This paper presents person identification algorithm based on 3D hand geometry. The algorithm comprises the following phases of 3D hand scan processing: segmentation, feature extraction and comparison, which the authors explain in detail in the paper. The authors present results of algorithm performance tested on publicly available DMCSv1 database which contains 1400 samples of 3D hand scans of left and right hand acquired from 35 individuals. Obtained values of equal error rate are 16% for the left hand scans, 17% for the right hand scan sand the values of rank-1 accuracy are 85% and 82% for the left and right hand scans, respectively.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.