Image Feature Extraction of Moment of Inertia Based on Otsu Threshold Segmentation

Abstract

In order to better extract image feature and recognition, a novel feature extraction algorithm of the binary image processing using Otsu combined with normalized moment of inertia (NMI) is put forward. Firstly, the image is processed into binary image and the target area is effectively segmented utilizing Otsu algorithm based on the criteria of maximal variance between-class , secondly, the NMI feature of the binary image is extracted, and finally, the extraction NMI feature is used in image recognition. Experimental results show that NMI feature of the binary image have the ability of anti-geometric distortions (translation, rotation and scaling, TRS), and anti-brightness distortions, the novel method have characteristics of simple extraction approach, little extraction parameter, easy implementation, and strong robustness.