An automatic labeling method for natural scene images

Abstract

The invention discloses an automatic marking method for a natural scene image, and belongs to the field of computer vision. The method comprises the following steps that image features are extracted; an original image is segmented by adopting an unsupervised algorithm so that a super-pixel graph is generated; modeling of a pixel marking model is performed through CRF and significant prior information is embedded in the model; and the model is solved and pixel marking is realized. The CRF is adopted to act as a basic model, the significant detection prior information is introduced in the CRF model, and separation of a foreground target and a background can be realized through significant detection and a universal connection association relation between the super-pixels is constructed in a foreground target area. The significant detection prior information is introduced so that the classification precision of the foreground target in the image can be effectively enhanced. Meanwhile, the problem of classification "crosstalk" of the foreground and the background can be effectively solved by the separation of the foreground area and the background area. Therefore, the overall classification precision of pixel marking can be effectively enhanced by the method, and the method has substantial effect for the scenes of relatively complex foreground target profiles and subareas of highly different colors and textures.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to an automatic labeling method for natural scene images. Background technique [0002] In recent years, image understanding in computer vision has developed rapidly and has been widely used in many fields, and has attracted extensive attention from scholars. Existing scene image annotation algorithms often use the undirected graph model conditional random field CRF (Conditional Random Field) as the basic framework, and achieve pixel label. Although the introduction of existing contextual prior information has enhanced the model description ability to a certain extent, there are still deficiencies, and it is difficult to effectively improve the classification accuracy, especially the classification accuracy of foreground objects. After research, it is found that the main reasons why the existing image understanding algorithms are difficult to effectively improve the accuracy of pixe...

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problem of low classification accuracy of complex foreground objects in image labeling, the present invention proposes an automatic labeling method for natural scene images, which can effectively solve the problem of crosstalk between foreground objects and background classification Inconsistent classification between sub-regions caused by large differences in color and texture features

Images