Human Recognition Using Ear Features: A Review

Abstract

Over the past few years, ear biometrics has attracted a lot of attention. It is a trusted biometric for the identification and recognition of humans due to its consistent shape and rich texture variation. The ear presents an attractive solution since it is visible, ear images are easily captured, and the ear structure remains relatively stable over time. In this paper, a comprehensive review of prior research was conducted to establish the efficacy of utilizing ear features for individual identification through the employment of both manually-crafted features and deep-learning approaches. The objective of this model is to present the accuracy rate of person identification systems based on either manually-crafted features such as DCT, DWT, DFT, PCA, LBP, SURF, SIFT, etc., or deep learning techniques such as CNN, DNN, Alex Net CNN, VGG-16, SVM, Squeeze Net, Google Net, MobileNetV2, etc. The effort will make it easier for researchers, especially those who are new to the field, to have a brief understanding of the trend of employing deep learning in a trustworthy biometric for the identification and recognition of human identification.