A system and method for image segmentation based on spiking-som neural network clustering

Abstract

The invention discloses an image segmentation system and method based on Spiking-SOM neural network clustering. Firstly, the median filtering method is adopted to denoise the target image; Window, calculate the RGB average value of all pixels in the superpixel as the color feature of the superpixel; then select K IF neurons to construct the Spiking-SOM neural network, and construct the initial weight of the network based on the distance between the color features calculated between the superpixels Value matrix, and use the Hebbian rule to train the network. After the network training is over, clustering is performed according to the synchronization and asynchrony of neuron discharge; finally, the RGB average value of the same superpixel is calculated, and it is used to replace the original superpixel RGB value, and reset After the image matrix, the image segmentation result is obtained. The invention combines the advantages of segmentation speed and segmentation accuracy, can effectively segment color images in natural scenes, and has certain potential application value and advancement.

Description

technical field [0001] The invention belongs to the field of image segmentation, and in particular relates to an image segmentation system and method based on Spiking-SOM neural network clustering. Background technique [0002] Image segmentation is the basis of image analysis, image understanding and computer vision, and is a difficult point in image processing. More and more researchers have applied Spiking neural network to image segmentation, and achieved fruitful results. Spiking neural network has many application methods in image segmentation, but there is a defect that the segmentation speed is not ideal. Contents of the invention [0003] The object of the present invention is to provide a kind of image segmentation system and method based on Spiking-SOM neural network clustering, to overcome the defect that the above-mentioned prior art exists, the present invention combines superpixel segmentation with Spiking neural network, can analyze natural scene Effective...

AI Technical Summary

Problems solved by technology

More and more researchers have applied Spiking neural network to image segmentation, and achieved fruitful results. Spiking neural network has many application methods in image segmentation, but there is a defect that the segmentation speed is not ideal.

Images