A deep learning approach for person identification using ear biometrics

Priyadharshini, R.; Arivazhagan, S.; Arun, Madakannu

doi:10.1007/s10489-020-01995-8

Cited by 66 publications

(17 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the performance of the proposed system has compared with other methods that have presented in [37]- [39], where the method in [37] has used CNN classifier for recognizing ear images, while the method in [38] has used three different types of classifiers which are support vector machine (SVM) with radial basis functions (RBF) kernel, and SVM with linear kernel, and K-nearest neighbours (K-NN). The experimental results showed that the K-NN is achieved the best results.…”

Section: Resultsmentioning

confidence: 99%

Ear recognition system using random forest and histograms of oriented gradients techniques

Mutar

Ahmed

Alsemawi

et al. 2022

IJEECS

View full text Add to dashboard Cite

In recent years, systems of ear recognition are considered a significant topic of research in the biometrics field. In such systems, the models of machine learning represent a principal part in order to recognise humans’ identities by using their ear images. In this paper, a system of ear recognition is proposed by using random forest (RF) and histograms of oriented gradients (HOG) techniques. The HOG is used to extract features from ear images. Subsequently, these extracted features will be fed to the RF classifier to classify the ear images with respect to the classes. In this study, the ear images have been selected from the Indian Institute of Technology Delhi, second version (IITD II). The performance of the proposed system has evaluated by using different evaluation measures such as accuracy, specificity, and G-mean. The experimental results show that the proposed system for ear recognition obtains accuracy up to 99.69%. Furthermore, this system archives 99.84% and 80.78% for specificity and G-mean, respectively. The proposed system has the ability to identify persons through their ear images effectively.

show abstract

Section: Resultsmentioning

confidence: 99%

Ear recognition system using random forest and histograms of oriented gradients techniques

Mutar

Ahmed

Alsemawi

et al. 2022

IJEECS

View full text Add to dashboard Cite

show abstract

“…These results refer that proposed technique outperform the compared methods, as well as it utilized techniques such as DWT & PSO to improve the efficiency of the proposed work. Table 6: the results of the comparison between the proposed method and some recent method Method R.R LBP/Laplacian filter method [36] 80% Deep earprint learning [37] 94% The method in [38] 97.36% Proposed method 99%…”

Section: Comparing the Proposed Methods With Some Recent Methodsmentioning

confidence: 99%

An Intelligent Ear Recognition Technique

Hussein¹,

Sahan²

2021

IJASCA

View full text Add to dashboard Cite

The human ear has unique and attractive details; therefore, human ear recognition is one of the most important fields in the biometric domains. In this work, we proposed an efficient and intelligent ear recognition technique based on particle swarm optimization, discrete wavelet transform, and fuzzy neural network. Discrete wavelet transform is used to provide comprise and effective features about the ear image, while the particle swarm optimization utilized to select more effective and attractive features. Furthermore, using particle swarm optimization leads to reduce the complexity of the classification stage since it reduces the number of the features. Fuzzy neural network used in the classification stage in order to provide strong distinguishing between the testing and training ear images. many experiments performed using two ear databases to examine the accuracy of the proposed technique. The analysis of the results refers that the presented technique gained high recognition accuracy using various data sets with less complexity. Keywords: Ear recognition; bio-metric; discrete wavelet transform, particle swarm optimization, fuzzy neural network.

show abstract

“…Noting that comparison of deep with handcrafted features has largely been debated in several literature works (Khaldi et al 2019 ; Korichi et al 2020 ). In another study (Priyadharshini et al 2021 ), a customized six layer deep CNN which is composed of stacked convolution, subsampling, batch and output layers is proposed. The performance of this network is tested on AMI and IIT Delhi II datasets, where effect of varying the network parameters (e.g., learning rate and activation function) was studied.…”

Section: Related Workmentioning

confidence: 99%

MDFNet: an unsupervised lightweight network for ear print recognition

Aiadi

Khaldi

Saadeddine

2022

J Ambient Intell Human Comput

View full text Add to dashboard Cite

In this paper, we propose an unsupervised lightweight network with a single layer for ear print recognition. We refer to this method by MDFNet because it relies on gradient Magnitude and Direction alongside with responses of data-driven Filters. At first, we align ear using Convolution Neural Network (CNN) and Principal Component Analysis (PCA). MDFNet starts by generating a filter bank from training images using PCA. This is followed by a twofold layer, which comprises two operations namely convolution using learned filters and computation of gradient image. To prevent over-fitting, a binary hashing process is done by combining different filter responses into a single feature map. Then, we separately construct histograms for each of gradient magnitude and direction according to the feature map. These histograms are then normalized, using power-L 2 rule, to cope with illumination disparity. Several fusion rules are evaluated to combine the two histograms. The main novelty of MDFNet lies in its simple architecture, effectiveness, the good compromise between processing time and performance it provides along with its high robustness to occlusion. We conduct extensive experiments on three public datasets namely AWE, AMI and IIT Delhi II. Experimental results demonstrate the effectiveness of MDFNet, which achieves high recognition rates (82.5%, 97.67% and 98.96%, respectively), and outperformed several state of the art methods with a high robustness to occlusion. Experiments revealed also the actual need for considering ear alignment.

show abstract

A deep learning approach for person identification using ear biometrics

Cited by 66 publications

References 24 publications

Ear recognition system using random forest and histograms of oriented gradients techniques

Ear recognition system using random forest and histograms of oriented gradients techniques

An Intelligent Ear Recognition Technique

MDFNet: an unsupervised lightweight network for ear print recognition

Contact Info

Product

Resources

About