Human Ear Recognition Using Geometrical Features Extraction

Anwar, Asmaa Sabet; Ghany, Kareem Kamal A.; Elmahdy, Hesham N.

doi:10.1016/j.procs.2015.09.126

Cited by 69 publications

(31 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…iris and eye movement) [72]. [73], [74], [75], [76], [77], [78], [79], [80] Behavioral (Gait, Signature, Handwriting) Sparse reconstruction based metric learning, Gradient local binary patterns, longest run feature [81], [82] Bioacoustics Pitch, Zernike moment [83], [84] Bio-Signal (EEG, ERG, ECG, EMG, EOG, GSR, MEG, MCG, MMG)…”

Section: )mentioning

confidence: 99%

Pattern Mining Approaches Used in Sensor-Based Biometric Recognition: A Review

et al. 2019

View full text Add to dashboard Cite

Sensing technologies place significant interest in the use of biometrics for the recognition and assessment of individuals. Pattern mining techniques have established a critical step in the progress of sensor-based biometric systems that are capable of perceiving, recognizing and computing sensor data, being a technology that searches for the high-level information about pattern recognition from low-level sensor readings in order to construct an artificial substitute for human recognition. The design of a successful sensor-based biometric recognition system needs to pay attention to the different issues involved in processing variable data being-acquisition of biometric data from a sensor, data pre-processing, feature extraction, recognition and/or classification, clustering and validation. A significant number of approaches from image processing, pattern identification and machine learning have been used to process sensor data. This paper aims to deliver a state-of-the-art summary and present strategies for utilizing the broadly utilized pattern mining methods in order to identify the challenges as well as future research directions of sensor-based biometric systems.

show abstract

Section: )mentioning

confidence: 99%

Pattern Mining Approaches Used in Sensor-Based Biometric Recognition: A Review

et al. 2019

View full text Add to dashboard Cite

show abstract

“…SqueezeNet is a CNN architecture developed by Forrest Iandola and others in 2016. It dubbed as scaled-50 AlexNet as it can achieve AlexNet accuracy with 50x reduced parameters [35]. SqueezeNet is mainly composed of fire modules with compression strategies onto its layers.…”

Section: ) Squeezenetmentioning

confidence: 99%

“…Each model is architected to learn 10 classes of ears in an unconstrained environment with a weight rate and neuron bias rate of 20 on both the fully connected layers and softmax or activation to further accelerate the process of learning on new layers. Fully connected, softmax, and classification layers are replaced in each architecture except for SqueezeNet as it is designed to learn with only convolutional layers and a softmax being present [35].…”

Section: Fine-tuning Of Pre-trained Cnn Architecturesmentioning

confidence: 99%

Unconstrained Ear Recognition through Domain Adaptive Deep Learning Models of Convolutional Neural Network

Alejo¹,

Hate²

2019

IJRTE

View full text Add to dashboard Cite

Limited ear dataset yields to the adaption of domain adaptive deep learning or transfer learning in the development of ear biometric recognition. Ear recognition is a variation of biometrics that is becoming popular in various areas of research due to the advantages of ears towards human identity recognition. In this paper, handpicked CNN architectures: AlexNet, GoogLeNet, Inception-v3, Inception-ResNet-v2, ResNet-18, ResNet-50, SqueezeNet, ShuffleNet, and MobileNet-v2 are explored and compared for use in an unconstrained ear biometric recognition. 250 unconstrained ear images are collected and acquired from the web through web crawlers and are preprocessed with basic image processing methods including the use of contrast limited adaptive histogram equalization for ear image quality improvement. Each CNN architecture is analyzed structurally and are fine-tuned to satisfy the requirements of ear recognition. Earlier layers of CNN architectures are used as feature extractors. Last 2-3 layers of each CNN architectures are fine-tuned thus, are replaced with layers of the same kind for ear recognition models to classify 10 classes of ears instead of 1000. 80 percent of acquired unconstrained ear images is used for training and the remaining 20 percent is reserved for testing and validation. Results of each architectures are compared in terms of their training time, training and validation outputs as such learned features and losses, and test results in terms of above-95% accuracy confidence. Above all the used architectures, ResNet, AlexNet, and GoogleNet achieved an accuracy confidence of 97-100% and is best for use in unconstrained ear biometric recognition while ShuffleNet, despite of achieving approximately 90%, shows promising result for use in mobile version of unconstrained ear biometric recognition.

show abstract

“…Some methods which are based on geometrical approach such as: perspective methods [18], geometrical parameters method [19][20], geometrical surface properties [21], etc., and some of them are based on global approach: force field transformation [12], local binary pattern [22], Gabor features [23], etc. Apart from using only 2D images [24][25][26], [13], A smaller number of researchers have looked at using 3D ear shape [28][29][30][31].…”

Section: Introductionmentioning

confidence: 99%

An Ear Recognition Method Based on Rotation Invariant Transformed DCT

Hourali

Gharravi

2017

IJECE

View full text Add to dashboard Cite

Human recognition systems have gained great importance recently in a wide range of applications like access, control, criminal investigation and border security. Ear is an emerging biometric which has rich and stable structure and can potentially be implemented reliably and cost efficiently. Thus human ear recognition has been researched widely and made greatly progress. High recognition rates which are reported in most existing methods can be reached only under closely controlled conditions. Actually a slight amount of rotation and translation which is inescapable would be injurious for system performance. In this paper, a method that uses a transformed type of DCT is implemented to extract meaningful features from ear images. This algorithm is quite robust to ear rotation, translation and illumination. The proposed method is experimented on two popular databases, i.e. USTB II and IIT Delhi II, which achieves significant improvement in the performance in comparison to other methods with good efficiency based on LBP, DSIFT and Gabor. Also because of considering only important coefficients, this method is faster compared to other methods.

show abstract

Human Ear Recognition Using Geometrical Features Extraction

Cited by 69 publications

References 11 publications

Pattern Mining Approaches Used in Sensor-Based Biometric Recognition: A Review

Pattern Mining Approaches Used in Sensor-Based Biometric Recognition: A Review

Unconstrained Ear Recognition through Domain Adaptive Deep Learning Models of Convolutional Neural Network

An Ear Recognition Method Based on Rotation Invariant Transformed DCT

Contact Info

Product

Resources

About