Method and system for automatically extracting image foreground

Abstract

The invention provides a method and a system for automatically extracting image foreground. The method includes conducting gray level processing on colored foreground images to be extracted, conducting filtering on the images subjected to the gray level processing, detecting remarkable foreground area of the filtered images, determining foreground range and conducting final foreground extraction according to the grabcut algorithm.

Description

technical field [0001] The present invention generally relates to the field of digital image processing in computer vision, in particular to a method and system for automatically extracting image foreground. Background technique [0002] Today, with the rapid development of science and technology and the Internet industry, the previous human processing can no longer meet the needs of people's material life today, and more computer processing methods are more quickly and widely integrated into modern people's lives. [0003] With the acceleration of the pace of life, the field of artificial intelligence is gradually being valued by people to replace the previous human processing and simple computer calculations. It is an inevitable trend of development to completely rely on computers to perform various tasks independently. most deeply felt. [0004] In daily life, people cannot do without shopping. The emergence and development of e-commerce has become a historical necessity...

AI Technical Summary

Problems solved by technology

[0004] In daily life, people cannot do without shopping. The emergence and development of e-commerce has become a historical necessity. Different from traditional shopping, e-commerce uses Internet technology to put goods on the Internet, through various terminals or even mobile phone clients. Complete shopping needs, but with the accelerated pace of life, the usual text search can no longer meet people's needs, a new shopping method - photo shopping emerges in due course

[0005] Shopping by taking pictures mainly relies on image processing methods, comparing the product images taken by users with the images in the product gallery to find the most similar products, but because the images taken by users are random The gallery is completely consistent, and the complex commodity background environment has had a great impact on this new shopping experience. The separation of commodities and background images has become the key to the technology, while the traditional background separation method is based on manual intervention, that is, it needs to be manually corrected. Framing and setting of the segmented area, or achieved through machine learning or other empirical manual intervention, does not achieve true artificial intelligence

Images