An artificial model for understanding from images inspired by human perceptive and cognitive system

Artificial Intelligence (AI) is an exciting and fascinating research area in computer science emerging to develop machines with human intelligence or human behaviour. One of the goals in AI is to develop algorithms and techniques based on the study of pinnacle of intelligence, human brain. The new direction makes a breakthrough in AI while facilitating powerful clues to the neuroscience to understand the unrevealed mechanisms in human brain. The traditional means of manipulating visual inputs by artificial systems are highly dependent on human intervention. A study of human vision system can be considered as a promising direction towards achieving truly intelligent artificial vision system. In this thesis, the main contribution is to investigate the human visual system from biological and psychological perspective and propose a new model for artificial perception. The new model, Artificial Model for Visual Perception (AMVP), accumulates knowledge from the environment in different aspects and abstraction levels and generate interpretations similar way to the humans using past experiences. The AMVP model is domain independent and has the flexibility to tailor for any situation. The subsequent aim of the thesis is to propose implementation architecture for the conceptual framework. Our implementation was based on the structure adaptive neural network. The conceptual model is applied in a real-life image data set and the functionalities of the proposed model are demonstrated. The difficulties faced during the feature extraction from the images for implementation of the conceptual model encouraged us to perform an analysis of differences between the visual inputs received by humans and artificial systems. This study continues to investigate the differences between subsequent stages of the human visual pathway with the methods used by artificial systems. This thesis also propose a possible representation for an artificial percept.