EFFICIENT IMPLEMENTATION OF FACET MODELS ON A MULTIMEDIA SYSTEM

Facet models are one of the most fundamental tools in image processing . Minimization of error between the underlying gray level and the obse rved data from the image forms the basis of facet models. It can be us ed in a variety of image processing applications, e.g., edge detection , image segmentation, optical flow, etc. However, the computational re quirement to support this algorithm is extensive and increases rapidly as the order of the model increases. Our focus has been on faster com putation of facet parameters and related factors like local moments. A n approach that speeds up the execution time by reducing the redundanc ies that exist among the kernels is presented. The new algorithm impro ves the performance by a factor of 7 over direct implementation on a S UN SparcStation 10/41 for estimating six parameters of the quadratic f acet model. The performance of this algorithm was also analyzed for th e MediaStation 5000, which is a high-performance desktop multimedia sy stem. Optimized implementation on the MediaStation 5000 achieves perfo rmance improvement of 38 times over the SUN SparcStation 10/41 impleme ntation. (C) 1996 Society of Photo-Optical instrumentation Engineers.