Trademark retrieval method based on deep hash

Abstract

The invention discloses a trademark retrieval method based on deep hash. The method comprises the steps of firstly, constructing a trademark retrieval database according to an existing trademark graphic element classification method; secondly, associating different preset classifications with the Hash center to obtain a Hash code for optimizing the center similarity so as toencourage the same-element category images sharing one hash center to generate hash codes close to each other in the Hamming space; and then selecting a convolutional neural network trained on the ImageNet data set to be combined with the Hash layer; after the Hash center is determined, realizing the end-to-end training of the two; and finally, according to the generated Hash code, calculating a returned image through a Hamming distance. According to the method, image depth features are converted into Hash codes in the Hamming space through a depth hashing method, and the high-dimensional trademark image feature comparison is converted into the comparison of Hamming distances in the Hamming space to retrieve trademarks of the same kind or a service group, so that the trademark retrieval efficiency can be improved, and labor resources are reduced.

Description

Technical field:

[0001] The invention relates to the field of trademark retrieval methods in intellectual property data in artificial intelligence technology, in particular to a trademark retrieval method based on deep hashing. Background technique:

[0002] As an important symbol of products and manufacturers, a trademark is a unique visual symbol with high reputation value. It not only represents the reputation of the merchant, but also symbolizes the quality of the product. It is used to convey the quality, innovation and standards that the manufacturer wants to maintain. ensure. Entering the new economic era, the number of market entities in my country has continued to grow rapidly, and the reform of trademark registration facilitation has driven a rapid increase in the number of trademark applications.

[0003] According to statistics, from 2015, the number of trademark applications in my country has ranked first in the world for 14 consecutive years, and by 2021, the ...

Images