Ear Contour Detection Based on Edge Tracking

Ear detection is an important step in ear recognition, the quality of detection will directly affect the final recognition rate . According to the feature of ear and its position on the side face, a method based on edge-tracking is adopted for human ear localization from side face images. Firstly binary image was generated using an adaptive threshold, then outer ear was divided into three regions. Binary image was combined with original image to find the contour of the three regions and the information of ear´s position in side face. Experimental results show that the method is simple, its localization accuracy is high, and ear contour edge extracted is clear, connected and non-disturbed