The authors propose a neural network algorithm for adaptive pattern recognition. The algorithm consists of five steps: local feature vector forming, statistical distribution measurement, adaptive clustering, optimal criteria guidance, and a recursive mechanism. Based on the local feature vectors formed in parallel from the neighbors of the original data set in the correspondent pattern space, the statistical distribution is computed in parallel, and the adaptive pattern recognition is performed on the feature space vectors and not directly on the pattern vectors themselves. The optimal criteria guide the clustering procedure and determine the goodness of the clusters. Asymptotical results in the optimal sense could be achieved by the recursive mechanism. The algorithm is efficient and was applied to the image pattern recognition system.
展开▼
