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

Image sorting method based on local colors and distribution characteristics of characteristic points

A feature point and image technology, applied in the field of image processing, can solve the problems of less feature point spatial distribution structure, affecting image accuracy, insufficient image feature description effectiveness, etc., to achieve the effect of overcoming matching errors and accurate description.

Inactive Publication Date: 2013-06-12
XIDIAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There are two problems in the image sorting method based on feature points: (1) The extracted image features mainly reflect the local characteristics of feature points, and less consider the spatial distribution structure of feature points, so the effectiveness of image feature description is not enough ; (2) Due to the difference between the underlying visual features of the image and the rich semantic features of the user, the results of image sorting are ambiguous
Both of these affect the accuracy of image picking

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 sorting method based on local colors and distribution characteristics of characteristic points
  • Image sorting method based on local colors and distribution characteristics of characteristic points
  • Image sorting method based on local colors and distribution characteristics of characteristic points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be described in further detail below with reference to the drawings.

[0035] Reference figure 1 The image picking steps of the present invention are as follows:

[0036] Step 1. Normalize and detect feature points for a specified target image.

[0037] (1.1) Scale normalization of target image

[0038] The target image Q(x, y) is normalized according to the following formula:

[0039] Q′(x,y)=Q(x / a,y / a)

[0040] Among them, Q'(x, y) is the target image after the scale is normalized, (x, y) represents the coordinates of the image pixels, Represents the scaling factor, β is a constant, Is the 0th order geometric moment of Q(x,y).

[0041] (1.2) Rotation normalization of target image

[0042] Calculate the normalized rotation angle θ of the target image Q′(x,y) after the scale is normalized:

[0043] θ=arctan(-t 1 / t 2 )

[0044] Where t 1 And t 2 Are two tensors, t 1 =μ 12 +μ 30 , T 2 =μ 21 +μ 03 ,

[0045] μ 12 , Μ 30 , Μ 21 , Μ 03 Are the four third-order ...

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 an image sorting method based on local colors and distribution characteristics of characteristic points, which mainly solves the problem of the poor effectiveness of image characteristic description and the ambiguity in image understanding in the prior art. The method comprises the following steps of: firstly, performing scale normalization and rotation normalization on the image, and detecting characteristic points; then, dividing the normalized image into a series of fan-shaped sub-regions with unequal acreage according to the distribution of the characteristic points, and extracting the local colors and the space distribution characteristics of the characteristic points in each sub-region, generating a characteristic vector, measuring the similarity and orderingthe sub-regions; taking the image as a multi-instance package to obtaining characteristics of a target image through a multi-instance learning method; and finally, recalculating the similarity, and outputting the sorting result. The method not only improves the effectiveness of the image characteristic description, but also reduces the ambiguity in the process of sorting out the images, so that the method can sort out internet images more accurately, and can be used for searching image information in the internet.

Description

Technical field [0001] The invention relates to the technical field of image processing, in particular to an image picking method, which can be used for searching image information in the Internet. Background technique [0002] The rapid development of computer technology and Internet technology makes it easy for people to share resources. The wide spread of multimedia information represented by digital images and audio / video on the Internet, how to quickly and efficiently detect users from massive image databases The required image is a challenging problem. Content-based image picking is a research hotspot in the multimedia field that has attracted much attention in recent years by extracting features from images and measuring similarity with images in the image library. Traditional methods use the global features of the image to sort out, but due to the large amount of calculation of the global features, and many times users are only interested in a certain object in the image...

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): G06K9/66
Inventor 郭宝龙孟繁杰郭磊
Owner XIDIAN 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