Ear Detection based on CenterNet

Biometric recognition, such as face recognition, fingerprint recognition, iris recognition, etc., has played an important role for personal authentication in modern society. However, the spread of new coronaviruses around the world may cause some trouble for these popular biometrics, because people usually wear masks or sun-glasses. Human ear is a kind of biological feature, which has the characteristics of universality, stability and easy collection. Ear recognition can be applied under unconstrained conditions. People don't have to take off the masks or glasses if the ears are visible. For an ear recognition system, ear detection is the first important part, which makes research on ear detection a hot topic. In this paper, we apply a single-stage target detection method -the CenterNet deep learning network -for real-time ear detection. CenterNet is the most advanced method for real-time 2D object detection. Its essential idea is to predict whether each pixel is the center of the object, and predict the object boundary if the pixel is indeed the center point. Experimental results and analysis on the human ear dataset show that compared with other detection methods, the proposed method has higher detection accuracy on both static images and videos.