Trademark image consistent semantic extraction method and trademark retrieval method

Abstract

The invention provides a trademark image consistent semantic extraction method and a trademark retrieval method. The trademark retrieval method comprises the steps of firstly performing similarity calculation on trademarks for trademark image retrieval, then adopting a similar image semantic extraction method based on shape representation and matching of the trademarks, and finally providing a trademark retrieval strategy based on calculated trademark image similarity class and semantic mapping relation. The trademark image consistent semantic extraction method and the trademark retrieval method can be applied after trademark images are segmented to obtain target objects, and accordingly accurate matching is performed on object level. In addition, by means of the trademark retrieval method, a user can further retrieve similar trademarks by using the trademark images or texts, and both the precision ratio and the recall ratio of retrieval results are improved.

Description

technical field [0001] The invention relates to the technical field of image search, in particular to a method for extracting consistent semantics from trademark images and a trademark retrieval method. Background technique [0002] With the rapid development of my country's market economy, the demand for trademark images continues to increase, and the traditional retrieval methods based on classification codes and at the cost of a large number of manpower are increasingly unable to solve the contradictions of current trademark registration. Content-based trademark retrieval technology, which is currently a research hotspot and difficult point, is based on computer vision technology, and uses pattern recognition and other related computer-aided knowledge for image retrieval, which provides a good way to solve the current trademark registration problems. [0003] The traditional commonly used image retrieval method is consistent with text information retrieval, both of which ...

AI Technical Summary

Problems solved by technology

This method is generally called text-based image retrieval, and there are two main problems: first, this retrieval method needs to tag images with reasonable keywords, but the current automatic image tagging technology is not yet mature; second, users Sometimes it is difficult to use several keywords to express retrieval conditions, and it is more desirable to search for similar images by image search

[0005] However, there is a huge gap between the visual features of the image and the semantic expression of the image in the current system, making retrieval unable to meet the needs of users in terms of accuracy and efficiency

The biggest difficulty is that the low-level content features of images extracted by the system cannot correspond to the high-level semantics used by users when searching, that is to say, the image features cannot express the high-level semantics of users at all, so the retrieval results are often unsatisfactory.

Images