Abstract—This paper describes on a real time tracking by using images captured from a closed circuit television (CCTV) before being transmitted to a recognition system for identification of the object’s contour shape and gesture. The purposes of this research are to develop a contour shapes and gesture recognition model that can be implemented in an intelligent CCTV target recognition system to discover the possible crime events immediately at the critical areas, while reducing the human power. The crime events that had been focused on were robberies and stealing that commonly happen in shopping malls and ATM machines. Therefore, the contour shape of dangerous weapon and suspected person’s gesture had been included in this study. The recognition system was designed using the Image Processing and Neural Network tools of Matrix Laboratory (MATLAB) programming language. The analysis of Sum Square Error and correlation coefficient of the designed network in this study had showed that the recognition system was performing well in recognizing the contour shapes and gesture.
Index Terms—Contour shape, neural network, multi layer perceptron, sum square error (SSE).
Lee Chin Kho is with Department of Information Science, Japan Advanced Institute of Science and Technology, Nomi, Ishikawa, 923-12 Japan (e-mail: email@example.com).
Sze Song Ngu and Liang Yew Ng are with the Electronic Engineering Department, Faculty of Engineering, Universiti Malaysia Sarawak, 94300 Kota Samarahan, Malaysia (e-mail: firstname.lastname@example.org, email@example.com).
Annie Joseph is with Kobe University, 657-8501 Kobe Shi, Nada-Ku, Rokko dai cho, 1-1, Japan (e-mail: firstname.lastname@example.org)
Cite: Lee Chin Kho, Sze Song Ngu, Annie Joseph, and Liang Yew Ng, "Contour Shapes and Gesture Recognition by Neural Network," International Journal of Computer Theory and Engineering vol. 4, no. 4, pp. 662-666, 2012.