Learning objectives
The purpose of the course is transfer to the students the knowledge needed to design and implement artificial vision systems, and an expertise useful for their future job. During the course the foundamentals and methodologies will be presented, and advanced topics will be discussed also through specific seminars. Laboratory activities will also be performed. Students need to be able to develop software, mainly in a Unix environment.
Prerequisites
All the courses which foster knowledge on the architecture and programming of processing systems.
Course unit content
- Visual perception and artificial vision<br />- Image acquisition, image models, calibration<br />- Low level image processing<br />- Pattern Recognition techniques<br />- Segmentation techniques<br />- Knowledge based vision<br />- 3D reconstruction<br
Bibliography
* M. Sonka, V. Hlavac, R. Boyle, Image Processing analysis and machine vision, Chapman and Hall, 1993.<br /> * V. Cantoni, S. Levialdi, La Visione delle Macchine, Tecniche Nuove, 1989<br /> * P. Zampironi, Metodi dell'Elaborazione Digitale di Immagini, Masson, 1990<br /> * R.C. Gonzalez, P. Wintz, Digital Image Processing, 2nd ed., Addison-Wesley, 1987<br /> * R. M. Haralick, L. G. Shapiro, Computer and Robot Vision, Vol I e II, Addison-Wesley, 1992 <br /> * R. O. Duda, P. E. Hart, D. G. Stork, Pattern Classification, 2nd ed., Wiley and Son, 2001<br /> * R. Jain, R. Kasturi, B. G. Schunck, Machine Vision, McGraw-Hill, 1995<br /> * S. E. Umbaugh, Computer Vision and Image Processing, Prentice Hall, 1998<br /> * E. Trucco, A. Verri, Introductory Techniques for 3-D Computer Vision, Prentice Hall, 1998<br /> <br /> Teacher’s slides ()
Teaching methods
Written test, evaluation of the project with oral exam. The main topics of the course will benefit from laboratory activities and demonstations. Each student will have to develop a project which will be evaluated for the final examination.
