Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Hash image retrieval method based on deep learning and low-rank matrix optimization

A low-rank matrix optimization and image retrieval technology, applied in digital data information retrieval, special data processing applications, instruments, etc., can solve problems such as inability to effectively control quantization errors, limit retrieval performance, and unable to retain similar feature representations.

Active Publication Date: 2019-08-30
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the previous methods of this kind all learn continuous feature codes first, and then binarize the continuous feature codes into hash codes through an independent post-processing step. This method cannot learn feature representations that retain similarity well. , and cannot effectively control the quantization error, which greatly limits the improvement of retrieval performance

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
  • Hash image retrieval method based on deep learning and low-rank matrix optimization
  • Hash image retrieval method based on deep learning and low-rank matrix optimization
  • Hash image retrieval method based on deep learning and low-rank matrix optimization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0083] The present invention will be further described below in conjunction with examples and drawings, but the embodiments of the present invention are not limited to this.

[0084] Such as figure 1 with figure 2 The shown method of hash image retrieval based on deep learning and low-rank matrix optimization includes the following steps:

[0085] S1. Obtain data, label and preprocess the data, and construct a database for image retrieval, including the following steps:

[0086] S11. Determine the scenes or objects that the data set focuses on, such as indoor scenes including TV, air conditioners, people, etc.; collect image data related to human indoor life scenes through web crawlers, and manually filter the image data to remove excluding human indoors Pictures of life scenes to get the data set Where x i Represents the i-th picture in the data set, N=50,000 is the total number of images in the data set;

[0087] S12. Perform category labeling on the images of the data set. The ...

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 discloses a Hash image retrieval method based on deep learning and low-rank matrix optimization, and the method comprises the following steps: S1, obtaining image data, carrying out themarking and preprocessing of the data, constructing a data set of image retrieval, and dividing the data set into a training set and a test set; S2, constructing a deep feature extraction network, andconstructing a deep Hash network trunk; S3, inputting the training set into a deep Hash network trunk, and constructing a Hash network based on a maximum probability likelihood and a low-rank regularization loss function; S4, training the Hash network; S5, respectively inputting the test set image and the training set image into a Hash network, generating a binary Hash code, and calculating a mutual Hamming distance; and S6, returning a picture with the minimum Hamming distance in the training set as a retrieval result. According to the image retrieval method based on Hash representation, theproblems of ring breakage of similarity information and large quantization error caused by the fact that binary continuous value features are directly coded into a Hamming space are solved, and the performance of the image retrieval method based on Hash representation is improved.

Description

Technical field [0001] The invention belongs to the technical field of hash image retrieval and artificial intelligence, and particularly relates to a hash image retrieval method based on deep learning and low-rank matrix optimization. Background technique [0002] In recent years, Internet technology, intelligent hardware and multimedia technology have achieved unprecedented development, and a large amount of network data has emerged, especially the widespread use of mobile devices, making all kinds of picture data full of network platforms and electronic communication equipment , How to match and retrieve massive image resources more accurately and efficiently, whether in theoretical research or in commercial applications, is of great value, such as recommendation of similar products in e-commerce shopping platforms, face retrieval, etc. [0003] The current image retrieval methods mainly include retrieval based on text tags and retrieval based on image content. Traditional imag...

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): G06F16/583G06K9/62
CPCG06F16/583G06V10/751G06F18/241G06F18/24147
Inventor 陈泽彬周万义青春美尹红艳吴婷婷
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products