ROI processing for visual features extraction in lip-reading
作者： Xiaoping Wang , Yufeng Hao , Degang Fu , Chunwei Yuan
DOI: 10.1109/ICNNSP.2008.4590335
关键词: Hidden Markov model 、 Image processing 、 Feature extraction 、 Region of interest 、 Artificial intelligence 、 Discrete cosine transform 、 Edge detection 、 Computer vision 、 Pattern recognition 、 Edge enhancement 、 Image segmentation 、 Computer science
摘要: Region of interest (ROI) is the key basis visual features extraction in lip-reading process. In this paper, we discussed ROI processing method and explored its impact on recognition accuracy with comparison four kinds processed ROIs obtained by using basic image methods: gray-scale normalization, difference enhancement, edge enhancement segmentation. Then tasks for speaker-independent were carried out aid continuous hidden Markov model (CHMM). The experimental results show that discrete cosine transform (DCT) based features, normalized can achieve best performance among these ROIs.
sci-hub.se 参考文章(17)
Eric David Petajan, Automatic lipreading to enhance speech recognition (speech reading) University of Illinois at Urbana-Champaign. ,(1984)
K.D. Lee, M.J. Lee, Soo-Young Lee, Extraction of frame-difference features based on PCA and ICA for lip-reading international joint conference on neural network. ,vol. 1, pp. 232- 237 ,(2005) , 10.1109/IJCNN.2005.1555835
Rui Wang, Wen Gao, Jiyong Ma, An Approach to Robust and Fast Locating Lip Motion international conference on multimodal interfaces. pp. 332- 339 ,(2000) , 10.1007/3-540-40063-X_44
M.E. Hennecke, K.V. Prasad, D.G. Stork, Automatic speech recognition system using acoustic and visual signals asilomar conference on signals, systems and computers. ,vol. 2, pp. 1214- 1218 ,(1995) , 10.1109/ACSSC.1995.540892
D. Chandramohan, P.L. Silsbee, A multiple deformable template approach for visual speech recognition international conference on spoken language processing. ,vol. 1, pp. 50- 53 ,(1996) , 10.1109/ICSLP.1996.607022
G. Potamianos, C. Neti, Improved ROI and within frame discriminant features for lipreading international conference on image processing. ,vol. 3, pp. 250- 253 ,(2001) , 10.1109/ICIP.2001.958098
S.L. Wang, W.H. Lau, S.H. Leung, H. Yan, A real-time automatic lipreading system international symposium on circuits and systems. ,vol. 2, pp. 101- 104 ,(2004) , 10.1109/ISCAS.2004.1329218
P. Delmas, P.Y. Coulon, V. Fristot, Automatic snakes for robust lip boundaries extraction international conference on acoustics speech and signal processing. ,vol. 6, pp. 3069- 3072 ,(1999) , 10.1109/ICASSP.1999.757489
I. Matthews, G. Potamianos, C. Neti, J. Luettin, A comparison of model and transform-based visual features for audio-visual LVCSR international conference on multimedia and expo. pp. 825- 828 ,(2001) , 10.1109/ICME.2001.1237849
J. Luettin, N.A. Thacker, S.W. Beet, Visual speech recognition using active shape models and hidden Markov models international conference on acoustics speech and signal processing. ,vol. 2, pp. 817- 820 ,(1996) , 10.1109/ICASSP.1996.543246