A neural network incorporating adaptive Gabor filters for image texture classification

A novel neural network architecture for image texture classification is introduced. The proposed kernel modifying neural network (KM Net), which incorporates a convolution filter kernel array and a classifier in one, enables an automated texture feature extraction in the multichannel texture classification through modification of the kernels and the connection weights by a backpropagation-based training rule. The first layer units working as the convolution kernels are constrained to be an array of Gabor filters, which achieves the most efficient texture feature localization. The following layers work as a classifier of the extracted texture feature vectors. The capability of the KM Net and its training rule is verified with basic problems of synthetic and fabric texture images, and also with a biological tissue classification problem in an ultrasonic echo image.