| High quality vein images are used in the vein display device or the vein recognition system.Veins in the captured images are usually unobvious because of the influence of the imaging environment and special vein structure.These captured images are disable to meet the requirements of the vein display equipment and human feature recognition system and it is necessary to be enhanced.In this paper,hand vein image acquisition system was built through combining the low rate zoom microscope with the vein acquisition system.This acquisition system can not only help doctors locate the location of subcutaneous veins accurately in patients with unobvious vein structure under visible light to improve the success rate of venipuncture,but also take vein images to facilitate the analysis of patients' superficial vein diseases.Vein images have the characteristics that the gray level intensity range is change little between the boundary and the background.The enhanced vein image by traditional vein enhancement algorithms has not been well improved and the noise of the original image even has been aggravated.Hand vein image enhancement algorithm based on phase congruency is proposed according to the structure and features of human hand vein images.The method of using the principle of phase consistency to detect the image edge information is not affected by the noise,brightness and contrast in the captured image.Multiple images containing vein edges are acquired by applying phase congruency which parameters are set differently,and two images that contain the majority of vein and less noise are selected by image entropy values,then the chosen images will be enhanced by contrast enhancement.At last,the original image and the enhanced image will be fused in gradient domain to further remove the noise in the image.The experiment results show that the proposed algorithm can enhance the contrast of the hand vein images efficiently,improve the quality of image significantly,and suppress noise perfectly. |
PDF Full Text Request