An approach towards ear feature extraction for human identification

摘要

Biometrics based security systems play a significant role in almost all the security aspects. Ear is a new class of relative stable biometrics. Feature Extraction plays a vital role in deciding the efficiency of any identification system. One of the challenges in Ear biometric system is segmentation of ear from the image. Ear biometric based human identification system's performance mainly depends on proper segmentation of ear from the image and the feature extracted from the segmented ear image. It is observed from the literature, that most of the ear identification methods are not automatic. It needs user intervention in segmenting the ear from the image in order to process further. Also many Feature descriptors have been proposed in the past In this paper, a new concept of fully automatic ear segmentation and “Adaptive blocks” based feature extraction technique was proposed. In this approach, the segmented ear image will be divided into `N' adaptive blocks-meaning the number of blocks are going to be same but, the height and width of the blocks will be based on the height and width of the ear. The advantage of this approach is that the feature vector obtained with respect to the selected points will be more meaningful and contribute more information in the identification process.