Multichannel pulse coupling neural network based color image segmentation technology

Abstract

A multichannel pulse coupling neural network based color image segmentation technology comprises the steps of step (1), inputting images to be segmented; step (2), using color vectors of all pixels of the images as input vectors of one input neuron and eight adjacent pixel color vectors as radial basis function (RBF) characteristic vectors, and determining initial seed points through seed selection conditions; step (3), growing the seed region through growing rules, classifying the pixel points in accordance with the growing rules in the seed region, and connecting the neurons and grouping and numbering the neurons; step (4), calculating the average characteristic vector of all connection regions, and replacing the characteristic vectors included in all neurons of the region with the obtained characteristic vector; step (5), connecting the qualified unconnected neurons with the proximate groups through a rapid connection rule; step (6),updating the preset threshold to be theta i = theta i1 +delta theta i, and repeating the step (5); step (7), performing rule merging on accordant regions in the images and merging proximate region blocks on space; repeating the step (7) till the region merging stopping conditions are met to complete color image segmentation.

Description

technical field [0001] The invention relates to a color image segmentation technology used in the field of digital image processing, in particular to a parallel computing technology for color image segmentation based on a multi-channel pulse-coupled neural network. Background technique [0002] Image segmentation is the technique of segmenting the foreground and background of the image. Using image segmentation can often further extract the foreground object or region of interest from the image. After decades of development, image segmentation techniques are divided into four categories: threshold methods, edge-based methods, region-based methods, and hybrid methods. Among numerous image segmentation methods, Pulse Coupled Neural Network (PCNN) is a biologically inspired method. In the early 1990s, the German scientist Professor and his collaborators discovered when studying the animal visual neural model that if a certain range of central nervous perception areas perceive ...

AI Technical Summary

Problems solved by technology

[0003] The traditional PCNN model is limited to grayscale image processing, and its limitations mainly include two points: first, the essence of interneuron coupling is limited to the scalar calculation of pixel grayscale values, making PCNN unsuitable for solving color image problems, which is Because the color must be represented by a vector (such as the combination of the three primary colors of red, green and blue); second, the algorithm complexity is too large

Images