-
Chapter and Conference Paper
An Improved Lightweight Network Based on MobileNetV3 for Palmprint Recognition
In recent years, there has been an increasingly urgent need for individual identification in various application scenarios. Palmprint has numerous advantages due to its uniqueness and security. Deep learning b...
-
Chapter and Conference Paper
Low-illumination Palmprint Image Enhancement Based on U-Net Neural Network
Palmprint has a high application prospect due to the stability, uniqueness, difficulty of reproduction, easy acquisition and high user acceptance of its own texture characteristics. However, palmprint images a...
-
Chapter and Conference Paper
PSU-Net: Paired Spatial U-Net for Hand Segmentation with Complex Backgrounds
Hand segmentation, as a key part of human-computer interaction, palmprint recognition and gesture recognition, is prone to interference from complex backgrounds subsequently resulting in poor segmentation accu...
-
Chapter and Conference Paper
Region of Interest Extraction for Closed Palm with Complex Background
The tilt of the closed palm can make it impossible to accurately locate the region of interest (ROI) in contactless palmprint recognition systems. In order to accurately extract the closed palm ROI in the tilt...