Method and system for object recognition using fractal maps

Abstract

A method for recognizing an object in an image is disclosed wherein a fractal map of the image is generated by estimating the fractal dimension of each pixel in the image. The fractal map may be segmented by thresholding and locations of candidate objects are determined. The pixel value of the image pixel corresponding to the same location where the candidate object is found in the fractal map may be compared to a threshold value. If the pixel value is greater than the threshold value, the candidate object is recognized as a valid object.

1 . An apparatus for discriminating objects in a digital image comprising:
 an automated scanning optical microscopy system;   a digital camera attached to said automated scanning optical microscopy system and configured to capture said digital image of field of view of said microscopy system;   an image processor configured to receive said digital image from said digital camera and to perform the steps of:
 automatically assigning to each pixel in the digital image a pixel value that represents the fractal dimension of the pixel to generate a fractal map; 
 segmenting the fractal map into two or more fractal images; and 
 shrinking objects in the segmented fractal images.