An Efficient Fpga Implementation Of Feature Extraction Based On Histopathalogical Image And Subsequent Classification By Svm

This paper present the implementation of feature extraction from histo-pathological images and subsequent classification using Verilog HDL. The proposed automated system use a number of features extracted from images of skin lesions through image processing techniques which consisted of adaptive median filter then applied Gabor filter bank to improve diagnostic accuracy. Histogram equalization to enhance the contrast of the images prior to segmentation is used. The obtained statistics are fed to a support vector machine (SVM) binary classifier to diagnose skin biopsies from patients as either malignant melanoma or benign nevi. Hradware implementation is using Spartan 6 FPGA Kit.