Multi-dimensional object robust high-speed retrieval and positioning method for some feature images

A feature image and positioning method technology, applied in special data processing applications, complex mathematical operations, instruments, etc., can solve problems such as image target retrieval and positioning system, image retrieval positioning system instability, poor positioning accuracy, etc., to achieve Solve the robustness and algorithm time complexity, improve the high accuracy rate, and reduce the effect of positioning error

Inactive Publication Date: 2012-06-20
洪涛
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0015] The technical problem to be solved by the present invention is to overcome the deficiencies and defects of the inaccurate or incapable image target retrieval and positioning system in the prior art when the target image content is incomplete; the purpose of the present invention is to realize when the image target part content In the case of occlusion or tight coupling, it provides an effective, fast and effective image target retrieval and recognition method, specifically a multi-dimensional target fast and robust retrieval and positioning method for partial feature images
The multi-dimensional target fast and robust retrieval and positioning method of this part of the feature image comprehensively solves the problem of image target retrieval and positioning through preprocessing, feature point processing, robust, fast and accurate matching of images, and image matching retrieval and positioning. Factors such as size, rotation, viewing angle transformation, partial occlusion, and tight coupling cause problems such as instability of the image retrieval and positioning system, low correspondence between accuracy and speed, and poor positioning accuracy; it is realized in the field of retrieval and positioning of partial feature images For better flexibility, easy to achieve the effect of performance, stability, accuracy, high speed and high precision

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] A method for fast and robust multi-dimensional target retrieval and positioning of partial feature images, the method sequentially includes the following specific steps:

[0040] Step (1), preprocessing: first, a plurality of different images stored in the database are filtered and decomposed by a Gabor filter to obtain 4 different bands in the frequency domain, each band is divided into 12 different sub-bands, each sub-band The ratio of the scale size is 1:2 in turn, and the angle difference between each sub-band is 30 degrees, then carry out the preprocessing of noise elimination and image definition enhancement in the Ycbcr image color gamut; wherein, in the process of noise elimination In, the size gradient model of the scale of each sub-band is used to roughly process the image edge, and the gradient mean is used as its control threshold; Image enhancement processing is performed separately in the space;

[0041] Step (2), feature point processing: for each band a...

Embodiment 2

[0045] A method for fast and robust multi-dimensional target retrieval and positioning of partial feature images, the method sequentially includes the following specific steps:

[0046] Step (1), preprocessing: first, a plurality of different images stored in the database are filtered and decomposed by a Gabor filter to obtain 4 different bands in the frequency domain, each band is divided into 12 different sub-bands, each sub-band The ratio of the scale size is 1:2 in turn, and the angle difference between each sub-band is 30 degrees, then carry out the preprocessing of noise elimination and image definition enhancement in the Ycbcr image color gamut; wherein, in the process of noise elimination In, the size gradient model of the scale of each sub-band is used to roughly process the image edge, and the gradient mean is used as its control threshold; Image enhancement processing is performed separately in the space;

[0047] Step (2), feature point processing: for each band a...

Embodiment 3

[0051] A method for fast and robust multi-dimensional target retrieval and positioning of partial feature images, the method sequentially includes the following specific steps:

[0052] Step (1), preprocessing: first, a plurality of different images stored in the database are filtered and decomposed by a Gabor filter to obtain 4 different bands in the frequency domain, each band is divided into 12 different sub-bands, each sub-band The ratio of the scale size is 1:2 in turn, and the angle difference between each sub-band is 30 degrees, then carry out the preprocessing of noise elimination and image definition enhancement in the Ycbcr image color gamut; wherein, in the process of noise elimination In, the size gradient model of the scale of each sub-band is used to roughly process the image edge, and the gradient mean is used as its control threshold; Image enhancement processing is performed separately in the space;

[0053] Step (2), feature point processing: for each band a...

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 a multi-dimensional object robust high-speed retrieval and positioning method for some feature images, which comprises the steps of pretreatment, feature point treatment, image robust high-speed accurate matching, and retrieval and positioning of matched images, and comprehensively solves the problems that an image retrieval and positioning system is unstable, low corresponding rate between the accuracy rate and speed, and poor positioning accuracy due to the size, rotation, viewing angle conversion, partial shielding, and close coupling of the images and other factors during the image object retrieval and positioning. The retrieval and positioning method provided by the invention belongs to the retrieval and positioning technical field of some feature images and has the effects of better flexibility, easiness in realization, stability, accuracy, high speed and high precision.

Description

technical field [0001] The invention belongs to the field of image feature target retrieval, and proposes a part-content image feature target retrieval method, in particular to a multi-dimensional target fast and robust search and positioning method for part feature images. Background technique [0002] In today's information society, although CAD technology has been widely used in the field of industrial design, a large amount of drawing information is still stored, managed and used in the form of paper and pictures. These engineering drawings are often accumulated by a system or industry for a long time, completely preserving the valuable experience in the past, and have a good reference for future design. A considerable part of them will be modified and reused in future design and manufacture. In order to reuse these drawings, it is an inevitable development to manage the information of these drawings and images with computers and establish a corresponding database, so a...

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): G06F17/30G06F17/14
Inventor 洪涛
Owner 洪涛
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