Super-Resolution Reconstruction of Finger Vein Image Based on Regression Tree Model
作者单位：School of AutomationHarbin University of Science and Technology
会议名称：《第32届中国控制与决策会议》
会议日期：2020年
学科分类：0831[工学-生物医学工程（可授工学、理学、医学学位）] 08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 0836[工学-生物工程]
关 键 词：Super-Resolution DCT Random Forest Vein Histogram Equalization
摘 要：Because the speed of clear fingerprint vein acquisition is slow,and the influence of some acquisition equipment makes the acquired vein graphics are relatively poor,this paper is based on random forest and DCT algorithm for super-resolution reconstruction of blurred *** random forest algorithm avoids overfitting the data and solves the classification *** transform compresses the image space to further speed up the training speed of the *** experimental result shows that the method is easy to converge during the process of training and has better image reconstruction quality.