Feature extracting method of Sobel operator filtering general picture for representing textile fabric veins

A Sobel operator and fabric texture technology, applied in computing, image data processing, computer parts and other directions, can solve problems such as difficulty in selection, inability to achieve more adequate characterization of textures, loss of grayscale transition information, etc., to achieve the calculation process. easy effect

Inactive Publication Date: 2011-04-06
DONGHUA UNIV
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This has two main disadvantages: one is that it is difficult to select the optimal threshold for different textures; the other is that after the image is binarized, a large amount of grayscale transition information is lost, leaving only black and full White binary information, while the texture image to be processed usually has 256 gray levels
Therefore, the above processing method is relatively cumbersome and the features extracted on this basis cannot achieve a more adequate representation of the texture.

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
  • Feature extracting method of Sobel operator filtering general picture for representing textile fabric veins
  • Feature extracting method of Sobel operator filtering general picture for representing textile fabric veins
  • Feature extracting method of Sobel operator filtering general picture for representing textile fabric veins

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] (1) Acquire the digital image of fabric texture, ensure that the weft direction is basically consistent with the horizontal direction of the image, and the warp direction is consistent with the vertical direction of the image, such as figure 1 shown.

[0055] (2) Implement Sobel operator horizontal filter processing on the original fabric image, and obtain the Sobel operator horizontal filter image of the original image, denoted as W h ,Such as figure 2 shown.

[0056] (3) Implement the Sobel operator vertical filtering process on the original fabric image, and obtain the Sobel operator vertical filtering image of the original image, denoted as W h ,Such as image 3 shown.

[0057] (4) Select the statistic to be used. In this example, Shannon entropy is selected as a statistic. The calculation formula of Shannon entropy is as follows:

[0058] X ( s ) = - Σ i ...

Embodiment 2

[0063] In this example, each step is the same as in Example 1, the difference is:

[0064] (1) The processed images are different. The digitized image of fabric texture obtained in this example is as follows: Figure 4 As shown, the graph after horizontal filtering by Sobel operator and the graph after vertical filtering by Sobel operator are shown as Figure 5 with Image 6 shown.

[0065] (2) Two statistics are selected, one is the Shannon entropy and the other is the gray mean value. Their calculation formulas are as follows:

[0066] Shannon entropy X ( s ) = - Σ i s i 2 log 2 ( s i 2 )

[0067] gray mean X ( s ) = 1 n ...

Embodiment 3

[0070] In this example, each step is the same as in Example 1, the difference is:

[0071] (1) The processed images are different. The digitized image of fabric texture obtained in this example is as follows: Figure 7 As shown, the graph after horizontal filtering by Sobel operator and the graph after vertical filtering by Sobel operator are shown as Figure 8 with Figure 9 shown.

[0072] (2) Three statistics are selected, one is logarithmic energy entropy, one is standard deviation, and the other is kurtosis. Their calculation formulas are as follows:

[0073] logarithmic energy entropy X ( s ) = Σ i log ( s i 2 )

[0074] standard deviation X ( s ) = 1 n - ...

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 belongs to the field of digital image process and pattern recognition, in particular relating to a feature extracting method of Sobel operator filtering general picture for representing textile fabric veins, comprising the following steps of: respectively and synchronously carrying out the treatments of horizontal filtering and vertical filtering of Sobel operator on a textile fabric image to obtain two corresponding filtering images, and then respectively extracting one or more groups of grey scale statistic with a coordinate calculation mode from the two corresponding filtering images to form feature vectors representing textile fabric veins general picture information, wherein the extracted grey scale statistic features have better complementarity, the feature vectors formed by the extracted grey scale statistic can more fully represent the general picture information representing the textile fabric veins. The invention has the other advantages of not needing to carry out fusion and binarization treatments on the image after the Sobel operator filtering, thereby avoiding the difficulty of binary threshold selection and also abundantly reserving the useful information of the image after the Sobel operator filtering.

Description

technical field [0001] The invention belongs to the field of digital image processing and pattern recognition, in particular to a Sobel operator filter profile feature extraction method for characterizing fabric texture. Background technique [0002] Sobel operator is one of the operators in image processing, mainly used for edge detection. Technically, it is a discrete difference operator, which is used to approximate the gradient of the image brightness function. Using this operator at any point in the image will generate a corresponding gradient vector. There are two Sobel operators, one to detect horizontal edges and the other to detect vertical edges. The Sobel operator uses two 3×3 direction templates or convolution kernels to perform neighborhood convolution with each point in the image in the image space to complete edge detection. One of the two direction templates is enhanced by approximating the vertical direction gradient. The horizontal edge of the image, and...

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): G06T7/00G06K9/46
Inventor 步红刚汪军黄秀宝周建
Owner DONGHUA UNIV
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