2026-05-01T10:32:26Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/4886 2021-12-13T02:02:56Z 1582963302567:1597824273898 user-ucsy

Finger Vein Recognition based on Histogram of Oriented Gradients (HOG) Htwe, Khin Sabai Aye, Nyein In this paper, a Region of Interest (ROI)extraction method is proposed based on labeling veinimages using morphological processing. Firstly,finger vein images are segmented to remove theunwanted background or the shape of the device.Secondly, the images are oriented to correct to solvethe finger displacement’s problem. Thirdly, ROIlocalization method is used to accurately extract theregion of vein vessels. Finally, Histogram of OrientedGradient (HOG) features are extracted to recognizethat person is the genuine or imposter. Segmentedfinger vein and calculated orientation can supporteach other to produce higher accuracy in localizingROIs. In addition, a simple feature differencingmethod is proposed to reduce the calculation time formatching. 2017-02-16 http://hdl.handle.net/20.500.12678/0000004886 https://meral.edu.mm/records/4886