Semantic image segmentation method and system based on edge enhancement

Abstract

The invention provides a semantic image segmentation method and system based on edge enhancement. The method comprises the steps of preprocessing an input image; establishing an edge enhancement network model, wherein the edge enhancement network model comprises a lightweight edge network and a deep semantic network; inputting the preprocessed image into a lightweight edge network, and adaptivelypaying attention to local edge information of the image by utilizing a spatial attention module; inputting the preprocessed images into a deep semantic network in batches, and optimizing the output ofthe deep network at different stages by using a channel attention module; carrying out cascading dimensionality reduction on the obtained features, fusing feature information of different levels, andadopting a channel attention module to perform optimization; performing normalizing to obtain an image segmentation result predicted by the edge enhancement network model; and calculating cross entropy loss and focus loss of the predicted segmentation image and a given standard segmentation image so as to respectively supervise output of the lightweight edge network and the deep semantic network,and updating model parameters of the edge enhancement network by using a random gradient descent method so as to realize accurate segmentation of an input image.

Description

technical field [0001] The invention belongs to the field of computer vision and image processing, and relates to an image segmentation method, in particular to a semantic image segmentation technical solution based on edge enhancement. Background technique [0002] Image semantic segmentation is a pixel-level classification task. Its essence is to assign a corresponding semantic label to each pixel in the image, and divide the image into several disjoint regions so that these features show consistency or similarities, but significant differences in different regions. Image semantic segmentation is an important preprocessing step for many computer vision tasks (such as recognition, detection, etc.), and is widely used in face recognition, fingerprint recognition, medical images, and satellite image positioning. [0003] With the rapid development of deep learning in recent years, convolutional neural network (CNN) has achieved great results in the field of image vision, and...

AI Technical Summary

Problems solved by technology

[0022] The purpose of the present invention is to propose a semantic image segmentation scheme based on edge enhancement, which solves the problem of image semantic boundary segmentation errors in the prior art, obtains the local edge features and global semantic features of the image through the edge network and the semantic network respectively, and fuses the two features at different levels to achieve precise segmentation of image boundaries and improve overall segmentation accuracy

Images