Title :
Multi-sensorial inputs for the identification of persons with synergetic computers
Author :
Wagner, Thomas ; Dieckmann, Ulrich
Author_Institution :
Fraunhofer-Inst. for Integrated Circuits, Erlangen, Germany
Abstract :
We present an approach to combine the optical motion analysis of the lips and acoustic voice analysis of defined single words for identifying the people speaking. Due to the independence of the different data sources, a higher reliability of the results in comparison with simple optical lip reading is observed. The classification of the preprocessed data is done by synergetic computers, which have attracted increasing attention as robust algorithms for solving industrial classification tasks. Special potential of synergetic computers lies in their close mathematical similarity to self-organized phenomena in nature. Therefore they present a clear perspective for hardware realizations. We propose that the combination of motion and voice analysis offers a possibility for realizing robust access control systems
Keywords :
acoustic signal processing; biometrics (access control); image sequences; motion estimation; speaker recognition; speech processing; acoustic voice analysis; data sources; hardware realizations; industrial classification tasks; lips; motion analysis; multi-sensorial inputs; optical motion analysis; persons identification; preprocessed data classification; reliability; robust access control systems; robust algorithms; self-organized phenomena; synergetic computers; Access control; Computer industry; Electrical equipment industry; Hardware; Identification of persons; Lips; Motion analysis; Robust control; Robustness; Speech analysis;
Conference_Titel :
Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference
Conference_Location :
Austin, TX
Print_ISBN :
0-8186-6952-7
DOI :
10.1109/ICIP.1994.413577
