Iraqi Journal of Humanitarian, Social and Scientific Research
Abstract:
Automatic person recognition using ear shape images is an active field of research within the biometric community. Similar to other biometric traits such as fingerprints, face and iris, ear also has numerous specific and unique features that aid in person identification. In this present worldwide pandemic of COVID-19 situation, most of the facial identification systems has almost failed due to the mask wearing scenario. The human ear is a perfect source of data for passive person identification as it does not involve the cooperativeness of the individual whom recognition is being attempted for and it is more easily captured at a distance. A human ear image acquisition is also easy as the ear is apparent even the users’ wearing masks. In an automatic human recognition system, an ear biometric system can be integrated as a supplement to other biometric systems and offer identity cues when other system information is unreliable or even unavailable. In this paper, a comprehensive review of growing research field of feature extraction techniques and the classification technique of deep learning using convolutional neural network (CNN) was conducted to exhibit the rate of accuracy for person recognition systems using ear shape images.
