A Method for Hand Dorsal Vein Recognition Based on Frangi and Morphological Operation

Aiming at the problem of image recognition of the hand dorsal vein, a method for hand dorsal vein recognition based on Frangi and morphological operation (Frangi-M) is proposed. Frangi-M combines the Frangi algorithm and morphological operation. Firstly, the Frangi algorithm is used to enhance the vascular structure of the hand dorsal vein by using the difference of the Hessian matrix eigenvalues of the points in the vascular part and the non-vascular part of the image, and then morphological operations and median filtering are used to eliminate image spots and smooth the image. Frangi-M was compared to the adaptive threshold method and Butterworth high-pass filter method by using qualitative and quantitative evaluation methods. Both qualitative and quantitative evaluation results show that Frangi-M has the clearest and most complete identification of the hand dorsal vein. In the quantitative evaluation, the precision, recall, and [email protected] of the YOLOv5 hand dorsal vein recognition model generated by Frangi-M are 0.90, 0.86, and 0.90, respectively, while those of the adaptive threshold method are 0.87, 0.82, and 0.89, respectively, and those of the Butterworth high-pass filter method are 0.85, 0.82, and 0.85, respectively.