Modeling an Environment: Agents in Character Feature Extraction

A feature extraction system based on artificial life concepts is presented. The system provides automatic character feature extraction through the local actions of autonomous feature agents. A feature agent is a simple artificial creature who has a face, a body and two mouths, and can eat, move, grow and bear children in its environment. Feature agents are situated in a character image environment, sense the environmental conditions and produce their bodies in this environment. The local action of such agents results in building a topological structure of the food environment (character strokes) which is essential to character recognition. The global result of feature extraction emerges from feature agents’ local activities. We have applied this feature extraction system to our research in digit recognition. The results are promising both from theoretical and practical points of view. The results demonstrate that the difficult problem of character feature extraction can be attacked ...

• Type: Conference
• Year: 1997
• Where: AGENTS
• Authors: Lijia Zhou, Stan Franklin
• Keywords: AGENTS 1997, Character Feature Extraction, Feature Agents, Feature Extraction, Security Privacy