Fluorescent image classification by major color histograms and a neural network

Efficient image classification of microscopic fluorescent spheres is demons trated with a supervised backpropagation neural network (NN) that uses as i nputs the major color histogram representation of the fluorescent image to be classified. Two techniques are tested for the major color search: (1) cl uster mean (CM) and (2) Kohonen's self-organizing feature map (SOFM). The m ethod is shown to have higher recognition rates than Swain and Ballard's Co lor Indexing by histogram intersection. Classification with SOFM-generated histograms as inputs to the classifier NN achieved the best recognition rat e (90%) for cases of normal, scaled, defocused, photobleached, and combined images of AMCA (7-Amino-4Methylcoumarin-3-Acetic Acid) and FITC (Fluoresce in Isothiocynate) stained microspheres. (C) 2001 Optical Society of America .