Fine edge detection method based on deep fusion correction network and fine edge detection device thereof

Abstract

The invention relates to the field of pattern recognition, computer vision and deep learning, provides a fine edge detection method based on a deep fusion correction network and a fine edge detectiondevice thereof, and aims at solving the problems that edge positioning in the image is insufficiently accurate and the detected edge is insufficiently fine. The method comprises the steps that step S1, the multi-scale features of an input image are acquired through the forward propagation part network of a convolutional neural network; step S2, the final image feature having the same resolution with that of the input image is acquired by using the method of gradually increasing the feature resolution through the reverse correction part network of the convolutional neural network; and step S3,the feature channel of the final image feature is dimensionally reduced into the single channel, and the edge detection result is generated through the fitting function. The network structure is simpler, and the acquired image feature expression further retains detail features so that the detection effect is better and the edge visualization result is finer.

Description

technical field [0001] The invention relates to the fields of pattern recognition, computer vision, and deep learning, and in particular to a fine edge detection method and device based on a deep fusion correction network. Background technique [0002] Thanks to deep convolutional neural networks, fields such as computer vision, artificial intelligence, and machine perception have developed rapidly. Edge detection, as a basic problem in computer vision, has also been greatly developed. Edge detection is to use computer to analyze the image, and then get the edge information of the object in the image. Edge detection is often used as a tool to assist other vision tasks. Traditional edge detection methods generally rely on artificially designed features, which are easily disturbed by light changes, object color changes, and noisy backgrounds. They are not robust in practical applications, and the accuracy is difficult to meet user needs. The edge detection method based on d...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem that the edge positioning in the image is not accurate enough and the detected edge is not fine enough, in one aspect of the present invention, a fine edge detection method based on a deep fusion correction network is proposed, including The following steps:

Images