Method for extracting and recognizing human ear characteristic by improved Hausdorff distance

Abstract

The invention relates to a method for picking up and identifying human ear characteristic by means of improved Hausdorff distance. The invention obtains standard human ear image through pretreatment of human ear image such as collection of human ear images, denoising of non-complexion noise, normalization of space dimension and illumination compensation; then, gray scale morphologic gradient and local threshold subdivision are adopted to pick up human ear edge feature so as to obtain standard human ear edge image. With the method and the Hausdorff distance improved through the length difference between standard variance and edge line segment, the influence of point set non-outline edge line segment point (outfield point) is reduced so as to obtain better anti-noise performance; moreover, the invention increases the accuracy of human ear edge image recognition by means of the characteristic value obtained on the basis of Hausdorff distance, thereby greatly increasing human ear recognition rate.

Description

technical field [0001] The invention belongs to the personal identification technology based on human biological features, in particular to a method for extracting and identifying human ear features by using improved Hausdorff distance. technical background [0002] Human ear recognition technology is a biometric recognition technology that began to emerge in the late 1990s. The unique physiological characteristics of the human ear and the advantages of observation angles make the human ear recognition technology have considerable theoretical research value and practical application prospects. The human outer ear is divided into the auricle and the external auditory canal. The object recognized by the human ear is actually the exposed auricle of the outer ear, which is what people are used to call the "ear". A complete automatic ear recognition system generally includes the following processes: ear image acquisition, image preprocessing, ear image segmentation, feature extr...

AI Technical Summary

Problems solved by technology

However, since the Hausdorff distance is a maximum and minimum distance, it is still very sensitive to the noise in the human ear image

In human ear recognition, although there may be two very similar or even identical human ear edge images, due to the existence of some false contours (non-human ear main contour segments), the calculation of the Hausdorff distance will also produce a large error.

Moreover, edge detection itself is an uncertain problem. The definition of edges is usually very vague, and it is very difficult to distinguish edge points from noise points.

Images