Ear Structure Feature Extraction Based on Multi-scale Hessian Matrix

Abstract

In this paper, a new ear anatomy feature edge extraction method based on Hessian matrix is proposed. Stable edge is obtained from principal curvature image across scale space. Firstly, the side face image that includes an ear is filtered and forms Gaussian pyramid. Secondly, the 2D gray image in the pyramid was regarded as a surface, maximum and minimum principal curvature and their direction were calculated by using Hessian matrix, and principal curvature image was formed. The characteristic of surface is that gray level changes in edge area is sharp and the curvature is larger compared to that of the smooth area. In accordance with this characteristic, automatic hysteresis thresholding based on curvature direction flow is used to segment curvature images. Lastly, combine different scale threshold images to get the feature edge image. The experiments demonstrate that extracted feature edge is smooth and connected. New method is robust to noise, and is sensitive to the weak edge, using Hausdorff distance as similarity measurement of two edge images can obtain above 96% recognition rate.