Tài liệu hạn chế xem trước, để xem đầy đủ mời bạn chọn Tải xuống
1
/ 341 trang
THÔNG TIN TÀI LIỆU
Thông tin cơ bản
Định dạng
Số trang
341
Dung lượng
11,59 MB
Nội dung
[...]... Gesture Recognition System for Hand Motion Trajectory In: International Conference on PatternRecognition (ICPR), pp 519–522 (2008) 11 Yoon, H., Soh, J., Bae, Y.J., Yang, H.S.: Hand Gesture Recognition Using Combined Features of Location, Angle and Velocity Journal of PatternRecognition 34, 1491–1501 (2001) 12 Lawrence, R.R.: A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. .. http://www.ti3.tu-harburg.de/rump/intlab/ Hand Gesture Spotting Based on 3D Dynamic Features Using Hidden Markov Models Mahmoud Elmezain, Ayoub Al-Hamadi, and Bernd Michaelis Institute for Electronics, Signal Processingand Communications Otto-von-Guericke-University Magdeburg, Germany {Mahmoud.Elmezain,Ayoub.Al-Hamadi}@ovgu.de Abstract In this paper, we propose an automatic system that handles hand gesture spotting and recognition. .. watermarked image and (d) extracted watermark Fig 3 Extracted watermarks from (a) the watermarked JPEG image with the file size ratio 34%, the watermarked JPEG2000 images with the file size ratio (b) 10.6% and (c) 9.7% image without any attack Figs.2∼3 illustrate the watermarks extracted from the attacked watermarked images under attacks such as marking, clipping, JPEG and JPEG2000 compressions The extracted images... Work This paper proposes an automatic hand gesture spotting system for numbers from 0 to 9 in stereo color image sequences using Hidden Markov Models Our system performs the hand gesture segmentation andrecognition tasks simultaneously Furthermore, it is suitable for real-time applications and solves the issues of time delay between the segmentation and the recognition tasks The database contains... Approach for Hand Gesture Recognition in Virtual Reality Driving Training System of SPG In: ICPR, pp 519–522 (2006) 4 Kim, D., Song, J., Kim, D.: Simultaneous Gesture Segmentation andRecognition Based on Forward Spotting Accumlative HMMs Journal of PatternRecognition Society 40, 3012–3026 (2007) 5 Elmezain, M., Al-Hamadi, A., Michaelis, B.: Real-Time Capable System for Hand Gesture Recognition Using... preprocessing, and Mean-shift algorithm in conjunction with Kalman filter is to track the hand to generate the hand motion trajectory For more details, the reader can refer to [5], [14] The input images were captured by Bumblebee stereo camera system that has 6 mm focal length at 15FPS with 240 × 320 pixels image resolution, Matlab implementation Our experiments is carried out an isolated gesture recognition. .. Algorithms for a HMM Gesture Recognition System In: International Workshop in Frontiers of Handwriting Recognition, pp 100–106 (2004) 14 Elmezain, M., Al-Hamadi, A., Michaelis, B.: A Novel System for Automatic Hand Gesture Spotting andRecognition in Stereo Color Image Sequences Journal of WSCG 17(1), 89–96 (2009) 15 Cover, T.M., Thomas, J.A.: Entropy, Relative Entropy and Mutual Information Elements... pixel Fig.1 (c) shows the watermarked image with PSNR=33.5774 obtained by the proposed blind method and the watermark extracted from the watermarked A Blind Image Wavelet-Based Watermarking Using Interval Arithmetic 7 Fig 1 (a) Original image, (b) watermark, (c) watermarked image with PSNR=33.5774 and (d) extracted watermark without any attack Fig 2 (a) Watermarked image with marked areas, (b) extracted... the start point of the gesture and then the segmented gesture is sent to the recognizer for recognition So, there is an inevitable time delay between the meaningful gesture spotting andrecognition This time delay is not suitable for on-line applications The main contribution of this paper is to propose a gesture spotting system that executes hand gesture segmentation andrecognition simultaneously using... experiments showed that the optimal number of clusters K is equal to 33 12 4 M Elmezain, A Al-Hamadi, and B Michaelis Gesture Spotting andRecognition System To spot meaningful gestures, we mention how to model gesture patterns discriminately and how to model non-gesture patterns effectively (Fig 2) Each reference pattern for numbers (0-9) is modeled by LRB model with varying number of states ranging from 3 . (SecTech), Signal Processing, Image Processing and Pattern Recognition (SIP), and u- and e-Service, Science and Technology (UNESST). We acknowledge the great effort of all the Chairs and the members. Communications in Computer and Information Science 61 Dominik ´ Sle˛zak Sankar K. Pal Byeong-Ho Kang Junzhong Gu Hideo Kuroda Tai-hoon Kim (Eds.) Signal Processing, Image Processing, and Pattern Recognition International. Jeju, Jeju Island, South Korea. SIP 2009 focused on various aspects of advances in signal processing, image proc- essing and pattern recognition with computational sciences, mathematics and informa- tion