Hybrid approaches to frontal view face recognition using the hidden Markov model and neural network

Abstract In this paper, for frontal view face recognition a hidden Markov model (HMM) algorithm and hybrid approaches using the HMM and neural network (NN) are proposed. In the preprocessing stage, edges of a face are detected using the conventional locally adaptive threshold (LAT) scheme and facial features are extracted based on generic knowledge of facial components. In constructing a database with normalized features, we employ HMM parameters of each person computed by the forward-backward algorithm. Computer simulation shows that the proposed HMM-NN algorithm yields higher recognition rate compared with several conventional face recognition algorithms.

[1]  Ian Craw,et al.  Automatic extraction of face-features , 1987, Pattern Recognit. Lett..

[2]  Tsunehiro Aibara,et al.  Human face profile recognition by a P-Fourier descriptor , 1993 .

[3]  Kiyoharu Aizawa,et al.  Detection and tracking of facial features , 1995, Other Conferences.

[4]  Horace Ho-Shing Ip,et al.  Human face recognition using Dempster-Shafer theory , 1994, Proceedings of 1st International Conference on Image Processing.

[5]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[6]  Thomas S. Huang,et al.  Frontal-view face detection , 1995, Other Conferences.

[7]  Gerhard Rigoll,et al.  Maximum mutual information neural networks for hybrid connectionist-HMM speech recognition systems , 1994, IEEE Trans. Speech Audio Process..

[8]  Dirk Van Compernolle,et al.  Multilayer perceptrons as labelers for hidden Markov models , 1994, IEEE Trans. Speech Audio Process..

[9]  Ashok Samal,et al.  Automatic recognition and analysis of human faces and facial expressions: a survey , 1992, Pattern Recognit..

[10]  L. D. Harmon,et al.  Identification of human face profiles by computer , 1978, Pattern Recognit..

[11]  Richard Lippmann,et al.  Hybrid neural-network/HMM approaches to wordspotting , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[12]  Philip D. Wasserman,et al.  Neural computing - theory and practice , 1989 .

[13]  Yoshio Hirose,et al.  Backpropagation algorithm which varies the number of hidden units , 1989, International 1989 Joint Conference on Neural Networks.

[14]  Edward R. Dougherty,et al.  Morphological methods in image and signal processing , 1988 .

[15]  Rae-Hong Park,et al.  Fuzzy-based recognition of human front faces using the trapezoidal membership function , 1995, Proceedings of 1995 IEEE International Conference on Fuzzy Systems..

[16]  Yoshio Nagashima,et al.  Image analysis for face modeling and facial image reconstruction , 1990, Other Conferences.

[17]  G. S. Robinson.  Edge detection by compass gradient masks , 1977 .

[18]  Rae-Hong Park,et al.  Knowledge-based face recognition using neural networks , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[19]  Rae-Hong Park,et al.  Recognition of human front faces using knowledge-based feature extraction and neurofuzzy algorithm , 1996, Pattern Recognit..