Title :
An efficiently method for recognizing 3D face based on constructed character
Author :
ZengGang, Lin ; Yanning, Zhang ; Zhe, Guo
Author_Institution :
Shaanxi Provincial Key Lab. of Speech & Image Inf. Process., Northwestern Polytech. Univ., Xi´´an, China
Abstract :
In order to eliminate the effect of the facial expression, and also improve the accuracy of the three dimensional (3D) face recognition, a new 3D face recognition method is proposed in this paper. First, segmenting the key regions and curves which are free from the facial and fully characterize the face; second, resampling curves and regions to uniform the data precision; third, processing data to extract the feature; finally, matching the features of curves and regions to identify 3D face. The Experiment results in actual 3D face database demonstrate the availability and effectiveness of the presented method.
Keywords :
face recognition; image matching; image sampling; image segmentation; 3D face recognition; constructed character; curves resampling; facial expression; feature matching; regions resampling; Algorithm design and analysis; Character recognition; Covariance matrix; Data mining; Face recognition; Feature extraction; Image recognition; Laboratories; Nose; Speech recognition; 3D Face Recognition; Coordinate Normalization; Fourier Transform; Resampling;
Conference_Titel :
Computer Engineering and Technology (ICCET), 2010 2nd International Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-6347-3
DOI :
10.1109/ICCET.2010.5485513
