Near-Infrared Dorsal Hand Vein Image Segmentation by Local Thresholding Using Grayscale Morphology

This paper presents a new method of dorsal hand vein images segmentation based on local thresholding using grayscale morphology. The images, captured by near- infrared CMOS cameras, have poor contrast, speckling noise and non-uniform lighting. After the preprocessing these images normalized, we use dilation and erosion operations to calculate the local thresholding and segment to get the binary images. We do experiments on 40 images effectively. Hence, the research will be significant for real-time applications using infrared vein image segmentation, such as identification systems and vein location or view for humans.