Study On Image Recognition Based On Dempster-Shafer Evidence Theory

Pearlite spheroidization can decrease metallic material high-temperature properties. The precision of contrapositive method is not high, which estimates the grade of metallic material peralite sphereoidization. In this paper a Dempster-Shafer evidence theory algorithm with infinite frame is proposed for texture image analysis of speruler pearlite gradation about 15CrMo.The image enhancement, segmentation and feature extraction is done first to form the feature space, which includes the fractal dimension, energy and entropy. The feature information is fused using the proposed algorithm. The experiment demonstrates that the algorithm applied to the case with both high accuracy and efficiency.