English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

With the growing demand for hand hygiene and convenience of use, palmprintrecognition with touchless manner made a great development recently, providingan effective solution for person identification. Despite many efforts that havebeen devoted to this area, it is still uncertain about the discriminativeability of the contactless palmprint, especially for large-scale datasets. Totackle the problem, in this paper, we build a large-scale touchless palmprintdataset containing 2334 palms from 1167 individuals. To our best knowledge, itis the largest contactless palmprint image benchmark ever collected with regardto the number of individuals and palms. Besides, we propose a novel deeplearning framework for touchless palmprint recognition named 3DCPN (3DConvolution Palmprint recognition Network) which leverages 3D convolution todynamically integrate multiple Gabor features. In 3DCPN, a novel variant ofGabor filter is embedded into the first layer for enhancement of curve featureextraction. With a well-designed ensemble scheme,low-level 3D features are thenconvolved to extract high-level features. Finally on the top, we set aregion-based loss function to strengthen the discriminative ability of bothglobal and local descriptors. To demonstrate the superiority of our method,extensive experiments are conducted on our dataset and other popular databasesTongJi and IITD, where the results show the proposed 3DCPN achievesstate-of-the-art or comparable performances.

Touchless Palmprint Recognition based on 3D Gabor Template and Block Feature Refinement