Title :
Person identification from actions based on Artificial Neural Networks
Author :
Iosifidis, Alexandros ; Tefas, Anastasios ; Pitas, Ioannis
Author_Institution :
Dept. of Inf., Aristotle Univ. of Thessaloniki, Thessaloniki, Greece
Abstract :
In this paper, we propose a person identification method exploiting human motion information. A Self Organizing Neural Network is employed in order to determine a topographic map of representative human body poses. Fuzzy Vector Quantization is applied to the human body poses appearing in a video in order to obtain a compact video representation, that will be used for person identification and action recognition. Two feedforward Artificial Neural Networks are trained to recognize the person ID and action class labels of a given test action video. Network outputs combination, based on another feedforward network, is performed in the case of multiple cameras used in the training and identification phases. Experimental results on two publicly available databases evaluate the performance of the proposed person identification approach.
Keywords :
fuzzy set theory; image representation; object recognition; pose estimation; self-organising feature maps; vector quantisation; video coding; action recognition; compact video representation; feedforward artificial neural networks; fuzzy vector quantization; human body poses; human motion information; person identification method; phase identification; phase training; self organizing neural network; topographic map; vision based pattern recognition tasks; Biometrics (access control); Cameras; Databases; Feedforward neural networks; Neurons; Training; Vectors;
Conference_Titel :
Computational Intelligence in Biometrics and Identity Management (CIBIM), 2013 IEEE Workshop on
Conference_Location :
Singapore
DOI :
10.1109/CIBIM.2013.6607907