System and method for performing region-based image retrieval using color-based segmentation

Abstract

An image retrieval system is provided for analyzing an image in a first color model format and detecting and retrieving from the image a selected image portion. The image retrieval system comprises an image processor for converting pixels in the image from the first color model format to a (Yrθ) color model format, where Y is an intensity component indicating a total amount of light, r is a saturation component indicating an amount of white light mixed with a color of each pixel, and θ is a hue component indicating the color of each pixel. The image processor groups spatially adjacent pixels into image regions according to hue components of the adjacent pixels and performs a merging process wherein a first image region and an adjacent second image region are merged into a composite region if a hue difference between the first and second image regions is less than a predetermined hue difference threshold. The process is repeated to continually merge regions of similar hue until no further merges can be performed.

We claim:  
     
         1 . An image processing device, comprising: 
 an image processor that is configured to: 
 convert a plurality of pixels of an image from a first color model format to a (Y,r,θ) color model format, wherein: 
 Y is an intensity component indicating a total amount of light,  
 r is a saturation component indicating an amount of white light mixed with a color of the each pixel, and  
 θ is a hue component indicating the color of the each pixel;  
 
 group spatially adjacent ones of the plurality of pixels into a plurality of image regions according to hue components of the adjacent pixels, substantially independent of intensity components and the saturation components of the adjacent pixels; and  
 selectively merge a first image region and a second image region proximate the first image region into a composite region if a hue difference between the first and second image regions is less than a predetermined hue difference threshold.  
   
     
     
         2 . The image processing device of  claim 1 , wherein 
 the image processor is configured to determine a histogram of hue components of the pixels in the image,    the histogram indicating a number of pixels of similar hue in the image.    
     
     
         3 . The image processing device of  claim 2 , wherein 
 the image processor is configured to determine a dominant hue in the image using a peak detection algorithm on the histogram.    
     
     
         4 . The image processing device of  claim 1 , wherein 
 the image processor is configured to determine and to mark ones of the plurality of image regions having less than a predetermined minimum number of pixels and disregarding the marked image regions during the merging process.    
     
     
         5 . The image processing device of  claim 1 , wherein 
 the image processor is configured to determine and mark achromatic ones of the plurality of image regions having less than a predetermined minimum number of pixels and disregarding the marked achromatic image regions during the merging process.    
     
     
         6 . The image processing device of  claim 5 , wherein 
 the first and second image regions are merged if a number of pixels in the first image region and a number of pixels in the second image region are greater than a predetermined image region size threshold.    
     
     
         7 . An image retrieval system capable of analyzing an image comprising a plurality of pixels in a first color model format comprising: 
 an image processing device capable of detecting and retrieving from the image a selected image portion,    the image processing device comprising: 
 an image processor that is configured to: 
 convert the plurality of pixels in the image from the first color model format to a (Y,r,θ) color model format,  
 wherein 
 for each pixel in the plurality of pixels,  
 Y is an intensity component indicating a total amount of light,  
 r is a saturation component indicating an amount of white light mixed with a color of the each pixel, and  
 θ is a hue component indicating the color of the each pixel;  
 
 group spatially adjacent ones of the plurality of pixels into a plurality of image regions according to hue components of the adjacent pixels, substantially independent of intensity components and the saturation components of the adjacent pixels; and  
 perform a merging process to merge a first image region and a second image region proximate the first image region into a composite region, if a hue difference between the first and second image regions is less than a predetermined hue difference threshold;  
 
 a display monitor that is configured to display the composite region; and  
 a user input device that is configured to receive user commands capable of controlling the merging process.  
   
     
     
         8 . The image retrieval system of  claim 7 , wherein 
 the image processor is configured to determine a histogram of hue components of the pixels in the image,    the histogram indicating a number of pixels of similar hue in the image.    
     
     
         9 . The image retrieval system of  claim 8 , wherein 
 the image processor is configured to determine a dominant hue in the image based on the histogram.    
     
     
         10 . The image retrieval system of  claim 9 , wherein 
 the image processor is configured to: 
 determine and mark ones of the plurality of image regions having less than a predetermined minimum number of pixels, and  
 disregard the marked image regions during the merging process.  
   
     
     
         11 . The image retrieval system of  claim 7 , wherein 
 the image processor is configured to: 
 determine and mark achromatic ones of the plurality of image regions having less than a predetermined minimum number of pixels, and  
 disregard the marked achromatic image regions during the merging process.  
   
     
     
         12 . The image retrieval system of  claim 11 , wherein 
 the first and second image regions are merged if a number of pixels in the first image region and a number of pixels in the second image region are greater than a predetermined image region size threshold.    
     
     
         13 . A method of processing an image comprising a plurality of pixels in a first color model format, the method comprising: 
 converting the plurality of pixels in the image from the first color model format to a (Y,r,θ) color model format, 
 wherein for each pixel in the plurality of pixels, 
 Y is an intensity component indicating a total amount of light,  
 r is a saturation component indicating an amount of white light mixed with a color of each pixel, and  
 θ is a hue component indicating the color of each pixel; and  
 
   grouping spatially adjacent ones of the plurality of pixels into a plurality of image regions according to hue components of the adjacent pixels, substantially independent of intensity components and the saturation components of the adjacent pixels; and    performing a merging process, 
 wherein a first image region and a second image region proximate the first image region are merged into a composite region if a hue difference between the first and second image regions is less than a predetermined hue difference threshold.  
   
     
     
         14 . The method of  claim 13 , further comprising: 
 determining and marking ones of the plurality of image regions having less than a predetermined minimum number of pixels; and    disregarding the marked image regions during the merging process.    
     
     
         15 . The method of  claim 13 , further comprising: 
 determining and marking achromatic ones of the plurality of image regions having less than a predetermined minimum number of pixels; and    disregarding the marked achromatic image regions during the merging process.    
     
     
         16 . The method of  claim 13 , wherein 
 the first and second image regions are merged if a number of pixels in the first image region and a number of pixels in the second image region are greater than a predetermined image region size threshold.    
     
     
         17 . For use in an image retrieval system capable of analyzing an image comprising a plurality of pixels in a first color model format, a computer executable process, stored on a computer readable storage medium, for detecting and retrieving from the image a selected image portion comprising: 
 converting the plurality of pixels in the image from the first color model format to a (Y,r,θ) color model format, 
 wherein for each pixel in the plurality of pixels, 
 Y is an intensity component indicating a total amount of light,  
 r is a saturation component indicating an amount of white light mixed with a color of each pixel, and  
 θ is a hue component indicating the color of each pixel; and  
 
   grouping spatially adjacent ones of the plurality of pixels into a plurality of image regions according to hue components of the adjacent pixels, substantially independent of intensity components and the saturation components of the adjacent pixels; and    performing a merging process, 
 wherein a first image region and a second image region proximate the first image region are merged into a composite region if a hue difference between the first and second image regions is less than a predetermined hue difference threshold.  
   
     
     
         18 . The computer executable process of  claim 17 , further comprising: 
 determining and marking ones of the plurality of image regions having less than a predetermined minimum number of pixels; and    disregarding the marked image regions during the merging process.    
     
     
         19 . The computer executable process of  claim 17 , further comprising: 
 determining and marking achromatic ones of the plurality of image regions having less than a predetermined minimum number of pixels; and    disregarding the marked achromatic image regions during the merging process.    
     
     
         20 . The computer executable process of  claim 17 , wherein 
 the first and second image regions are merged if a number of pixels in the first image region and a number of pixels in the second image region are greater than a predetermined image region size threshold.