CompNet: Competitive Neural Network for Palmprint Recognition Using Learnable Gabor Kernels

Xu, Liang; Yang, Jinyang; Lu, Yao; Zhang, David

doi:10.1109/lsp.2021.3103475

Cited by 28 publications

(16 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Among all the methods, (x) mAlexNet and (xi) mMo-bileNet show low identification accuracy since the training and test images are from different databases. The identification accuracy of CompNet [29], (xii) PB-CM, and (xiii) PB-HBM is 100%, and (xiv) PB-HBM-CSC achieves the next highest accuracy. These results demonstrate the effectiveness of phase-based matching (xii)-(xiv) in palmprint identification in terms of identification accuracy.…”

Section: Resultsmentioning

confidence: 99%

“…These CNNs can be trained with a limited number of training images. In addition to the above CNN-based methods, we refer to the results of 6 state-of-the-art methods: PalmNet [25], JCLSR [27], CompNet [29], SMHNet [18], DDH [30], and LCDDR [28]. Note that we refer only to results for which the experimental conditions are almost the same.…”

Section: A Methodsmentioning

confidence: 99%

“…They also proposed a Learning Complete and Discriminative Direction Representation (LCDDR) method [28]. Liang et al [29] proposed CompNet consisting of Learnable Gabor Convolution (LGC) layer, PostProcessing Unit (PPU), and multisize Competitive Blocks (CBs). Liu et al [18] proposed Similarity Metric Hashing Network (SMHNet), which extracts plamprint features using a simple CNN, calculates scores by Structural Similarity Index Measure (SSIM), and compresses features by hashing.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Phase-Based Palmprint Identification With Convolutional Sparse Coding

Marval-Perez

Ito

Aoki

2022

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

Phase-based image matching has shown high recognition accuracy in palmprint verification. The algorithm compares a pair of palmprint images by extracting local phase features from the images and computing local correlation functions between them. A major drawback of this algorithm is its high computational cost associated with the evaluation of local correlation functions. This needs to be addressed, especially in the case of one-to-many comparisons required for palmprint identification. The problem becomes increasingly severe as the number of enrolled images increases. In this paper, we propose a novel palmprint identification algorithm with low computational complexity, which employs a sparse representation of enrolled phase features (i.e., phase templates) to evaluate local correlation functions. For this purpose, we also develop an efficient Convolutional Sparse Coding (CSC) algorithm that can derive a compact representation of phase templates. The proposed method reduces the computational cost of phase-based palmprint identification without significant degradation of recognition performance. Our experiments using public databases clearly demonstrate the advantage of the proposed method over conventional methods.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: A Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Phase-Based Palmprint Identification With Convolutional Sparse Coding

Marval-Perez

Ito

Aoki

2022

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

show abstract

“…Matkowski et al [39] proposed a palmprint recognition method suitable for low-constraint scenarios, which uses a cascading network structure consisting of two sub-networks to perform ROI segmentation and feature extraction tasks respectively. Liang et al [40] proposed CompNet, which uses CNN to learn the parameters of Gabor filter and effectively utilizes the direction information in palmprint through special Softmax and channel convolution operations. CompNet has lower equal error rate compared with the existing methods, and has fewer parameters in the network, so it is easy to train.…”

Section: Deep-learning-based Methodsmentioning

confidence: 99%

“…The reconstructed image dataset is the reconstructed images generated by the BMS, which contains 300 images. The adversarial sample dataset contains 400 adversarial samples generated by FGSM against CompNet[40]. At the same time, two kinds of presentation attack datasets should be made based on these three datasets, namely, monitor presentation attack dataset and paper presentation attack data set.…”

mentioning

confidence: 99%

Presentation Attacks in Palmprint Recognition Systems

Sun¹,

Wang²

2022

J Multimed Inf Syst

View full text Add to dashboard Cite

Background: A presentation attack places the printed image or displayed video at the front of the sensor to deceive the biometric recognition system. Usually, presentation attackers steal a genuine user's biometric image and use it for presentation attack. In recent years, reconstruction attack and adversarial attack can generate high-quality fake images, and have high attack success rates. However, their attack rates degrade remarkably after image shooting. Methods: In order to comprehensively analyze the threat of presentation attack to palmprint recognition system, this paper makes six palmprint presentation attack datasets. The datasets were tested on texture coding-based recognition methods and deep learning-based recognition methods. Results and conclusion: The experimental results show that the presentation attack caused by the leakage of the original image has a high success rate and a great threat; while the success rates of reconstruction attack and adversarial attack decrease significantly.

show abstract