Probabilistic PCA Human Ear Recognition System

Diksha Kumari , Satnam Singh , Bhanu Gupta

Ear Recognition, CPD, Probabilistic PCA, MATLAB.

The human ear is a perfect source of data for passive person identification in many applications. In a growing need for security in various public places, ear biometrics seems to be a good solution, since ears are visible and their images can be easily taken, even without the examined person’s knowledge. Human ears have been used as major feature in forensic science for many years (for example in airplane crashes). Ear prints, found on the crime scene, have been used as a proof in over few hundred cases in the Europe and the United States. Nowadays, police and forensic specialists use ear prints as a standard proof of identity. There are many advantages of using the ear as a source of data for human identification. Firstly, the ear is one of the most stable human anatomical features. It does not change considerably during human life. Furthermore, the ear is one of our sensors, therefore it is usually visible (not hidden underneath anything) to enable good hearing. Reliability in personal authentication is a key to the stringent security requirements in many application domains ranging from airport surveillance to electronic banking. Many physiological characteristics of humans, i.e., biometrics, are typically invariant over time, easy to acquire, and unique to each individual. The first step of ear recognition is the segmentation of ear image from the profile face. Ear images taken at different time can vary significantly due to changes in hair length and color. Due to this variation many false point matches may occur and this reduce the accuracy of image distance measurement significantly. The proposed system is to be developed in MATLAB and tested on a available Human Ear Database.

Volume 4 Issue 3, March-2019

Pages : 79 - 83