Duplicate picture detection method based on SIFT algorithm

An algorithm and picture technology, applied in computing, computer parts, instruments, etc., can solve problems such as high labor costs, and achieve the effect of easy extraction, easy identification of objects, and large amount of information

Inactive Publication Date: 2017-11-24
FOCUS TECH
View PDF6 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In order to cope with the complex picture environment of e-commerce websites, the judgment of duplicate pictures was usually manually detected by business personnel in the past. However, with the increase of website traffic and a large number of new products, the manual detection method will inevitably consume a lot of labor costs.

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
  • Duplicate picture detection method based on SIFT algorithm
  • Duplicate picture detection method based on SIFT algorithm
  • Duplicate picture detection method based on SIFT algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The specific embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0026] refer to figure 1 Shown, the implementation steps of the present invention are as follows:

[0027] S11: Image preprocessing

[0028] Because some merchants on the Made in China website will add text and logos to the upper and lower ends of their product pictures, and the main body of the image, that is, the product display part, is mainly concentrated in the center of the picture. Therefore, before applying SIFT, it is necessary to do screenshot processing and pass the actual test. We only save the upper and lower 15%-85% of the image.

[0029] S12: Representation of scale space

[0030] The SIFT algorithm is to find key points in different scale spaces, and the acquisition of scale spaces needs to be realized by using Gaussian blur. The scale space L(x,y,σ) of an image is defined as the convolution operation of the ori...

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 an automatic e-commerce website duplicate picture detection method based on an SIFT algorithm. The method comprises the following steps: 1) carrying out screenshot pretreatment on pictures to be processed in a website, and keeping 15%-85% of upper and lower intervals of the pictures; 2) scale space construction: through scale transform of the pictures, obtaining a scale space representation sequence of the images under multiple scales; 3) key point positioning: at each candidate position, determining location and scale through a fitting fine model; 4) key point direction determination: based on image local gradient direction, allocating one or more direction to each key point position; 5) key point description: in neighborhood surrounding each key point, measuring image local gradient in the selected scale; 6) key matching: carrying out pair-wise comparison through a describer in the two images and finding out a plurality of pairs of matched feature points; and 7) similarity calculation: through a customized picture similarity calculating formula, judging whether the pictures are duplicate pictures.

Description

technical field [0001] The invention relates to the field of image detection, in particular to a method for detecting repeated pictures on an e-commerce website based on the SIFT algorithm. Background technique [0002] In the increasingly competitive commodity market, merchants on some e-commerce websites (such as Made in China, etc.) submit the same product repeatedly, that is, repeatedly distribute goods, in order to increase product flow and sales. Usually, e-commerce websites will restrict merchants from re-distributing goods. Usually, the website has the following definition for re-distributing goods: products that are exactly the same and have the same important attributes of the goods are only allowed to use one selling method and publish once. Violation of the above rules can be judged as repeated distribution; for different products, product titles, descriptions, pictures, etc. must reflect the differences of the products, otherwise it will be judged as repeated di...

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): G06K9/46G06K9/62
CPCG06V10/462G06F18/22
Inventor 钟力吴海龙
Owner FOCUS 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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap