Learning of Shape Classes

Please enable javascript in your browser.

Sheikhi, Samira | 2010

555 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 40532 (02)
University: Sharif University of Technology
Department: Mathematical Sciences
Advisor(s): Razvan, Mohammad Reza; Mirshams Shahshahani, Mehrdad
Abstract:
Learning of shape classes from a set of given data is of special practical importance in computer vision. Large variations in the surrounding objects makes the problem of shape learning a very di°cult one. These di°culties may vary according to diferences in pose and part articulations of shapes. Despite all of the problems, large applications of this problem in areas such as tracking, object recognition and text recognition inspires many groups to work on it. In this thesis we aim to investigate a solution for this problem
Keywords:
Shapes Learning ; Unsupervised Learning ; Structural Learning ; Shape Skeleton ; Skeleton Graph