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

Sketch retrieval method based on multiple binary HoG descriptors

A descriptor and binary technology, applied in character and pattern recognition, instrumentation, computing, etc., can solve the problems of memory occupancy timeliness and accuracy, and achieve wide adaptability, robustness, and effectiveness. Effect

Active Publication Date: 2017-11-28
NANJING UNIV OF SCI & TECH
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

We propose a retrieval method based on multiple binary HoG descriptors to solve the problems of memory usage, timeliness and accuracy in sketch 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
  • Sketch retrieval method based on multiple binary HoG descriptors
  • Sketch retrieval method based on multiple binary HoG descriptors
  • Sketch retrieval method based on multiple binary HoG descriptors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0015] combine figure 1 , a sketch retrieval method based on multiple binary HoG descriptors, including the following steps:

[0016] Step 1, extracting edge images from images in the database;

[0017] Step 2: Obtain a PBHoG feature descriptor based on the BHoG feature descriptor to extract and store the features of the edge image and the input sketch;

[0018] Step 3, based on the traditional HoG feature descriptor, a DBHoG descriptor is obtained to extract and store the feature of the edge image and the input sketch;

[0019] Step 4, set an image mask mask of a sketch as a query constraint, and calculate the distance between the two features of the input sketch and the edge image in steps 2 and 3 based on the Hamming distance;

[0020] Step 5, normalize and add the distances obtained by the two features to obtain the final MBHoG feature descriptor result, and select the image corresponding to the smallest first N values ​​in MBHoG as the query result;

[0021] Step 6, us...

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 sketch retrieval method based on multiple binary HoG descriptors. The sketch retrieval method includes extracting an edge image from an image in a database; extracting and storing characteristics of the edge image and an input sketch according to PBHoG characteristic descriptors; extracting and storing the characteristics of the edge image and the input sketch according to DBHoG descriptors; setting a sketch image mask as a restraint condition for query, and performing distance calculation on the two characteristics of the input sketch and the edge image according to Hamming distance; normalizing and summing the distances acquired based on the two characteristics to acquire a final MBHoG characteristic descriptor result, and selecting images corresponding to smallest front N values in MBHoG as an query result; taking single RGB value as input, acquiring multiple RGB values according to a weight setting method, and forming a 4096-dimensional color histogram; according to the color histogram, re-sequencing the front N images acquired in the step 5 and displaying the result.

Description

technical field [0001] The invention relates to a feature extraction and image retrieval technology, in particular to a sketch retrieval method based on multiple binary HoG descriptors. Background technique [0002] Image retrieval is a very important topic in the field of computer vision. In today's highly developed information age, the number of images on the Internet is increasing, and the content is becoming more and more abundant. How to find an effective image retrieval method is an important issue. The text-based retrieval method does not describe the image content clearly enough, and it is a time-consuming and labor-intensive task to label the image in the database, so the content-based retrieval method gradually appears. Traditional graph search methods use natural images as query input, but many times we do not have images that can be used as input. With the popularity of touchable smart devices, it is a good choice to use hand-drawn sketches as input for image r...

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): G06F17/30G06K9/46
CPCG06F16/5838G06V10/44G06V10/56G06V10/462
Inventor 唐金辉王天齐
Owner NANJING UNIV OF SCI & TECH
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