Ear Biometrics Using Deep Learning: A Survey

Table 7

Differences between this review article and the recent/existing review papers.

Author(s) and date of publication	Paper title	Aim/focus/objective	Paper coverage (year) and scope
(1) This paper	Ear Biometrics using Deep Learning: A Survey	This paper proved that using a bag of feature techniques and the classification technique of deep learning using convolutional neural network was better than standard machine learning techniques	Eighty-nine (89) application papers that are deep learning ear identification methods are reviewed in this paper
(2) Emeršič et al. [60] 29 June 2017	Training convolutional neural networks with limited training data for ear recognition in the wild	It was a handcrafted feature extraction method, such as LBP and patterns of oriented edge magnitudes (POEM), and CNN-based feature extraction methods were used to obtain the ear identification	Forty-one (41) application papers that are deep learning ear identification methods are reviewed in this paper
(3) Tian et al. [21] 16 February 2017	Ear recognition based on deep convolutional network	This system used deep convolutional neural network (CNN) to ear recognition. There were occlusions like no earrings, headsets, or similar occlusions	Fifteen (15) application papers that are deep learning ear identification methods are reviewed in this paper
(4) Raveane et al. [64] 18 June 2019	Ear detection and localization with convolutional neural networks in natural images and videos	This system used variable conditions, and this could also be because of the odd shape of the human ears and changing lighting conditions	Thirty-five (35) application papers that are deep learning ear identification methods are reviewed in this paper