Pet eye correction

Abstract

Correction of color defects in a pupil represented in a digital image is disclosed. For example, 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. For pupils that appear all white, appropriately configured pupil images are inserted therein.

1 . A method implemented at least in part by a data processing system, the method for correcting color defects in a pupil represented in a digital image, and the method comprising the steps of:
 identifying a location in the pupil within the digital image;   computing a target color to be corrected based at least upon an analysis of pixels within a first region in which the location resides;   identifying defect pixels in a second region in which the location resides, the defect pixels being identified as having a pixel color similar to the target color; and   color-correcting the defect pixels.   
   
   
       2 . The method of  claim 1 , wherein the pupil is a pet pupil. 
   
   
       3 . The method of  claim 1 , wherein the location in the pupil is identified based at least upon user input. 
   
   
       4 . The method of  claim 1 , wherein the analysis of the pixels includes determining an average of pixel color values of at least some of the pixels within the first region. 
   
   
       5 . The method of  claim 1 , wherein the analysis of the pixels excludes pixels representing specular highlights in the computing of the target color. 
   
   
       6 . The method of  claim 1 , wherein the identifying defect pixels step identifies defect pixels as those within the second region exhibiting a difference in color with respect to the target color within a threshold. 
   
   
       7 . The method of  claim 1 , wherein the identifying defect pixels step does not identify pixels representing specular highlights as defect pixels. 
   
   
       8 . The method of  claim 1 , wherein the color-correcting step modifies the defect pixels so that they are more neutral in color. 
   
   
       9 . The method of  claim 1 , wherein the color-correcting step modifies the defect pixels so that they are neutral or substantially neutral in color. 
   
   
       10 . The method of  claim 9 , wherein the color-correcting step corrects each defect pixel to have red, green, and blue color values equal to a minimum of the defect pixel's pre-corrected red, green, and blue color values. 
   
   
       11 . The method of  claim 1 , further comprising the step of blending pixels in a third region in which the second region resides, wherein the blending step occurs after the color-correcting step. 
   
   
       12 . The method of  claim 1 , wherein the first region is within the second region. 
   
   
       13 . A processor-accessible memory system storing instructions configured to cause a data processing system to implement a method for correcting color defects in a pupil represented in a digital image, wherein the instructions comprise:
 instructions for identifying a location in the pupil within the digital image;   instructions for computing a target color to be corrected based at least upon an analysis of pixels within a first region in which the location resides;   instructions for identifying defect pixels in a second region in which the location resides, the defect pixels being identified as having a pixel color similar to the target color; and   instructions for color-correcting the defect pixels.   
   
   
       14 . The processor-accessible memory system of  claim 13 , wherein the pupil is a pet pupil. 
   
   
       15 . The processor-accessible memory system of  claim 13 , wherein the analysis of the pixels includes determining an average of pixel color values of at least some of the pixels within the first region. 
   
   
       16 . The processor-accessible memory system of  claim 13 , wherein the analysis of the pixels excludes pixels representing specular highlights in the computing of the target color. 
   
   
       17 . A system comprising:
 a data processing system; and   a memory system communicatively connected to the data processing system and storing instructions configured to cause the data processing system to implement a method for correcting color defects in a pupil represented in a digital image, wherein the instructions comprise:   instructions for identifying a location in the pupil within the digital image;   instructions for computing a target color to be corrected based at least upon an analysis of pixels within a first region in which the location resides;   instructions for identifying defect pixels in a second region in which the location resides, the defect pixels being identified as having a pixel color similar to the target color; and   instructions for color-correcting the defect pixels.   
   
   
       18 . The system of  claim 17 , wherein the pupil is a pet pupil. 
   
   
       19 . The system of  claim 17 , wherein the analysis of the pixels includes determining an average of pixel color values of at least some of the pixels within the first region. 
   
   
       20 . The system of  claim 17 , wherein the analysis of the pixels excludes pixels representing specular highlights in the computing of the target color. 
   
   
       21 . A method implemented at least in part by a computer system, the method for correcting color defects in a pupil represented in a digital image, and the method comprising the steps of:
 identifying an expected pupil-location within the digital image;   determining that all or substantially all of the pixels within a particular region in which the expected pupil-location resides have a white or a substantially white color;   identifying a presumed pupil region; and   inserting into the presumed pupil region an image of a pupil configured to fit the presumed pupil region.   
   
   
       22 . The method of  claim 21 , wherein the image of the pupil includes an image of an iris.