Human ear detection method under complex static color background

Abstract

The invention relates to a human ear detection method with phase optimization under complex static color background; the method has the following steps of: (1) selecting YCbCr space as a skin color division space, using a Gaussian model as a skin color distribution model, conducting skin color likelihood score conversion and dynamic threshold division to the conversed image; (2) using a morphological method to optimize each divided region and conducting skin color region screening so as to exclude the skin color region not covering human side face and reduce interference; (3) using a wavelet modulus maximum method to detect the image edges under different scales and overlapping edge binary images under different scales, thereby not only accurately detecting the internal and external edges of human ear, but also suppressing noise interference; and (4) realizing human ear detection by conducting expansion, filling, refinement and reconstruction to the edge binary images. The test result shows that the method obtains good effect and is expected to provide useful reference for the development of a human ear automatic identification system.

Description

technical field [0001] The invention relates to a human ear detection method, in particular to a human ear detection method using information such as skin color, geometric features of side faces, gray information of side faces, inner edges of human ears and the like to detect complex static color backgrounds. Background technique [0002] In recent years, biometrics has attracted more and more researchers' attention. It plays an important role in everything from authentication to gate entry security. However, most biometric technologies at this stage have strict requirements on their working environment, thus limiting their scope of application. So researchers are trying to find new biometric technologies. [0003] Human ear recognition is a new type of recognition technology, and there are not many related researches at home and abroad. Human ear recognition technology has high theoretical research value and practical application prospect because of its unique physiologi...

AI Technical Summary

Problems solved by technology

However, the offline training time of this method is long, and the training of the classifier alone takes 16 days

At the same time, the AdaBoost method is more dependent on the training samples in the image library. If the sources of human ear images in different backgrounds vary greatly, the detection effect of this method is not ideal.

Images