METHOD FOR DETECTION OF BLEND PIXELS FOR USE IN AN IMAGE SEGREGATION
A method and system comprising image processing techniques that utilize spatio-spectral information relevant to an image, derived from multiple sets of selectively varied representations of the image to accurately and correctly identify illumination and material aspects of the image is provided. Blend pixels are detected to improve the accuracy of the identification of the illumination and material aspects of the image.
1 . An automated, computerized method for processing an image, comprising the steps of:
providing an image file depicting an image, in a computer memory;
identifying Type C tokens in the image;
examining the Type C tokens to identify candidate 1-D tokens;
examining each one of the candidate 1-D tokens to verify that each one of the candidate 1-D tokens is composed of blend pixels; and
performing an image segregation operation as a function of 1-D tokens composed of blend pixels.
2 . The method of claim 1 wherein the step of examining each one of the candidate 1-D tokens to verify that each one of the candidate 1-D tokens is composed of blend pixels is carried out by examining each one of the candidate 1-D tokens to determine when a candidate 1-D token is a one of a shadow boundary or texture.
3 . A computer program product, disposed on a non-transitory computer readable media, the product including computer executable process steps operable to control a computer to: receive an image file depicting an image, identify Type C tokens in the image, examine the Type C tokens to identify candidate 1-D tokens, examine each one of the candidate 1-D tokens to verify that each one of the candidate 1-D tokens is composed of blend pixels and perform an image segregation operation as a function of 1-D tokens composed of blend pixels.
4 . The computer program product of claim 3 wherein the process step of examining each one of the candidate 1-D tokens to verify that each one of the candidate 1-D tokens is composed of blend pixels is carried out by examining each one of the candidate 1-D tokens to determine when a candidate 1-D token is a one of a shadow boundary or texture.