Robust ear biometric recognition using neural network
Mozammel Chowdhury, Rafiqul Islam, Junbin Gao · 2017
Ear based biometric recognition has been gaining popularity in recent years because the ear is unique to individuals and generally unaffected by changing pattern over aging. This paper aims to propose a robust and efficient ear biometric recognition scheme using local features of the human ear employing a neural network algorithm. The scheme initially estimates the ear region from the facial image and then extracts the edge features from the detected ear. We use edge local features since they are invariant to illumination changes and occlusion. A neural network is used to recognize the user by matching the extracted ear features of the user with a feature database. The performance of the approach is tested with different datasets and compared with some existing well known methods. Experimental evaluation clearly proves the robustness and effectiveness of the proposed scheme over similar techniques.