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

Image retrieval method based on margin directional error histogram

An edge direction, image retrieval technology, applied in image analysis, image data processing, special data processing applications, etc., can solve the problem that the accuracy rate and callback rate of returned result sets are not high, fast and accurate retrieval cannot be achieved, and image database retrieval efficiency Low-level problems, to achieve the effect of effective robustness, improved accuracy and recall rate, and effective feature difference

Inactive Publication Date: 2013-11-06
XIDIAN UNIV
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method incorporates image classification technology on the basis of the traditional content-based image retrieval method, which greatly improves the speed of image retrieval, there are still shortcomings: the accuracy rate and callback rate of the returned result set are not high. Inefficient database retrieval
Although this method can quickly and accurately locate the category of the image submitted by the user and improve the accuracy of the secondary retrieval, but this method uses the feedback interaction method, so when the image database is relatively large, due to the feedback information and its own Retrieval of information, resulting in a large increase in the amount of information processing, unable to achieve fast and accurate 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
  • Image retrieval method based on margin directional error histogram
  • Image retrieval method based on margin directional error histogram
  • Image retrieval method based on margin directional error histogram

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] The invention is a retrieval method based on the feature of the edge direction difference histogram. With the continuous development of multimedia technology and the continuous popularization of the Internet, the application of image information is becoming more and more extensive. Image retrieval involves all aspects of today's society and people's daily life, such as digital libraries, public security and crime investigation. Image retrieval can quickly and effectively find the information people need, integrate it into people's daily life, and bring people Convenience, image retrieval has more and more broad application prospects. refer to figure 1 , provide the following specific examples to the realization of the present invention:

[0043] Step 1: Input the retrieved color image.

[0044] Step 2: Perform grayscale transformation on the input retrieved image, process it through a direction-tunable filter, select a two-dimensional Gaussian function as the filter k...

Embodiment 2

[0074] Retrieval method based on edge direction difference histogram feature is the same as embodiment 1

[0075] Step 1, input the retrieved color image;

[0076] This example inputs a search image randomly selected in the Corel-1000 image database, see image 3 , it is necessary to retrieve images of the same type in the Corel-1000 image database, which includes 10 types of images, see figure 2 , each category includes 100 images, and some examples of each category such as figure 2 As shown, the retrieved image used in this example is image 3 shown.

[0077] Step 2: Perform grayscale transformation on the input retrieved image, process it through a direction-tunable filter, select a two-dimensional Gaussian function as the filter kernel function, and calculate the directional derivative of the image in the X and Y directions with the first-order Gaussian kernel function The convolution of each pixel gets the energy function W in 2L directions σ (x, y, θ), L represent...

Embodiment 3

[0092] Retrieval method based on edge direction difference histogram feature is the same as embodiment 1-2

[0093] This example also selects the Corel-1000 image database, which includes 10 types of images, and some examples of each type are as follows figure 2 As shown, each class includes 100 images, and the same retrieval process of embodiment 1 is performed on each image in the database, and when the value n of the number of retrieved images returned is 10, 20, ..., 100, all images in the image database are calculated. The average retrieval accuracy rate and the average retrieval recall rate of 1000 images were drawn and compared with the method and CSD method proposed by Jhanwar, Hung, and Chuen well known in the art. The comparison curve of the average retrieval accuracy rate is as follows Figure 7 As shown, the comparison curve of the average retrieval callback rate is as follows Figure 8 shown.

[0094] The comparison results of the average accuracy rate of all 1...

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 retrieval method based on an edge directional error histogram. The method comprises the following steps: firstly, inputting an image required to be retrieved; processing the image through a steerable filter; extracting the edge of the image according to the result of the steerable filter; extracting the edge directional error characteristic of the retrieval image according to the edge of the retrieval image; calculating the edge direction pixel characteristics of the pixels of the retrieval image; obtaining the edge directional error histogram characteristic of the image through integrated computation, that is, obtaining the characteristic of the image, which is used for matching; likewise, extracting the edge directional error histogram characteristics of to-be-retrieved images in a database; performing similarity matching to the edge directional error histogram characteristics of the retrieval image and the to-be-retrieved images; displaying image retrieval results according to the similarity matching result of the retrieval image and the to-be-retrieved images. The method particularly has the advantages of high retrieval speed and higher accuracy rate and callback rate in retrieval of a large-scale image database, and can be applied to real-time man-machine interaction and the image retrieval of large-scale image databases.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a content-based image retrieval method, in particular to an image retrieval method based on an edge direction difference histogram, which can be applied to fields such as real-time human-computer interaction image retrieval and offline large database image retrieval. Background technique [0002] Image retrieval refers to the technique of finding images with specified characteristics or containing specified content in an image collection. With the continuous development of multimedia technology, network technology and database technology, and the continuous popularization of the Internet, people's demand for multimedia data such as graphics and images is becoming stronger and stronger, so the application of image information is becoming more and more extensive. The capacity of digital images is increasing rapidly with people's demand, and millions of images are generated e...

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): G06F17/30G06T7/00
Inventor 田小林刘宪龙焦李成王爽马文萍马晶晶张坤张小华
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com