A parallel computation approach to two-dimensional shaperecognition is proposed and illustrated. The approach uses paralleltechniques for contour extraction, parallel computation of normalizedcontour-based feature strings independent of scale and orientation, andparallel string-matching algorithms. The string matching can be appliedin a manner independent of rotation. An implementation on the exclusiveread, exclusive write parallel random access memory (EREW PRAM)architecture is discussed, but it can be adapted to other parallelarchitectures. An illustrated example is presented
展开▼