Trademark density based personalized trademark matching recognition method

Abstract

A trademark density based personalized trademark matching recognition method includes: establishing a trademark image sample library, extracting SIFT (scale invariant feature transform) features, calculating the trademark density, and setting personalized matching strategies according to the trademark density; extracting the SIFT features and GSC (generalized shape contexts) features for trademark images in the sample library and establishing an SIFT word bag model and a GSC word bag model; extracting the SIFT features and the GSC features for a to-be-recognized image area, and respectively calculating similarity lists of remarks in the SIFT word bag model and the GSC word bag model; combining the two similarity lists of the trademarks according to the personalized matching strategies to acquire the all the similarity lists of the trademarks of the area, and taking the trademarks with the largest similarity and meeting the similarity thresholds as the recognition result of the area. The trademarks are recognized rapidly and accurately, and good effect of detection under the influence of scale variation, focus change, illumination, shielding, background interference and the like on the trademark can be achieved.

Description

technical field [0001] The invention relates to the technical field of target detection and recognition, in particular to a personalized trademark matching and recognition method based on trademark density, which can be used for fast trademark recognition and trademark retrieval. Background technique [0002] Specific object recognition is one of the challenging tasks in computer vision. At the same time, with the explosive growth of object types, there is an increasing demand for real-time object recognition under large-scale categories, especially in mobile applications and recommendation systems. specific area identification. Trademarks can be seen as flat surface objects and they have great value in modern marketing, advertising and trademark registration. In particular, the trademark library can reach tens of thousands of categories, which is rarely seen in the field of ordinary target detection and recognition. Our main goal is to identify the trademarks (such as fi...

AI Technical Summary

Problems solved by technology

For methods based on shape features, when the shape of the trademark consists of many trivial small areas, such as figure 1 In Starbucks and Unilever, these features cannot obtain accurate shape features

Therefore, these boundary-based descriptors are not suitable when the trademark is complex and boundary information is difficult to obtain

For systems using local features, when the logo consists of some smooth regions or the logo is very simple, such as figure 1 In Baidu and Texaco, local features cannot obtain enough key points

Therefore, for simple trademarks, local features will lead to lower recall and precision

Images