Training method, matting method, device, medium and terminal for image processing model

Abstract

The embodiment of the application discloses a training method, a matting method, a device, a medium and a terminal of an image processing model. The training method of the image processing model includes obtaining a trichotomy of the original image; Generating a training sample set according to the original image and the trichotomy; The preset depth learning network is trained based on the training sample set to obtain an image processing model, wherein, the image processing model is used for labeling the original image to obtain a trichotomy. By adopting the technical proposal, the input original image can be automatically annotated to obtain a trichotomy, and a large amount of hairline level data annotation can be carried out without manual annotation, the annotation workload can be reduced, and the image annotation efficiency can be improved. In addition, the matting effect can be optimized by using image processing model to label the original image, avoiding the error that may be introduced by manual labeling.

Description

technical field [0001] The embodiments of the present application relate to image processing technologies, and in particular to a training method for an image processing model, a map matting method, a device, a medium, and a terminal. Background technique [0002] At present, image matting has become one of the most commonly performed operations in image processing. For example, more and more people choose to buy clothes on the Internet, so the function of searching for things by pictures of e-commerce came into being. It is very difficult to accurately search for similar clothing, so it is necessary to segment the portraits in the picture. For another example, the realization of some portrait beautification functions also depends on the precise segmentation of background and portrait. [0003] The matting scheme in the related art is mainly based on pixel clustering methods and algorithms such as "Graph Partitioning" (GraphPartitioning) algorithms. This type of method is ...

AI Technical Summary

Problems solved by technology

Such methods have poor segmentation results when the background is complex or the similarity between the background and the foreground (which can also be called a matting target) is large, such as the inability to achieve the perfection of hair, delicate clothes, branches and other exquisite items. split etc.

Images