Feature vector or time-series – comparison of gestures representations in automatic gesture recognition systems

• Autorzy: Barczewska K. , Wójtowicz W. , Moszkowski T.
• Języki publikacji: EN

Abstrakty

EN

In this paper, we performed recognition of isolated sign language gestures - obtained from Australian Sign Language Database (AUSLAN) – using statistics to reduce dimensionality and neural networks to recognize patterns. We designated a set of 70 signal features to represent each gesture as a feature vector instead of a time series, used principal component analysis (PCA) and independent component analysis (ICA) to reduce dimensionality and indicate the features most relevant for gesture detection. To classify the vectors a feedforward neural network was used. The resulting accuracy of detection ranged between 61 to 87%.

Słowa kluczowe

EN

principal component analysis (PCA); independent component analysis; ICA; neural networks; sign language; automatic recognition

PL

analiza składowych głównych (PCA); analiza składowych niezależnych (ICA); sieci neuronowe; język migowy; rozpoznawanie automatyczne

• Wydawca: Foundation for Young Scientists
• Czasopismo: Challenges of Modern Technology
• Rocznik: 2015
• Tom: Vol. 6, no. 1
• Strony: 1--5
• Opis fizyczny: Bibliogr. 22 poz., rys., wykr., tab.

Twórcy

autor

Barczewska K.

• AGH University of Science and Technology, Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, Department of Automatics and Biomedical Engineering, al. Mickiewicza 30, 30-059 Krakow, Poland

autor

Wójtowicz W.

• Cracow University of Technology, al. Jana Pawła II 37, 31-864 Cracow, Poland

autor

Moszkowski T.

• AGH University of Science and Technology, Faculty of Electrical Engineering, Automatics, Computer Science and Biomedical Engineering, Department of Automatics and Biomedical Engineering, al. Mickiewicza 30, 30-059 Krakow, Poland

Bibliografia

• [1] Liang R.H., Ouhyoung M., Wolthusen S.D., Real-time Continuous Gesture Recognition System for Sign Language, Proc. 1998 Third IEEE International Conference on Automatic Face and Gesture Recognition, pp. 558-567, April 1998.
• [2] Gweth Y.L., Plahl C., Ney H., Enhanced Continuous Sign Language Recognition using PCA and Neural Network Fea tures, Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference on. Providence, pp. 55-60, June 2012.
• [3] Liwicki S., Everingham M., Automatic Recognition of Fingerspelled Words in British Sign Language. Proc. 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, pp. 50-57, June 2009.
• [4] Lichtenauer J.F., Hendriks E.A., Reinders M.J.T., Sign Language Recognition by Combining Statistical DTW and Independent Classification, IEEE Transactions on Pattern Analysis and Machine Inteligence, 30(11) , pp. 2040-2046, 2008.
• [5] KinecTranslator, [web page] http://www.kinectranslator.com/pl/technologia/. [Accessed on 31 Jul.2013.].
• [6] Barczewska K., Drozd A., Folwarczny Ł, Rozpoznawanie gestów z wykorzystaniem czujników inercyjnych o 9 stopniach swobody, Pomiary, Automatyka, Kontrola, 59(3), pp. 235-238, 2013.
• [7] Theodorakis S., Pitsikalis V., Rodomagoulakis I., Maragos P., Recognition with raw canonical phonetic movement and handshape subunits on videos of contiunuous sign language, Proc. 2012 IEEE International Conference on Image Processing (ICIP), pp. 1413-1416, 2012.
• [8] Kapusciński T., Rozpoznawanie polskiego języka migowego w systemie wizyjnym, PhD dissertation. Uniwersytet Zielonogórski, Wydział Elektrotechniki, Informatyki i Telekominukacji , Zielona Góra 2006.
• [9] Oszust M., Zastosowanie grupowania szeregów czasowych do rozpoznawania wypowiedzi w języku migowym na podstawie sekwencji wizyjnych, PhD dissertation. AGH WIET, Kraków 2013.
• [10] Nguyen T.D., Ranganath S., Facial expressions in American sign language: Tracking and recognition, Pattern Recognition, 45(5), pp. 1877-1891, 2012.
• [11] von Agris U., Knorr M., Kraiss K.F., The significance of facial features for automatic sign language recognition, IEEE International Conference on Automatic Face & Gesture Recognition, pp. 1-6, Sept. 2008.
• [12] Kadous M.W., Temporal Classification: Extending the Classification Paradigm to Multivariate Time Series, Doctoral Dissertation, School of Computer Science and Engineering, University of New South Wales, 2002 .
• [13] Trmal J., Hruz M., Zelinka J., Campr P., Muller L., Feature Space Transforms for Czech Sign-Language Recognition, Proceedings of the Interspeech 2008, Bris- bain, Australia, pp. 2036-2039, 2008.
• [14] Chai X., Li G., Lin Y., Xu Z., Tang Y., Chen X., Sign Language Recognition and Translation with Kinect, [web page] http://vipl.ict.ac.cn/sites/default/files/papers [Accessed on 30 Nov . 2013].
• [15] Barczewska K, Automatic Recognition of Isolated Sign Language Signs Based on Gesture Components and DTW Algorithm, Challenges of Modern Technology 5(3), 2014.
• [16] AUSLAN data set, [web page] http://archive.ics.uci.edu/ml/machine-learning-databases/auslan2-mld/auslan.data.html [Accessed on 31 Sep. 2013.].
• [17] Hyvarinen A., Fast and robust fixed-point algorithms for independent component analysis, IEEE Trans. Neural Networks, 10(3), pp. 626-634, 2011.
• [18] FastICA algorithm, [web page] http://research.ics.aalto.fi/ica/fastica/ [Accessed on 31 Aug. 2013].
• [19] Ng A., Machine Learning materials from on-line course [web page] https://www.coursera.org/ [Accessed on 30 Jun. 2013].
• [20] Baek K., Draper B.A., Beveridge J.R., She K., PCA vs ICA: A comparison on the FERET data set, Proc. of the 4th International Conference on Computer Vision, ICCV ‘02, 2002.
• [21] Hyvarinen A., Oja E., Independent component analysis: Algorithms and Applications, Neural Networks, 13(4-5), pp. 411-430, 2013.
• [22] Hyvarinen A., Independent component analysis: recent advances, Phil. Trans. R. Soc„ 371( 1984), 2013.