Recognition Method for 3D Occluded Face Based on Ridge Point Features
WANG Lijuan
WANG Jiehao
WEI Yifan
Abstract：A simple yet effective method for the recognition of occluded 3D face is proposed in this paper.The method is main-ly based on the ridge points model of the 3D occluded face.The spatial distribution of the ridge points of each occluded region of the face is used to determine whether the region is occluded or not.After that,the ridge point sets of the un-occluded region are repre-sented by 3D Shape Context descriptor and compared with the ridge point sets of the corresponding region of 3D face template.Differ-ent weights are assigned to the matching results of each region,and the overall matching results are obtained.The method is tested on the Bosphorus and UMB-DB database.The results show that the occluded area can be detected effectively and the 3D occluded face can be effectively recognized with high accuracy.
Keywords：3D face recognitionocclusionridge pointshape contextord
Publication Date：2025-01-19
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：6( 103-107,163 )