Theory and application of image neighborhood parallel processing

We propose the theory of image neighborhood processing which includes algorithm, storage and processing for parallel image data. Its core idea lies in the identity and parallelism of data structures used by software algorithm, memory and processing unit. This theory solves the problem of frame data flow which is the bottleneck of high speed image processing. In this paper, we discuss the storage structure using incomplete rotate matrix and its corresponding processing unit. Based on the theory of image neighborhood processing, we have developed NIPC-3 neighborhood image parallel computer, providing parallel access to very large neighborhood image. The largest size of neighborhood core is 25 × 24 and the peak speed of neighborhood computing reaches 135 billion multiplication-accumulation operations per second. Experimental results show that NIPC-3 enables much faster implementation for low level processing and can be utilized by more complex algorithms.