Intelligent texture anti-counterfeiting method on basis of DWT-DFT (Discrete Wavelet Transform to Discrete Fourier Transformation)
A DWT-DFT and texture technology, applied in data processing applications, image data processing, image analysis, etc., can solve the problems of manual comparison and long time consumption, and achieve good compatibility, strong resistance to geometric attacks, and network transmission speed accelerated effect
Inactive Publication Date: 2013-08-07
HAINAN UNIVERSITY
View PDF2 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] There are following deficiencies in the above-mentioned identification method in practical application: 1) need manual comparison
When comparing texture anti-counterfeiting labels, users must first download clear texture photos from the Internet, which takes a long time
[0005] For this reason, the conventional texture anti-counterfeiting technology has certain shortcomings in terms of intelligence, rapidity and occupied storage space of identification.
In particular, the research on intelligent algorithms for automatic identification has not yet been publicly reported.
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
[0114] The present invention will be further described below in conjunction with accompanying drawing, select a texture picture with black frame as original texture image, adding black frame is in order to guarantee energy conservation when geometrical transformation, be recorded as: F={f(i, j)|f (i, j)∈R; 1≤i≤N1, 1≤j≤N2}, see Figure 1(a), where the size of the texture image is 128×128. The corresponding full-image DWT-DFT coefficient matrix is FF(i, j), select the low intermediate frequency coefficient Y(j), 1≤j≤L, the first value Y(1) represents the DC component of the image, and then from low to Arranged in order of highest frequency. Considering the goodness of the detection effect, we choose 4x4=16 complex coefficients of low and medium frequencies as the feature vector V (here, a complex number is regarded as two coefficients of real part and imaginary part), and there are 16x2=32 low-frequency coefficients in total. That is, L=32. The selected DWT-DFT coefficient ma...
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 an intelligent texture anti-counterfeiting method on the basis of DWT-DFT (Discrete Wavelet Transform to Discrete Fourier Transformation) and belongs to the field of texture anti-counterfeiting. In the intelligent texture anti-counterfeiting method, image feature extraction is firstly carried out and then image automatic authentication is carried out, wherein the image feature extraction process comprises the steps of (1) carrying out DWT on texture images, then carrying out DFT on an approximation subgraph and extracting feature vectors V (j), and (2) storing the obtained N feature vectors into a texture feature database; and the image automatic authentication process comprises the steps of (3) scanning a texture tagged image to be detected by a mobile phone, obtaining a visual feature vector V' of the image to be detected by applying the method in the step (1) and uploading the visual feature vector V' to a server, (4) obtaining a value of a normalized correlation coefficient NC (n) between visual feature vectors V(n) of all the texture images in the database and the visual feature vector V' of the image to be detected, and (5) returning the maximum value of the NC (n) to the mobile phone of a user. Experiments prove that the intelligent texture anti-counterfeiting method has capacity of automatically identifying the texture images and has a high network transmission speed.
Description
technical field [0001] The invention belongs to the technical field of texture anti-counterfeiting. The invention relates to an intelligent texture anti-counterfeiting technology involving wavelet transform (DWT), discrete Fourier transform (DFT), and image visual features, and is a method for automatically identifying texture anti-counterfeiting labels. Background technique [0002] Counterfeit and shoddy products are a major hazard to society, seriously endangering the legitimate rights and interests of consumers, and seriously disrupting the rules of the entire social and economic operation. In order to solve the problem of counterfeit and shoddy products, using anti-counterfeiting technology is an effective means. Anti-counterfeiting technology is a technical means used to identify authenticity and prevent counterfeiting and counterfeiting. From the perspective of technical characteristics and functional evolution, current anti-counterfeiting technology can be divided i...
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 IPC IPC(8): G06T7/00G06Q30/00
Inventor 李京兵周又玲沈重任佳
Owner HAINAN UNIVERSITY