Infrared Image Segmentation Algorithm Based on Fusion of Multi-Feature

Abstract

For the poor contrast and low SNR of infrared images, a new multi-feature fusion image segmentation algorithm is proposed which is based on the features of several traditional image segmentation algorithms. The proposed algorithm segments the target in the region of interest by combining gray, region and boundary information. The proposed algorithm can detect the target from complex background and its performance is superior to traditional algorithms. The experiment results show that the proposed algorithm accurately and effectively segments the target.Keywordsmulti-feature fusioninfrared imagesimage segmentationregion of interest