Palm vein recognition based on multi-sampling and feature-level fusion

Yan, Xuekui; Kang, Wenxiong; Deng, Feiqi; Wu, Qiuxia

doi:10.1016/j.neucom.2014.10.019

Cited by 80 publications

(71 citation statements)

References 36 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further modified edge detection algorithm is applied on CH and CV to retain the significant texture features, which in turn reduces the dimension drastically. The algorithm uses multi-step to extract features of edges along with noise suppression simultaneously [17]. 1) The filter in Eq.…”

Section: D-edge Detectionmentioning

confidence: 99%

Dimension Reduction of Hand and Face Feature Level Fusion in Multimodal Biometric Authentication

Gowda¹,

AN²

2019

IJITEE

View full text Add to dashboard Cite

The proposed work is a multimodal biometric authentication approach with image texture feature dimension reduction of trained feature vector which leads reduction in memory size and in turn reduces the computational time. In this paper hand and face features are used for person identification. The texture features of hand image are extracted using Haar and several Daubechie’s of 2D-DWT followed by 2D- edge detector gives better identification with reduction in feature vector and face features are extracted by neighborhood common characterization with block based segmentation approach to estimate the disparity in face. The neighborhood common characterization based structure recognition with a person representative per sample is more effective. The neighborhood features are constructed by extracting the similar blocks in the image, the intra pixel disparity feature is obtained by exploiting external common images to estimate the feasible facial disparities. Neighborhood common characterization reduces the overall residual of the given features over the local feature, common disparity dictionary, and shape based residual of a block. Neighbourhood common characterization representation, of face recognize with one representative per person more effectively. The system uses either of the biometric traits for person identification with 99.98% of authentication rate.

show abstract

Section: D-edge Detectionmentioning

confidence: 99%

Dimension Reduction of Hand and Face Feature Level Fusion in Multimodal Biometric Authentication

Gowda¹,

AN²

2019

IJITEE

View full text Add to dashboard Cite

show abstract

“…To learn these parameters, we maximize the conditional likelihood through a sigmoid function, i.e., p(y = 1|x p , x c ) = σ(f (x p , x c )), with L 2 regularization added where sigmoid function σ is defined to be σ(x) = 1 1+e −x . Yan et al (2015), and hence it is desirable to utilize multiple feature information for our mixed kinship verification task. However, multiple feature descriptors generally have multiple modalities.…”

Section: Mixed Kinship Verificationmentioning

confidence: 99%

Mixed bi-subject kinship verification via multi-view multi-task learning

Qin

Tan²,

Chen³

2016

Neurocomputing

View full text Add to dashboard Cite

Bi-subject kinship verification addresses the problem of verifying whether there exists some kind of kin relationship (i.e., father-son, father-daughter, motherson and mother-daughter) between a pair of parent-child subjects based purely on their visual appearance. The task is challenging due to the involvement of two different subjects possibly with different genders and ages. In addition, collecting sufficient training samples for each type of kinship is difficult. In this work, we present a novel method to address these issues by considering each type of kin relation verification as one task and learning them at one time in the framework of multi-task learning, by sharing feature sets and useful structures among the tasks.Particularly our contributions are three folds: first, we introduce a new type of learning problem, called mixed bi-subject kinship verification, to the topic of bi-subject kinship verification: instead of simply verifying whether some fixed kinship relationship (e.g., mother-son) can be established for a given pair of parent-child images, we try to figure out whether any type of the four kinship relations can be established according to the visual features of the image pair, with no need to know the genders of the subjects to be verified beforehand. Second, we propose a novel multi-task learning method to address this problem with two transformation matrices -one is shared amongst all the tasks and the other is unique to each task. Both matrices are simultaneously learned in a joint framework, which enables our algorithm to utilize the common knowledge of the four tasks. Third, we propose a multi-view multi-task learning(MMTL) method to perform multiple feature fusion to improve the mixed bi-subject kinship verification performance. Extensive experiments on the large scale KinFaceW kinship database demonstrate the feasibility and effectiveness of the proposed algorithm.

show abstract

“…Matching scores are computed and authentication is performed with an equal error rate of 1.14%. As suggested by previous studies [19], [7], image processing on single palm image often is not enough for user authentication. Fusion techniques and supervised learning are used on multiple sample images for the same user for efficient recognition.…”

Section: Introductionmentioning

confidence: 95%

“…A similarity measure based on normalized Hamming distance is used for user authentication. Yan et al proposed in [19] an algorithm for user recognition based on image fusion technique applied on multiple palm image samples. They observed that it is difficult to obtain sufficient features for effective recognition using a SIFT algorithm on a single image.…”

Section: Introductionmentioning

confidence: 99%

Dorsal Hand Vein Pattern Analysis and Neural Networks for Biometric Authentication

Belean¹,

Streza²,

Crisan³

et al. 2017

STUD INFORM CONTROL

View full text Add to dashboard Cite

Over the past several years, the subcutaneous blood vessels have emerged as a new solution for identity management. Biometric systems based on hand veins are considered to be very promising for high security environments. In this paper, we propose a novel user authentication approach based on dorsal hand vein pattern analysis and multi-layer perceptron neural network classification. For image processing two different techniques are employed: rotation invariant Hough transform and clustering based segmentation and mathematic morphology. Both approaches lead to binary images containing the vein patterns. The vessel structure corresponding to hand image samples of the same user are used to extract the final features, independent of hand rotation and distance to the camera lens during acquisition. These characteristics are used to train the neural network, whereas are computed for the new input images to be classified as corresponding to one of the legitimate subjects or not. The experimental analysis shows that user classification with an equal error rate of 0.83% can be attained, bringing the advantages of proposed image processing techniques for vein detection and neural network classification into complete synergy.

show abstract

Palm vein recognition based on multi-sampling and feature-level fusion

Cited by 80 publications

References 36 publications

Dimension Reduction of Hand and Face Feature Level Fusion in Multimodal Biometric Authentication

Dimension Reduction of Hand and Face Feature Level Fusion in Multimodal Biometric Authentication

Mixed bi-subject kinship verification via multi-view multi-task learning

Dorsal Hand Vein Pattern Analysis and Neural Networks for Biometric Authentication

Contact Info

Product

Resources

About