Comparative study of 1D-local descriptors for ear biometric system

Regouid, Meryem; Touahria, Mohamed; Benouis, Mohamed; Mostefai, L.; Lamiche, Imane

doi:10.1007/s11042-022-12700-x

Cited by 5 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results demonstrated that employing ear segmentation rather than original images improves the recognition performance. Regouid et al [18] explored the transformation of two-dimensional ear images into one-dimensional representations. Their investigation focused on the one-dimensional local binary patterns (1D-LBP) descriptor and its variations as an alternative solution for feature extraction.…”

Section: Handcrafted Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Boosting the Performance of Deep Ear Recognition Systems Using Generative Adversarial Networks and Mean Class Activation Maps

Bouaouina,

Benzaoui,

Doghmane

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Ear recognition is a complex research domain within biometrics, aiming to identify individuals using their ears in uncontrolled conditions. Despite the exceptional performance of convolutional neural networks (CNNs) in various applications, the efficacy of deep ear recognition systems is nascent. This paper proposes a two-step ear recognition approach. The initial step employs deep convolutional generative adversarial networks (DCGANs) to enhance ear images. This involves the colorization of grayscale images and the enhancement of dark shades, addressing visual imperfections. Subsequently, a feature extraction and classification technique, referred to as Mean-CAM-CNN, is introduced. This technique leverages mean-class activation maps in conjunction with CNNs. The Mean-CAM approach directs the CNN to focus specifically on relevant information, extracting and assessing only significant regions within the entire image. The process involves the implementation of a mask to selectively crop the pertinent area of the image. The cropped region is then utilized to train a CNN for discriminative classification. Extensive evaluations were conducted using two ear recognition datasets: mathematical analysis of images (MAI) and annotated web ears (AWEs). The experimental results indicate that the proposed approach shows notable improvements and competitive performance: the Rank-1 recognition rates are 100.00% and 76.25% for MAI and AWE datasets, respectively.

show abstract

Section: Handcrafted Methodsmentioning

confidence: 99%

“…The comparison reveals satisfactory Rank-1 recognition rates for most of the analyzed papers, such as [18,[20][21][22][23][24][25][26][27][28], achieving rates surpassing 93% with the MAI dataset. Conversely, our approach exhibits the highest and most competitive performance, reaching a Rank-1 recognition rate of 100.00%.…”

Section: Comparisonmentioning

confidence: 97%

Boosting the Performance of Deep Ear Recognition Systems Using Generative Adversarial Networks and Mean Class Activation Maps

Bouaouina,

Benzaoui,

Doghmane

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Raghavendra et al [47] 86.36% --Alshazly et al [48] 70.20% --Chowdhury et al [49] 67.26% --Hassaballah et al [50] 73.71% --Alshazly et al [42] 94.50% 99.40% 98.90% Alshazly et al [43] 97.50% 99.64% 98.41% Omara et al [51] 97.84% --Zhang et al [52] 93.96% --Omara et al [53] 96.82% --Khaldi et al [44] 96.00% 99.00% 94.47% Hassaballah et al [24] 72.29% --Ahila et al [2] 96.99% --Khaldi et al [54] 98.33% --Alshazly et al [45] 99.64% 100% 98.99% Aiadi et al [55] 97.67% --Sharkas [56] 99.45% --Ebanesar et al [57] 98.99% --Kohlakala et al [58] 99.20% --Our method (CFDCNet) 99.70% 100% 99.01% [16] 49.60% --Dodge et al [59] 56.35% 74.80% -Dodge et al [59] 68.50% 83.00% -Zhang et al [30] 50.00% 70.00% -Emersic et al [46] 62.00% 80.35% 95.51% Khaldi et al [44] 50.53% 76.35% 80.97% Hassaballah et al [24] 54.10% --Khaldi et al [60] 48.48% --Khaldi et al [54] 51.25% --Alshazly et al [45] 67.25% 84.00% 96.03% Regouid et al [61] 43.00% --Kacar et al [62] 47.80% 72.10% 95.80% Sajadi et al [25] 53.50% --Omara et al [63] 72 accurately extract the characteristics of ear images through a small number of ear samples and improve the accuracy of human ear recognition.…”

Section: R1 R5 Aucmentioning

confidence: 99%

A Feature Fusion Human Ear Recognition Method Based on Channel Features and Dynamic Convolution

Liu

et al. 2023

Symmetry

View full text Add to dashboard Cite

Ear images are easy to capture, and ear features are relatively stable and can be used for identification. The ear images are all asymmetric, and the asymmetry of the ear images collected in the unconstrained environment will be more pronounced, increasing the recognition difficulty. Most recognition methods based on hand-crafted features perform poorly in terms of recognition performance in the face of ear databases that vary significantly in terms of illumination, angle, occlusion, and background. This paper proposes a feature fusion human ear recognition method based on channel features and dynamic convolution (CFDCNet). Based on the DenseNet-121 model, the ear features are first extracted adaptively by dynamic convolution (DY_Conv), which makes the ear features of the same class of samples more aggregated and different types of samples more dispersed, enhancing the robustness of the ear feature representation. Then, by introducing an efficient channel attention mechanism (ECA), the weights of important ear features are increased and invalid features are suppressed. Finally, we use the Max pooling operation to reduce the number of parameters and computations, retain the main ear features, and improve the model’s generalization ability. We performed simulations on the AMI and AWE human ear datasets, achieving 99.70% and 72.70% of Rank-1 (R1) recognition accuracy, respectively. The recognition performance of this method is significantly better than that of the DenseNet-121 model and most existing human ear recognition methods.

show abstract

Local tri directional pattern (LTDP): a novel descriptor for face recognition in unconstrained conditions

Karanwal

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Comparative study of 1D-local descriptors for ear biometric system

Cited by 5 publications

References 40 publications

Boosting the Performance of Deep Ear Recognition Systems Using Generative Adversarial Networks and Mean Class Activation Maps

Boosting the Performance of Deep Ear Recognition Systems Using Generative Adversarial Networks and Mean Class Activation Maps

A Feature Fusion Human Ear Recognition Method Based on Channel Features and Dynamic Convolution

Local tri directional pattern (LTDP): a novel descriptor for face recognition in unconstrained conditions

Contact Info

Product

Resources

About