3D Object Classification and Segmentation Methods - High-Quality Visual Experience - page 346

important step in achieving high-quality visual experience in future multimedia
content quality and interactivity improvement.
Object modelling and segmentation is also very important in motion estimation
and prediction when several matched shapes can appear in one object, so the mo-
tion can be tracked for each shape separately. Depending on the number of kernel
shapes and the match precision, motion prediction can be improved as well as con-
tent quality and interactivity in visual experience of 3D motion objects.
References
1. Trucco, E., Verri, A.: Introductory Techniques for 3-D Computer Vision. Prentice
Hall, Upper Saddle River (2003)
2. Tankus, A., Yeshurun, Y.: Detection of regions of interest and camouflage breaking by
directconvexity estimation. In: IEEE Workshop on Visual Surveillance, pp. 42-48
(1998)
3. Hwang, T., Clark, J.J.: A Spatio-Temporal Generalization of Canny's Edge Detector.
In: Proc. of 10th International Conference on Pattern Recognition, pp. 314-318 (1990)
4. Bankman, I.M.: Handbook of medical imaging: Processing and analysis. Academic
Press, San Diego (2000)
5. Žagar, M., Knezović, J., Mlinarić, H.: 4D Data Compression Methods for Modelling
Virtual Medical Reality. In: Proc. of the 18th International Conference on Information
and Intelligent Systems, Varaždin, Croatia, pp. 155-161 (2007)
6. Žagar, M.: 4D Medical Data Compression Architecture. PhD Thesis, Faculty of Elec-
trical Engineering and Computing, Zagreb, Croatia (2009)
7. Sarris, N., Strintzis, M.G.: 3D Modelling and Animation: Synthesis and Analysis
Techniques for the Human Body. IRM Press, Hershey (2005)
8. Corrochano, E.B.: Handbook of Geometric Computing Applications in Pattern Recog-
nition, Computer Vision, Neuralcomputing, and Robotics. Springer, Berlin (2005)
9. Žagar, M., Kovač, M., Bosnić, I.: Lossless and Lossy Compression in 4D Bio-
modelling. In: Proc. of the First International Conference in Information and Commu-
nication Technology & Accessibility: New Trends in ICT & Accessibility, Hamma-
met, Tunis, pp. 271-277 (2007)
10. Galushkin, A.I.: Neural Networks Theory. Springer, Berlin (2007)
11. Veelenturf, L.P.J.: Analysis and Applications of Artificial Neural Networks. Prentice
Hall, Hempstead (1999)
12. Tang, H., Tan, K.C., Yi, Z.: Neural Networks: Computational Models and Applica-
tions. Springer, Berlin (2007)
13. Medseker, L.R., Jain, L.C.: Recurrent Neural Networks, Design and Applications.
CRC Press, Boca Raton (2001)