Appearance design patent retrieving method based on dynamic texton

Abstract

The present invention relates to an appearance design patent retrieving method based on a dynamic texton. The method comprises the following steps: step 1) extracting a texton; and step 2) extracting an LBP feature based on statistical analysis from the texton, and performing normalization and similarity measurement on an extracted feature vector, and returning a retrieval result. According to the method provided by the present invention, on the basis of an appearance design patent and targeted at the characteristic that different image textons may have unequal sizes, an image retrieving algorithm of dynamcially extracting a texton according to image content and extracting a feature from the texton is provided. When retrieving images with a repeated texton, the retrieval effect of the method provided by the present invention is superior to the existing retrieving method based on a whole image, and images with the same texton but different arrangement structures can be searched out; and the method can be used for image texture structure similarity determination, has excellent retrieval effects and can well meet the requirements of actual application.

Description

technical field [0001] The invention belongs to the technical field of design patent retrieval, in particular to a design patent retrieval method based on dynamic texture primitives. Background technique [0002] With the development of international forms and the acceleration of trade integration, design patents occupy an increasingly important position in industrial property rights, and the number of design patent applications is growing rapidly. Design patents use images as the object of protection, and mainly protect the foreground objects in the patent image. As far as design patents are concerned, the patent examiners will compare the shape, pattern, and color of the submitted appearance patent image with the applied patent images in the database to determine whether they have a certain similarity. According to the similarity judgment standard of design patent images, two appearance patent images that contain the same texture primitives but present different pattern c...

AI Technical Summary

Problems solved by technology

Since different types of images contain different contents, the size of the texture primitive is also different, so setting the texture primitive to a fixed size cannot correctly reflect the real texture structure information of the image

The retrieval method based on the spatial distribution characteristics of texture primitives introduces the spatial distribution information into the texture feature descriptor, which improves the retrieval efficiency of images, but for images with the same texture but different spatial distributions, this retrieval method cannot achieve good retrieval results

[0004] Although the existing texture primitive-based retrieval methods propose the concept of texture primitives, they cannot effectively extract texture primitives in images.

Images