Supercharge Your Innovation With Domain-Expert AI Agents!

Image-segmentation-based picture searching method

A technology of image segmentation and image search, which is applied in the field of image search based on image segmentation, and can solve problems such as the difficulty of separating the human body from the image background

Inactive Publication Date: 2015-09-16
SHANGHAI JIAO TONG UNIV
View PDF8 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is difficult for this technology to separate the human body in the image from the background of the image.

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
  • Image-segmentation-based picture searching method
  • Image-segmentation-based picture searching method
  • Image-segmentation-based picture searching method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] Such as figure 1 As shown, this embodiment includes the following steps:

[0022] The first step is to segment and process the pictures in the picture library to obtain the internal feature information of the picture and the region. Obtain the H histogram of HSV in the area, extract and obtain line information, and retain the area feature, H feature, and line feature as image features for subsequent search.

[0023] The line features refer to the lines separating neighborhoods obtained after image segmentation processing.

[0024] In the second step, the user establishes a link with the server, and uploads the image taken, and the server obtains the image taken and uploaded by the user through the socket and has been shrunk down to a standard size.

[0025] The third step is to perform image segmentation on the uploaded image to obtain a certain number of segmented regions.

[0026] The fourth step is to calculate the similarity between the reference picture and 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 relates to an image-segmentation-based picture searching method. The method comprises: step one, carrying out segmentation on a picture in a picture database; to be specific, dividing the image into different areas based on a segmentation algorithm; step two, obtaining internal feature information of the picture and the areas; to be specific, obtaining H histograms of HSVs in the areas, extracting and obtaining line information, and keeping area features, H features, and line features as image features; step three, obtaining an image shot and uploaded by a user by using socket and carrying out image segmentation; and step four, comparing the feature information with segmented areas, filling inputted picture segmented areas having highest similarity with reference image areas in the database successively, and combining three kinds of pieces of information of the image features to obtain a searching result. With the method, searched pictures in a picture wall have the backgrounds with highest similarity with backgrounds of pictures shot by users.

Description

technical field [0001] The present invention relates to a technique in the field of image processing, in particular to an image search method based on image segmentation. Background technique [0002] Similar image search is a new technology emerging in recent years, that is, to use a picture to search for similar pictures in the picture library, which has been implemented by some search engines. Most of the existing similar image matching methods are based on the key technology of "perceptual hashing algorithm". It generates a fingerprint string for each image and compares the fingerprints of different images. The more similar the results, the closer the images are. [0003] In terms of image segmentation, the classic greedy clustering image segmentation method is proposed in the paper "Efficient Graph‐Based Image Segmentation" published by Pedro F. Felzenszwa and Daniel P. Huttenlocher, which calculates the pixel point and its neighborhood The dissimilarity, update thresh...

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 Applications(China)
IPC IPC(8): G06T7/00
CPCG06T7/66G06T7/80
Inventor 边艺徐男秦立厦夏立盛斌
Owner SHANGHAI JIAO TONG UNIV
Features
  • R&D
  • 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