Abstract
This chapter deals with the characterization and the recognition of human gestures in videos. We propose a global characterization of gestures that we call the Gesture Signature. The gesture signature describes the location, velocity, and orientation of the global motion of a gesture deduced from optical flows. The proposed hybrid CRF/HMM model combines the modelling ability of hidden Markov models and the discriminative ability of conditional random fields. We applied this hybrid system to the recognition of gesture in videos in the context of one-shot learning, where only one sample gesture per class is given to train the system. In this rather extreme context, the proposed framework achieves very interesting performance which suggests its application to other biometric recognition tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
The mentioned adaptation is the model adaptation to the one-shot learning context.
References
Austin, S., Schwartz, R., Placeway, P.: The forward-backward search algorithm. In IEEE ICASSP, pp. 697–700 (1991)
Baum, L.E., Petrie, T.: Statistical inference for probabilistic functions of finite state Markov chains. Ann. Math. Stat. 37, 1554–1563 (1966)
Bengio, Y., LeCun, Y., Nohl, C., Burges, C.: LeRec: a NN/HMM hybrid for on-line handwriting recognition. neural Comput. 7(6), 1289–1303 (1995)
Bhandarkar, Suchendra M., Luo, Xingzhi: Integrated detection and tracking of multiple faces using particle filtering and optical flow-based elastic matching. CVIU 113(6), 708–725 (2009)
Bradski, Gary, Kaehler, Adrian: Learning OpenCV: Computer Vision with the OpenCV Library. O’Reilly, Cambridge (2008)
Corradini, A.: Real-time gesture recognition by means of hybrid recognizers. In: Gesture Workshop, vol. 2298, pp. 34–46. Springer (2001)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: International Conference on Computer Vision & Pattern Recognition, vol. 2, pp. 886–893 (2005)
Ganapathiraju, A., Hamaker, J., Picone, J.: Hybrid SVM/HMM architectures for speech recognition. In: INTERSPEECH, ISCA, pp. 504–507 (2000)
Gilloux, M., Lemarie, B., Leroux, M.: A hybrid RBF network/hidden Markov model handwritten word recognition system. In: ICDAR, pp. 394–397 (1995)
Gunawardana, A., Mahajan, M., Acero, A., Platt, J.C.: Hidden conditional random fields for phone classification. In INTERSPEECH, ISCA, pp. 1117–1120 (2005)
Guyon, I., Athitsos, V., Jangyodsuk, B., Hamner, P., Escalante, H.: ChaLearn gesture challenge: Design and first results. In CVPR Workshops, pp. 1–6. IEEE (2012)
Hebert, D., T. Paquet, Nicolas, S.: Continuous CRF with multi-scale quantization feature functions application to structure extraction in old newspaper. In: ICDAR, pp. 493–497 (2011)
Jackson, E.: An HMM-based approach for gesture recognition using edge features. In: CVPR 2012 Workshop on Gesture Recognition (2012)
Johansen, F.T.: A comparison of hybrid HMM architectures using global discriminative training. In: ICSLP, ISCA (1996)
Knerr, S., Augustin, E.: A neural network-hidden markov model hybrid for cursive word recognition. ICPR 2, 1518–1520 (1998)
Konencny, J., Hagara, M.: One-shot learning gesture recognition using HOG/HOF features. In: ICPR 2012 Workshop on Gesture Recognition (2012)
Lafferty, J., McCallum, A., Pereira, F.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: ICML, pp. 282–289 (2001)
Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions and reversals. Soviet Physics Doklady 10, 707 (1966)
Marukatat, S., Artieres, T., Gallinari, P., Dorizzi, B.: Sentence recognition through hybrid neuro-Markovian modeling. In: ICDAR, pp. 731–737 (2001)
Matan, O., Burges, C., Lecun, Y., Denker, J.S.: Multi-digit recognition using a space displacement neural network. In: Advances in Neural Information Processing Systems, vol. 4, pp. 488–495 (1992)
Morgan, N., Bourlard, H., Renls, S., Cohen, M., Franco, H.: Hybrid neural network/hidden Markov model systems for continuous speech recognition. IJPRAI 7(4), 899–916 (1993)
Morita, M.E., Sabourin, R., Bortolozzi, F., Suen, C.Y.: Segmentation and recognition of handwritten dates: an HMM-MLP hybrid approach. IJDAR 6(4), 248–262 (2003)
Neidle, Carol, Sclaroff, Stan, Athitsos, Vassilis: SignStream: a tool for linguistic and computer vision research on visual-gestural language data. Behav. Res. Methods Instrum. Comput. 33(3), 311–320 (2001)
Niles, L.T., Silverman, H.F.: Combining hidden Markov models and neural network classifiers. In: ICASSP, pp. 417–420 (1990)
Ong, S.C.W., Ranganath, S.: Deciphering gestures with layered meanings and signer adaptation. In: IEEE International Conference on Automatic Face and Gesture Recognition, p. 559 (2004)
Quattoni, A., Wang, S., Morency, L., Collins, M., Darrell, T.: Hidden conditional random fields. IEEE Trans. Pattern Anal. Mach. Intell. 29(10), 1848–1852 (2007)
Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. In: Proceedings of the IEEE, pp. 257–286 (1989)
Rajko, S., Qian, G.: A Hybrid HMM/DPA adaptive gesture recognition method. In: ISVC, vol. 3804, pp. 227–234 (2005)
Rigoll, G.: Maximum mutual information neural networks for hybrid connectionist-HMM speech recognition systems. IEEE Trans. Speech Audio Process. 2(1), 175–184 (1994)
Sayre, Kenneth M.: Machine recognition of handwritten words: a project report. Pattern Recogn. 5(3), 213–228 (1973)
Soullard, Y.: Hybrid HMM and HCRF model for sequence classification. Bruges, Belgium (2011)
Tebelskis, J., Waibel, A., Petek, B., Schmidbauer, O.: Continuous speech recognition by linked predictive neural networks. In: NIPS, pp. 199–205 (1990)
Thomas, S., Chatelain, C., Heutte, L., Paquet, T., Kessentini, Y.: A deep HMM model for multiple keywords spotting in handwritten documents. Accepted in Pattern Anal. Appl. (2015)
Trentin, E.: A survey of hybrid ANN/HMM models for automatic speech recognition. Neurocomputing 1–4, 91–126 (2001)
Viterbi, A.: Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Trans. Inf. Theory 13(2), 260–269 (1967)
Vogler, C., Metaxas, D.: A framework for recognizing the simultaneous aspects of American Sign Language. Comput. Vis. Image Underst. 81, 358–384 (2001)
von Agris, U., Zieren, J., Canzler, U., Bauer, B., Kraiss, K.-F.: Recent developments in visual sign language recognition. Univ. Access Inf. Soc. 6(4), 323–362 (2008)
Weiss, D.: HMM based one shot gesture recognition. In: CVPR 2012 Workshop on Gesture Recognition (2012)
Wu, D., Zhu, F., Shao, L.: One shot learning gesture recognition from RGBD images. In: CVPR, IEEE, pp. 7–12 (2012)
Yang, Yang, Saleemi, I., Shah, M.: Discovering motion primitives for unsupervised grouping and one-shot learning of human actions, gestures, and expressions. IEEE Trans. Pattern Anal. Mach. Intell. 35(7), 1635–1648 (2013)
Zavaliagkos, G., Austin, S., Makhoul, J., Schwartz, R.M.: A hybrid continuous speech recognition system using segmental neural nets with hidden Markov models. IJPRAI 7(4), 949–963 (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Belgacem, S., Chatelain, C., Paquet, T. (2015). A Hybrid CRF/HMM for One-Shot Gesture Learning. In: Rattani, A., Roli, F., Granger, E. (eds) Adaptive Biometric Systems. Advances in Computer Vision and Pattern Recognition. Springer, Cham. https://doi.org/10.1007/978-3-319-24865-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-24865-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24863-9
Online ISBN: 978-3-319-24865-3
eBook Packages: Computer ScienceComputer Science (R0)