This thesis includes the development of an architectural framework for the proposed image to text translation system containing four components. Selection of appropriate algorithms for the first three components developed three effective multi-label classification algorithms for the fourth component, i.e. the translation component, for different problem settings
Notes
Submitted to the School of Engineering of the Faculty of Science and Technology, Deakin University
Thesis (Ph.D.)--Deakin University, Victoria, 2010
Bibliography
Includes bibliographical references (leaves 248-266)