Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Similarity image retrieval method and system based on sparse coding

An image retrieval and sparse coding technology, applied in the field of image recognition, can solve the problems of relying on training samples, feature extraction methods are not very effective, and there is no targeted measurement standard, so as to achieve the effect of improving learning efficiency

Pending Publication Date: 2020-11-10
SHANDONG INST OF BUSINESS & TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] 1. The feature extraction method is not very effective and highly dependent on training samples;
[0005] 2. There is no targeted measurement standard in the process of similarity calculation

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
  • Similarity image retrieval method and system based on sparse coding
  • Similarity image retrieval method and system based on sparse coding
  • Similarity image retrieval method and system based on sparse coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0029] see figure 1 , figure 1 A schematic diagram of the steps of a similarity image retrieval method based on sparse coding provided by an embodiment of the present invention, which includes the following steps:

[0030] Step S100, performing basis vector characterization according to the reference image to obtain a first sparse characterization result;

[0031] Specifically, the reference image is the selected image to be retrieved, and the base vector is the most basic component in the vector space, because the base vector must be linearly independent, and this part can represent each vector in the vector space, reducing the dimension of the image, Obtain the first sparse representation result.

[0032] In some implementation manners, the electronic device shoots in various scenes, such as night scenes or backlit environments. In the same shooting scene, the electronic device can capture multiple frames of images, and perform image registration on the multiple frames of...

Embodiment 2

[0047] see figure 2 , figure 2 A schematic diagram of detailed steps of a similarity image retrieval method based on sparse coding provided by an embodiment of the present invention, which includes the following steps:

[0048] Step S200, fixing the basis vectors in the dictionary and adjusting the encoding coefficients to minimize the objective function;

[0049] Specifically, the dictionary training is completed by keeping the base vectors in the dictionary unchanged and changing the coding coefficients to minimize the objective function.

[0050] Step S210, fixing the encoding coefficients, adjusting the basis vectors in the dictionary to minimize the objective function;

[0051] Specifically, by keeping the coding coefficients unchanged and changing the basis vectors in the dictionary, the objective function is minimized, thereby completing the dictionary training.

[0052] Step S220, by continuously iterating until convergence, a set of basis vectors that well expres...

Embodiment 3

[0074] see image 3 , image 3 It is a schematic diagram of modules of a similarity image retrieval system based on sparse coding provided by an embodiment of the present invention. A similarity image retrieval system based on sparse coding, which includes a first acquisition module, which is used to perform base vector representation according to a reference image to obtain a first sparse representation result, and a second acquisition module, which is used to perform base vector representation according to an image in an image database The second sparse characterization result is obtained by vector characterization, the calculation module is used to calculate the similarity between the first sparse characterization result and the second sparse characterization result, and the judgment module is used to judge whether the similarity is greater than a preset threshold, and if so, the judgment is yes Similarity image, if not, it is judged as a non-similarity image.

[0075] It...

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 provides a similarity image retrieval method and system based on sparse coding, and relates to the field of image recognition. The similarity image retrieval method based on sparse coding comprises the following steps: performing base vector representation according to a reference image to obtain a first sparse representation result; performing base vector representation according tothe images in the image library to obtain a second sparse representation result; calculating the similarity between the first sparse representation result and the second sparse representation result;and judging whether the similarity is greater than a preset threshold, if yes, judging that the image is a similarity image, and if not, judging that the image is a non-similarity image. According tothe method, the image feature information can be extracted more fully, and the similarity calculation process is more accurate and targeted. In addition, the invention further provides a similarity image retrieval system based on sparse coding. The similarity image retrieval system comprises a first acquisition module, a second acquisition module, a calculation module and a judgment module.

Description

technical field [0001] The present invention relates to the field of image recognition, in particular to a similarity image retrieval method and system based on sparse coding. Background technique [0002] With the advent of the digital media era, massive digital images have become an indispensable part of our lives, and are widely used in life sciences, education, culture and other fields. Many classic machine learning methods, especially deep learning methods, can retrieve target images from massive image libraries. How to use a single image to retrieve semantically similar images from a massive image database has very good practical application value. [0003] However, traditional machine learning methods cannot be very effectively applied to the retrieval of single similar images. The current mainstream methods have the following problems: [0004] 1. The feature extraction method is not very effective and highly dependent on training samples; [0005] 2. There is no...

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
IPC IPC(8): G06K9/62G06K9/46
CPCG06V10/513G06V10/40G06V10/462G06F18/22G06F18/214
Inventor 华臻王浩然李小玲吴昊
Owner SHANDONG INST OF BUSINESS & TECH
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com