Learning to recognize visual concepts: development and implementation of a method for texture concept acquisition through learning
Jerzy W. Bala · 1993
The goal of this research is to explore the application of symbolic learning methods to problems of computer vision. The research presented in this thesis has been concerned primarily with the development of methods for inductive learning of texture descriptions. Texture description learning is done in the following phases: (i) data preprocessing and attribute extraction, (ii) acquisition of texture concept descriptions, (iii) optimization of acquired descriptions, and (iv) recognition of unknown texture samples. The methodology adapted to the acquisition and recognition of complex vision data is based on an extension of AQ (Michalski, 1986), a learning from-examples algorithm. This approach for inductive learning of texture descriptions was originally proposed by Michalski (1973) and was initially applied using ILLIAC III image recognition computer facilities. This research presents a novel extension to the initial approach, which is called Multilevel Logical Templates. The novelty lies in multilevel symbolic image transformations, new advanced concept description optimization methods for noise-tolerant learning, and a multistrategy approach to learning from vision data. An important contribution of the research is the experimental demonstration that symbolic inductive learning methods can be successfully applied to the domain of continuous attributes of low level vision in which non symbolic methods have been traditionally employed.