Image texture feature extraction method and system based on local norm difference
A feature extraction and image texture technology, applied in the field of image processing, can solve problems such as loss of contrast information, high noise sensitivity, and difficult texture classification, and achieve the effect of improving accuracy and avoiding the effect of rotation changes
Active Publication Date: 2019-08-16
SHANDONG UNIV +1
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Such a rough approach may lead to two problems: loss of contrast information, high sensitivity to noise in uniform and near-uniform regions
Another limitation of LBP is the sensitivity to rotation changes
In fact, images are often affected by orientation changes, which will cause great difficulties for texture classification
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention.
[0047] figure 1 It is a schematic flow chart of an image texture feature extraction method based on local norm difference of the present invention, as shown in the figure, the image texture feature extraction method based on local norm difference includes:
[0048] Step 1: Obtain the image to be detected and convert it into a gray image;
[0049] Step 2: extract the local difference vector DV of each region in the gray image;
[0050] In step 2, the intensity difference between each neighborhood pixel and the central pixel is first calculated; finally, all the differences are concatenated to form a difference vector DV.
[0051] Specifically, in order not to lose gen...
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
Login to View More Abstract
The invention discloses a method and system for extracting image texture features based on local normative differences, wherein the method includes: acquiring an image to be detected and converting it into a gray image; extracting a local difference vector DV of each region in the gray image; The extracted local difference vectors DV are normalized respectively to obtain the original normalized difference vectors NDV of the local features of each region in the gray image; the original normalized difference vectors NDV of the local features of each region in the gray image are The normalized difference vector NDV is cyclically shifted; then the original normalized difference vector NDV and its cyclically shifted normalized difference vector NDV are classified and aggregated to generate several clusters; finally, the normalized difference vector with the smallest number of clusters is screened out. The normalized difference vector NDV is used as the texture feature of the image to be detected.
Description
technical field [0001] The invention belongs to the field of image processing, and in particular relates to an image texture feature extraction method and system based on local norm difference. Background technique [0002] Image texture is a type of visual pattern that reflects the spatial distribution of pixel intensities. Texture analysis is very important in many applications such as classification, recognition and segmentation. As an important topic in computer vision, texture classification has been extensively studied in the past few years. However, for real-world applications, texture classification remains a great challenge due to the complexity of texture patterns, variability in texture styles and scales. [0003] In addition, lighting is crucial for texture classification because lighting is very variable, such as shadows and highlights, not only between two different images, but also between different regions of an image. In general, it is currently difficult...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/46G06K9/62
CPCG06V10/44G06F18/23213G06F18/241
Inventor 张伟张伟东俞晓东李艺萌
Owner SHANDONG UNIV