GEOMETRICAL SHAPE-RECOGNITION USING A CELLULAR-AUTOMATON ARCHITECTUREAND ITS VLSI IMPLEMENTATION

This paper presents a new, fast geometrical shape recognition techniqu e based on the properties of cellular automata (CA). The VLSI implemen tation of the architecture developed for this purpose is also presente d. The digitized binary image of the geometrical shape is loaded onto a 2D CA grid. This binary image is the initial global state of the CA. The CA evolves in time until a final stable global state is reached. The geometrical shapes are classified into four different categories, according to the symmetries of their final stable global state, and ar e then recognized, Eleven geometrical shapes have been recognised usin g the proposed technique, The die size dimensions of the chip for a 8 x 8 pixel image are 2.56 mm x 2.70 mm = 6.91 mm(2), and its maximum fr equency of operation is 35 MHz. Targeted applications include classifi cation and inspection tasks in industry. (C) 1997 Academic Press Limit ed.