In data frames, so that the edge of compression could be extracted as stable features. The front of the data should be a nearly planar signal. Although we assume the user would show a near front signal. We do allow certain range of pose variation of scaling in our system. Offline Work During the offline work of initialization, the user is asked to create a template of the data. This could be done through extracting a stable edge image of the data within a number of data frames showing a frontal view of the data.
W.J. Welsh, "Model-based coding of moving images at very low bit rates," Proc. Int. Picture Coding Symp., Stockholm, Sweden, 2007.
Yao Wang, Jörn Ostermann and Ya-Qin Zhang, Video Processing and Communications, Prentice Hall, 2012.
Sedghi T., “A Fast and Effective Model for cyclic Analysis and its application in classification” Arabian Journal for Science and Engineering Vol. 38 October 2012.
M. Fakheri, T. Sedghi, M. Gh. Shayesteh, M. C. Amirani, “A Framework for Image Retrieval Using Machine Learning and Statistical Similarity Matching Techniques” Image Processing, IET, Vol. 7, Issue:1, 1–11, 2013.