Identity recognition based on the external shape of the human ear

Benzaoui, Amir; Hezil, Nabil; Boukrouche, Abdelhani

doi:10.1109/arcse.2015.7338129

Cited by 24 publications

(27 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The presented results are comparable to what was reported by other authors for similar techniques on the same datasets, e.g., [39], [41], [56], [78], [80], which suggests that the AWE toolbox provides competitive implementations of all evaluated descriptor-based techniques.…”

Section: Methodssupporting

confidence: 88%

Ear recognition: More than a survey

2017

View full text Add to dashboard Cite

Automatic identity recognition from ear images represents an active field of research within the biometric community. The ability to capture ear images from a distance and in a covert manner makes the technology an appealing choice for surveillance and security applications as well as other application domains. Significant contributions have been made in the field over recent years, but open research problems still remain and hinder a wider (commercial) deployment of the technology. This paper presents an overview of the field of automatic ear recognition (from 2D images) and focuses specifically on the most recent, descriptorbased methods proposed in this area. Open challenges are discussed and potential research directions are outlined with the goal of providing the reader with a point of reference for issues worth examining in the future. In addition to a comprehensive review on ear recognition technology, the paper also introduces a new, fully unconstrained dataset of ear images gathered from the web and a toolbox implementing several stateof-the-art techniques for ear recognition. The dataset and toolbox are meant to address some of the open issues in the field and are made publicly available to the research community. Index Terms-biometry, dataset, in-the-wild, unconstrained image, descriptor-based method, open-source toolbox, ear recognition• Survey: We present a comprehensive survey on ear recognition, which is meant to provide researchers in this field with a recent and up-to-date overview of the state-of-technology. We introduce a taxonomy of the existing 2D ear recognition approaches, discuss the characteristics of the technology and review the existing state-of-the-art. Most importantly, we elaborate on the open problems and challenges faced by the technology. • Dataset: We make a new dataset of ear images available to the research community. The dataset, named Annotated Web Ears (AWE), contains images collected from the web and is to the best of our knowledge the first dataset for ear recognition gathered "in the wild". The images of the AWE dataset contain a

show abstract

Section: Methodssupporting

confidence: 88%

Ear recognition: More than a survey

2017

View full text Add to dashboard Cite

show abstract

“…This is likely due to the increased complexity of the images of the USTB II dataset and the fact that the images of the IITD II dataset are more tightly cropped than the images of the USTB II dataset. To compare the performance of the proposed technique with the state of the art PCA and learning based techniques, the Top-1 experimental results of the proposed 2D-CMBPCA, single image PCA, [5] 89.78% 24.28% 2D-MBPCA [13] 92.76% 53.90% Proposed Technique 94.14% 52.90% Learning based Techniques BSIF [20] 97.31% -Wavelet and Neural Network [9] -97.50%…”

Section: Experimental Results For the Proposed 2d-wmbpca Methodsmentioning

confidence: 99%

“…eigenfaces [5], 2D-MBPCA [13], BSIF [20], and wavelet and neural network based [9] techniques are tabulated in Table V. From Table V, it is apparent that the proposed 2D-WMBPCA technique significantly outperforms the single image PCA and the eigenfaces method and gives competitive results for the images of the IITD II dataset when compared with learning based techniques.…”

Section: Experimental Results For the Proposed 2d-wmbpca Methodsmentioning

confidence: 99%

Single Image Ear Recognition Using Wavelet-Based Multi-Band PCA

Zarachoff

Sheikh-Akbari

Monekosso

2019

2019 27th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Principal Component Analysis (PCA) has been successfully used for many applications, including ear recognition. This paper presents a 2D Wavelet based Multi-Band PCA (2D-WMBPCA) method, inspired by PCA based techniques for multispectral and hyperspectral images, which have shown a significantly higher performance to that of standard PCA. The proposed method performs 2D non-decimated wavelet transform on the input image dividing the image into its subbands. It then splits each resulting subband into a number of bands evenly based on the coefficient values. Standard PCA is then applied on each resulting set of bands to extract the subbands eigenvectors, which are used as features for matching. Experimental results on images of two benchmark ear image datasets show that the proposed 2D-WMBPCA significantly outperforms both the standard PCA method and the eigenfaces method.

show abstract

“…Scenario 1 : In this scenario, one ear image of each subject is chosen for training and the remaining ones are used for testing. Since the subjects in these four databases have at least three images, most competing methods [24, 50] conduct three experiments by, respectively, using the first, the second, or the third images per subject for training. Then, the average recognition rate is given in [24, 50].…”

Section: Resultsmentioning

confidence: 99%

Learning pairwise SVM on hierarchical deep features for ear recognition

Omara

Zhang

et al. 2018

IET biom.

View full text Add to dashboard Cite

Convolutional neural networks (CNNs)-based deep features have been demonstrated with remarkable performance in various vision tasks, such as image classification and face verification. Compared with the hand-crafted descriptors, deep features exhibit more powerful representation ability. Typically, higher layer features contain more semantic information, while lower layer features can provide more low-level description. In addition, it turns out that the fusion of different layer features will lead to superior performance. Here, we propose a novel approach for human ear identification by combining hierarchical deep features. First, hierarchical deep features are extracted from ear images using CNN pre-trained on large-scale data set. To enhance the feature representation and reduce the high dimension of deep features, the discriminant correlation analysis (DCA) is adopted for fusing deep features from different layers for further improvement. Owing to the lack of ear images per person, the authors propose to transform the ear identification problem to the binary classification by composing pairwise samples and resolve it with the pairwise support vector machine (SVM). Experiments are conducted on four public databases: USTB I, USTB II, IIT Delhi I, and IIT Delhi II. The proposed method achieves promising recognition rate and exhibits decent performance compared with the state-of-the-art methods.

show abstract

Identity recognition based on the external shape of the human ear

Cited by 24 publications

References 24 publications

Ear recognition: More than a survey

Ear recognition: More than a survey

Single Image Ear Recognition Using Wavelet-Based Multi-Band PCA

Learning pairwise SVM on hierarchical deep features for ear recognition

Contact Info

Product

Resources

About