Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

A Novel Method of Hand Measurement Point Recognition Based on the MLS Image Registration

NIE Lei1,WU Zhuang-zhi1,LAI Jun2,MA Teng1(1.School of Computer Science and Engineering,Beihang University,Beijing 100191,China;2.Quartermaster Research Institute of the PLA General Logistics Department,Beijing 100010,China)  
Hand shape measurement is an important part of anthropometry,and also a way of identity authentication.The non-contact hand measurement based on 2D image is widely studied and applied.This paper proposes a novel automatic method of hand measurement point recognition.The method is based on the MLS image registration technique;adopts the DOS(Different Of Slope) method to get the corresponding points of any two images;an undirected weighted graph based on the hand pixel point set is created,and the Euclidean distance is replaced by the Dijkstra shortest path to calculate the weight function.Compared with the traditional method based on the feature extraction and statistics,the experimental results show that the method features conciseness,uniformity,and efficiency.The robustness,accuracy and recognition rate of the method is also prominently improved.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved