3-D OBJECT RECOGNITION SYSTEM BASED ON 2-D CHAIN CODE MATCHING

This paper presents a new high-speed three-dimensional (3-D) object re cognition system based on two-dimensional (2-D) chain code matching. A n observed 3-D object is precisely represented by a 2-D chain code seq uence from the discrete surface points of the 3-D object, so that any complex objects can be recognized precisely. Moreover, the normalizati on procedures such as translation, rotation of 3-D objects except scal e changes can be performed systematically and regularly regardless of the complexity of the shape of 3-D objects, because almost all the nor malization procedures of 3-D objects are included in the 2-D chain cod e matching procedure. As a result, the additional normalization proced ure becomes only the processing time for scale changes which can be pe rformed easily by normalizing the length of the chain code sequence. I n addition, the fast fourier transformation (FFT) is applicable to 2-D chain code matching which calculates cross correlation between an inp ut object and a reference model, so that very fast recognition is perf ormed. In fact, it is demonstrated that the total recognition time of a 3-D object is estimated at 5.35 (sec) using the 28.5-MIPS SPARC work station.