Image segmentation network and image segmentation method

Abstract

The invention discloses an image segmentation network and an image segmentation method. In the image segmentation method, a welding pool image is input into an image segmentation network for image segmentation; wherein the image segmentation network is based on a Unet structure, the image segmentation network comprises a multi-layer feature extraction structure and a multi-layer feature fusion structure, the feature extraction structure is in jump connection with the feature fusion structure through an attention module, and the attention module focuses on target features of an image and filters redundant information generated in jump connection; the feature extraction structure comprises a plurality of branches and a feature splicing module; a plurality of branches extract features from different scales according to input information, and enrich semantic information; therefore, the image segmentation network has a better image segmentation effect.

Description

technical field [0001] The invention relates to the field of image processing, in particular to an image segmentation network and an image segmentation method. Background technique [0002] As one of the key issues in computer vision, image semantic segmentation is an important research direction. During the welding process, molten metal drips onto the base metal to form a molten pool, and the contour is the most basic visual morphological feature in the shape of the melt. Using image recognition technology, the features of molten pool can be extracted, and the welding quality can be predicted according to the features of molten pool. But the weld pool image features are complex. The front edge of the weld pool contour is covered by the welding arc, and the brightness saturation area on the weld pool surface impacts the contour trailing edge, and the boundary between the weld pool edge and the periphery is not clear. The shape of the weld pool is varied, and its edges are...

AI Technical Summary

Problems solved by technology

This makes it difficult to extract the contour features of the welding pool image, and most image segmentation algorithms or image segmentation networks cannot achieve high-precision and robust image segmentation effects on the welding pool image.

Images