Label anti-transfer method based on computer visual recognition
A computer vision, anti-transfer technology, applied in computer parts, computing, record carriers used by machines, etc., can solve the problems of inconvenient application and high chip cost, and meet market demand, low-cost application requirements, strong label anti- The effect of transfer performance
Active Publication Date: 2021-09-24
深圳纸芯科技有限公司
View PDF16 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The disadvantages of this technology, in addition to the high cost of the chip itself, the inconvenience of application is also the reason why it has not been widely popularized in the mass anti-counterfeiting market.
For example, Android mobile phones can read third-party anti-counterfeiting chips on the market, but Apple mobile phones do not open this function.
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 1
[0082] The label anti-transfer method based on computer vision recognition in the present embodiment comprises the following steps:
[0083] Step S1, label generation, the specific steps are as follows:
[0084] Step S10, generating a noise pattern;
[0085] First, for each label, a random and independent noise pattern is generated. Because this noise pattern must be used for identification and comparison in the later stage of the algorithm, and considering the interference that may be introduced by the resampling of the image by the mobile phone camera, the noise pattern should not be too small. The salient features in the noise pattern must withstand the impact of camera resampling.
[0086] For this, the present invention proposes a checkerboard-based noise generation method. The checkerboard noise generation method needs to first divide the image into grids, and each grid can be understood as a salient feature in the noise pattern. Such as figure 1 As shown, the patte...
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 label anti-transfer method based on computer visual recognition. The method comprises the following steps of generating an original noise pattern; performing polar coordinate conversion to generate a polar coordinate noise pattern; combining the polar coordinate noise pattern into an outer circle defined in a preset label template; according to the combined pattern, printing the polar coordinate noise pattern and the label template on a piece of label paper at the same time, and obtaining a label; when the label is pasted, hollowing an area between the polar coordinate noise pattern and the outer circle in the label template; obtaining an recognition parameter of the combined pattern; capturing the polar coordinate noise pattern, and performing inverse transformation processing on the polar coordinate noise pattern to obtain an inverse transformation noise pattern; judging whether the inverse transformation noise pattern is the same as the original noise pattern or not, and performing foreign attack detection on the label; and judging whether the LBP value of the inverse transformation noise pattern is the same as the LBP value of the original noise pattern or not so as to judge whether the label is true or false. According to the present invention, the anti-transfer performance is higher, the production cost is reduced, and the user experience is improved.
Description
technical field [0001] The invention relates to a method for protecting an anti-counterfeit label, in particular to a method for preventing label transfer based on computer vision recognition. Background technique [0002] At present, counterfeit and shoddy goods are the public enemy of the whole people, causing heavy losses to consumers and enterprises. At present, the relatively new anti-counterfeiting means on the market are mainly divided into two basic forms: the first is material fingerprint anti-counterfeiting; the second is label anti-counterfeiting. As an emerging anti-counterfeiting method in recent years, material fingerprint anti-counterfeiting is a similar technology to our common face and fingerprint recognition. The fingerprint in the material fingerprint anti-counterfeiting refers to the characteristic texture of the appearance of the product. The material fingerprint anti-counterfeiting needs to collect and analyze the characteristic texture of the product ...
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 Applications(China)
IPC IPC(8): G06K19/06
CPCG06K19/06046G06K19/06037G06K19/06075
Inventor 何洋
Owner 深圳纸芯科技有限公司