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

A semi-supervised hash image search device based on group Lasso

An image search and semi-supervised technology, applied in the field of image search, can solve problems such as labor-intensive and no labels, and achieve the effect of saving storage space

Active Publication Date: 2019-10-08
EAST CHINA NORMAL UNIV +1
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, considering the status quo of image data labeling in real life, especially in the fields of image search and recognition, the largest amount of image data that is most convenient to obtain is unlabeled, and only a small part is obtained with manpower and material resources. labeled image data

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
  • A semi-supervised hash image search device based on group Lasso
  • A semi-supervised hash image search device based on group Lasso
  • A semi-supervised hash image search device based on group Lasso

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] According to an embodiment of the present invention, a semi-supervised hash image search device based on Group Lasso is provided, such as figure 2 shown, including:

[0038] The preprocessing module 201 is used to identify label images and non-label images in the image database, and preprocess the input images, label images and non-label images;

[0039] The training and learning module 202 is used to carry out semi-supervised hash learning based on Group Lasso to obtain the corresponding binary hash code of each image according to the input image, label image and non-label image after preprocessing module 201 preprocessing;

[0040] The calculation module 203 is used to calculate the Hamming distance between the input image and each image in the image database according to the binary hash code obtained by the training learning module 202, and return the image corresponding to the minimum Hamming distance as the image search result.

[0041] According to an embodiment...

Embodiment 2

[0054] According to an embodiment of the present invention, a semi-supervised hash image search method based on Group Lasso is proposed, such as image 3 shown, including:

[0055] Step 101: Identify label images and non-label images in the image database, and preprocess the input images, label images and non-label images;

[0056] Step 102: Perform semi-supervised hash learning based on GroupLasso according to the preprocessed input image, label image and non-label image to obtain the binary hash code corresponding to each image;

[0057] Step 103: Calculate the Hamming distance between the input image and each image in the image database according to the binary hash code, and return the image corresponding to the minimum Hamming distance as the image search result.

[0058] According to an embodiment of the present invention, in step 101, the preprocessing includes but not limited to: grayscale, normalization, geometric transformation and noise reduction operations.

[005...

Embodiment 3

[0077] According to an embodiment of the present invention, a semi-supervised hash image search method based on Group Lasso is proposed, such as Figure 4 As shown, including: the process of training image data and the process of searching image data;

[0078] Among them, the training image data process includes:

[0079] Step a1: identifying label images and non-label images in the image database, and preprocessing each image in the image database;

[0080] Step a2: Perform semi-supervised hash learning based on Group Lasso according to the processed label image and non-label image to obtain the binary hash code corresponding to each image;

[0081] Among them, the semi-supervised hash learning based on Group Lasso obtains the group structure learning results in units of groups, and has sparsity.

[0082] Step a3: Generate a hash lookup table according to the obtained binary hash codes.

[0083] During the image search process, include:

[0084] Step b1: Preprocessing 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 provides a semi-supervised hash image search device based on Group Lasso, which belongs to the field of image search. The device includes: a preprocessing module, used to identify label images and non-label images in the image database, and preprocess the input image, label image and non-label image; Image, label image and non-label image are based on Group Lasso semi-supervised hash learning to obtain the binary hash code corresponding to each image; the calculation module is used to calculate the relationship between the input image and each image in the image database according to the binary hash code. Hamming distance, and returns the image corresponding to the minimum Hamming distance as the image search result. In the present invention, the image data structure can be effectively modeled in combination with the status of the existing image data, and the required image can be quickly and accurately searched without storing the image itself, which greatly saves storage space.

Description

technical field [0001] The invention relates to the field of image search, in particular to a semi-supervised hash image search device based on Group Lasso. Background technique [0002] The advent of the era of big data, the rapid development of Internet technology and the increasing popularity of imaging devices such as smartphones and cameras have made data collection of media resources such as images more and more convenient. In the era of Web 2.0, people are no longer satisfied with just using words to convey information, especially with the popularity of social software such as Facebook, Twitter, WeChat, Weibo, etc., people have become very proficient in using chat "emoticons" in daily life package”, small videos in Moments, voice messages, etc. These images, videos, audios and other massive unstructured data are growing at an alarming rate every day. According to a survey report by the market research company IDC, 80% of the data in the world are unstructured data, ...

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): G06F16/58G06K9/36G06K9/40G06K9/42G06K9/62
CPCG06F16/5866G06V10/247G06V10/20G06V10/32G06V10/30G06F18/22G06F18/214
Inventor 黄滟鸿史建琦王祥丰吴苑斌
Owner EAST CHINA NORMAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com