS J.;REEL/FRAME:020346/0524 Effective date: 20080110 |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |
|
AS | Assignment |
Owner name: CITICORP NORTH AMERICA, INC., AS AGENT, NEW YORK Free format text: SECURITY INTEREST;ASSIGNORS:EASTMAN KODAK COMPANY;PAKON, INC.;REEL/FRAME:028201/0420 Effective date: 20120215 |
|
AS | Assignment |
Owner name: FAR EAST DEVELOPMENT LTD., NEW YORK Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: KODAK AMERICAS, LTD., NEW YORK Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: NPEC INC., NEW YORK Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: FPC INC., CALIFORNIA Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: EASTMAN KODAK COMPANY, NEW YORK Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: CREO MANUFACTURING AMERICA LLC, WYOMING Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: KODAK PHILIPPINES, LTD., NEW YORK Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: EASTMAN KODAK INTERNATIONAL CAPITAL COMPANY, INC., Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: KODAK PORTUGUESA LIMITED, NEW YORK Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: KODAK IMAGING NETWORK, INC., CALIFORNIA Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: LASER-PACIFIC MEDIA CORPORATION, NEW YORK Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: QUALEX INC., NORTH CAROLINA Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: KODAK AVIATION LEASING LLC, NEW YORK Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: KODAK (NEAR EAST), INC., NEW YORK Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: PAKON, INC., INDIANA Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 Owner name: KODAK REALTY, INC., NEW YORK Free format text: PATENT RELEASE;ASSIGNORS:CITICORP NORTH AMERICA, INC.;WILMINGTON TRUST, NATIONAL ASSOCIATION;REEL/FRAME:029913/0001 Effective date: 20130201 |
|
AS | Assignment |
Owner name: MONUMENT PEAK VENTURES, LLC, TEXAS Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:INTELLECTUAL VENTURES FUND 83 LLC;REEL/FRAME:064599/0304 Effective date: 20230728 |