A Dynamic Region Generation Algorithm for Image Segmentation Based on Spiking Neural Network

We propose a dynamic region generation algorithm for image segmentation based on spiking neural network inspired by human visual cortex that shows the tremendous capacity of processing image. The network structure generated by the proposed algorithm is automatically and dynamically. An image can be decomposed into several different shape and size of regions that look like superpixels. Merging these regions based on the color space similarity can extract contour. Dynamic network architecture brings stronger computing power. Dynamic generation method leads to more flexible network. Experimental results on BCDS300 dataset confirm that our approach achieves satisfactory segmentation results for different images compared with SLIC.