Unlock instant, AI-driven research and patent intelligence for your innovation.

An Image Retrieval Method Based on Hybrid Microstructure Descriptor

An image retrieval and microstructure technology, applied in image analysis, image data processing, special data processing applications, etc., can solve the problem of insufficient feature description ability, and achieve the effect of image retrieval performance improvement and strong resolution ability

Active Publication Date: 2016-12-28
BEIJING YINGPU TECH CO LTD
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to avoid the shortcomings of the prior art, the present invention proposes an image retrieval method based on hybrid microstructure descriptors, which overcomes the shortcomings of insufficient feature description capabilities in existing image retrieval methods, and improves the accuracy of image retrieval

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • An Image Retrieval Method Based on Hybrid Microstructure Descriptor
  • An Image Retrieval Method Based on Hybrid Microstructure Descriptor
  • An Image Retrieval Method Based on Hybrid Microstructure Descriptor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Now in conjunction with embodiment, accompanying drawing, the present invention will be further described:

[0039] 1. For all the images in the image library, use HMSD to describe the features of the image content, and generate the image feature library corresponding to the image library offline;

[0040] 2. Use the hybrid microstructure descriptor to extract the content features of the retrieved image;

[0041] 3. Use the retrieved image features and the feature vectors in the image feature library to use L 1 The distance is used to measure the similarity one by one. And sort according to the distance from small to large, and get the top N results with the smallest distance;

[0042] 4. Sort according to the distance from small to large, and get the top N results with the smallest distance. Return the images corresponding to these N results.

[0043] In the present invention, the hybrid microstructure descriptor extraction process is as follows:

[0044] (1) Conver...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to an image retrieval method based on a hybrid microstructure descriptor. First, a hybrid microstructure descriptor (Hybrid MSD, HMSD) is used to generate an image feature library corresponding to an image library, and then the HMSD is used to extract the content features of the retrieved image, and then the The similarity measurement criterion is used for measurement, and finally the similarity measurement results are sorted, and corresponding images are presented to the user. Since the hybrid microstructure descriptor in the present invention contains microstructures of direction and color under two commonly used color space models, it has a strong ability to distinguish colors, textures, shape features and color distribution information, and to a certain extent Reflects the properties of the human visual system. Therefore, the image retrieval performance of the image retrieval method based on the hybrid microstructure descriptor has been greatly improved.

Description

technical field [0001] The invention relates to an image retrieval method based on mixed microstructure descriptors. Background technique [0002] The basic idea of ​​content-based image retrieval (Content Based Image Retrieval, CBIR) is to establish feature vectors according to the visual perception content and semantic content contained in the retrieved images, and then perform matching retrieval according to the similarity of feature vectors. The commonly used visual content features in CBIR mainly include image color, shape and texture. Color, shape, and texture describe image content from different angles. In order to improve retrieval performance, image content needs to be described more reasonably, so combining different types of features is an effective way to improve retrieval performance. The document "Image retrieval based on micro-structure descriptor, Pattern Recognition, 2011, 44(9): 2123-2133." discloses a micro-structure descriptor (Micro-Structure Descript...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F17/30G06T7/00
Inventor 李映孙文超焦文健
Owner BEIJING YINGPU TECH CO LTD