A Novel Parallel Texture Feature Extraction Method using Log-Gabor Filter and Singular Value Decomposition (SVD)

Abstract

Texture feature extraction consolidated with texture feature detection and feature matching solves many typical problems of image processing and computer vision; such as, texture classification, pattern recognition, object detection, and image segmentation. Through this paper, a new method for texture feature extraction is presented which uses Log-Gabor Filter and Singular Value Decomposition (SVD) algorithm. In the proposed model, sample images are converted to gray level images. And then, to elicit suitable distinctive texture orientation, a 2D Log-Gabor filter with various frequencies and different edges disintegrated with the SVD employ on each converted gray level images. Finally, singular values of SVD used as feature vector for this texture feature extraction model. For training and testing of experimental datasets, Naive Bayes classifier has been used. The Log-Gabor and SVD based feature extraction shows improved performance by exhibiting higher classification accuracy for our tested dataset compare to conventional Gabor and SVD feature extraction method. Furthermore, in order to decrease the computational and time complexity, an NVIDIA GeForce GTX780 GPU is used to implement our proposed model in parallel. The GPU implementation of proposed model showed average 3X speedup for per image than conventional CPU implementation.