FAV-Net: A Simple Single-Shot Self-attention Based ForeArm-Vein Biometric

Prasad, Shitala; Tang, Chaoying; Zhang, Yufeng; Wang, Biao

doi:10.1007/978-3-031-31417-9_34

Cited by 1 publication

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To keep the value of the loss function, we can decrease the value 𝜃 𝑦 𝑖 or increase the value 𝜃 𝑗 . That is to say, the embedding feature output by the network should be closer to the weight of the same class or farther away from those of other classes [22]. The Arcface loss function is illustrated in Fig.…”

Section: Loss Function and Training Strategymentioning

confidence: 99%

Deep Learning-Based Small Sample Body Vein Recognition and Its Implementation

Tang,

Prasad,

Zhang

2024

Preprint

View full text Add to dashboard Cite

In scenarios like forensic investigations, only RGB images of body parts, especially limbs, are available from surveillance. Traditional biometric methods like face, fingerprints, and iris scans are not applicable in such cases. Additionally, hand veins, typically captured using NIR imaging, are not accessible either. To address this challenge, body vein recognition technology has been introduced. Different techniques have been proposed to uncover and extract vein patterns from RGB images. However, handcrafted features are sensitive to image noise, and deep learning methods require extensive training data, which is lacking in forensic investigations. In this study, we presented a small-sample body vein recognition approach based on deep learning. A data augmentation method utilizing Gabor filtering and vein line traction was introduced to enhance generalization performance and tackle the limitation of training samples. A new model combining improved DenseNet and Arcface loss was developed for body vein recognition. Furthermore, a feature retrieval scheme based on binary hash coding was introduced to optimize recognition accuracy and retrieval efficiency. Experimental results using images from 250 forearms and 230 thighs demonstrated the superiority of our small-sample body vein recognition method over other matching techniques. Ablation studies confirmed the effectiveness of the data augmentation and feature retrieval schemes. Finally, the model was deployed on a portable system, leading to the implementation of a contactless body vein recognition system.

show abstract

Section: Loss Function and Training Strategymentioning

confidence: 99%