A Symbolic/Neural Hybrid Approach to Emergent Subshape Recognition
Chu Mon · Proceedings of the International Conference on Computer-Aided Architectural Design Research in Asia · 1996
Recognizing emergent subshape is one kind of human visual behaviour. People usually recognize several distinct emergent subshapes from primary shapes and give them different interpretations. This paper presents a symbolic/connectionist hybrid system to provide computers the ability of this kind. Through this approach, the recognition system is divided into three modules. Source images are sent to the first module, that is a connectionist network, of the hybrid system. The network is responsible for transforming the source image into abstract visual data, named Pre-attention Distribution and Local Feature Information. Then, the abstract visual data are processed in the second module that is a symbolic subsystem. The subsystem is responsible for making decision in the Visual Search Attention processes and for managing the features of the whole shape. Finally, another connectionist network takes the previous results from the symbolic subsystem and performs the final recognition.