Method and system for processing image by using regional architecture

Abstract

The invention discloses a method and a system for processing an image by using a regional architecture. The method comprises the following steps of: classifying a plurality of neighboring pixels with at least one similar characteristic in an image into a cluster region with the same characteristic; giving a unique cluster label to each cluster region and describing an edge of each cluster region as a regional chain code, so that subsequent image processing programs can be only operated aiming at the neighboring pixels with the same cluster label around the processed pixel; and finally differentiating the cluster regions according to the cluster label and the regional chain code of each cluster region to synchronously operate image processing in the cluster regions.

Description

technical field [0001] The present disclosure relates to an image processing method and system using a region framework. Background technique [0002] Today's image processing technology uses many "image processing basic units", such as smooth (smooth) processing unit, de-noise (de-noise) processing unit, edge (edge) detection unit, corner (corner) detection unit, straight line (straight line) ) detection unit, and a curve (curve line) detection unit to optimize the original image or obtain effective image features. However, the calculations of these basic units are all based on the "point structure", and use "neighborhood pixels (neighborhood pixels)" to complete various image processing calculation requirements. Every time when a specific basic unit is implemented, each pixel will generate a corresponding result according to its neighboring pixels, and the operation results of each pixel are collected together, which is the processed result. [0003] figure 1 (a) and f...

AI Technical Summary

Problems solved by technology

[0010] Second: It is impossible to know the difference between the nature of a pixel and its adjacent pixels, so in actual operation, all neighboring pixels must be used

[0012] Fourth: Inability to effectively integrate and operate multiple image processing basic units in parallel

In other words, parallel processing cannot be used to reduce unnecessary operations

[0013] Fifth: The image after the calculation of the basic unit cannot provide additional information for the subsequent "image processing advanced unit" for reference

For example, the "edge detection unit" can only detect the edge pixels in the image, but it cannot know which edge pixels belong to the same area (object), so it cannot provide area information to the subsequent "image segmentation" or Advanced image processing units such as "graphic recognition" for more efficient processing

Images