CN110866578B - A two-dimensional texture code and its encoding and decoding method - Google Patents
A two-dimensional texture code and its encoding and decoding method Download PDFInfo
- Publication number
- CN110866578B CN110866578B CN201911035069.7A CN201911035069A CN110866578B CN 110866578 B CN110866578 B CN 110866578B CN 201911035069 A CN201911035069 A CN 201911035069A CN 110866578 B CN110866578 B CN 110866578B
- Authority
- CN
- China
- Prior art keywords
- texture
- code
- dimensional
- dimensional texture
- texture code
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000012937 correction Methods 0.000 claims abstract description 37
- 238000013135 deep learning Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 206010047571 Visual impairment Diseases 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000029257 vision disease Diseases 0.000 description 2
- 230000004393 visual impairment Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012567 pattern recognition method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K19/00—Record carriers for use with machines and with at least a part designed to carry digital markings
- G06K19/06—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code
- G06K19/06009—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code with optically detectable marking
- G06K19/06037—Record carriers for use with machines and with at least a part designed to carry digital markings characterised by the kind of the digital marking, e.g. shape, nature, code with optically detectable marking multi-dimensional coding
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
本发明公开了一种二维纹理码及其编码和解码方法，所述二维纹理码包括L形的格式矫正区和矩形的纹理数据区，所述格式矫正区用于矫正二维纹理码的格式，所述矩形的纹理数据区被分割成m个矩形的子区域，所述每一子区域由一个纹理图片所占据，共有n种不同类型的纹理图片，每一种类型的纹理图片对应一个解码字符，且n>m。本发明的二维纹理码及其编码和解码方法，可有效降低二维码的信息冗余，提高低像素下解码的鲁棒性。
The invention discloses a two-dimensional texture code and a coding and decoding method thereof. The two-dimensional texture code includes an L-shaped format correction area and a rectangular texture data area, and the format correction area is used for correcting the two-dimensional texture code. Format, the rectangular texture data area is divided into m rectangular sub-areas, each sub-area is occupied by a texture picture, there are n different types of texture pictures, and each type of texture picture corresponds to one Decode characters, and n>m. The two-dimensional texture code and the encoding and decoding method thereof of the present invention can effectively reduce the information redundancy of the two-dimensional code and improve the robustness of decoding at low pixels.
Description
Technical Field
The invention relates to the technical field of two-dimensional codes, in particular to a two-dimensional texture code and a coding and decoding method thereof.
Background
With the continuous progress and development of digital technology, people's daily life is profoundly changed. The novel technologies such as mobile payment, single-vehicle sharing, unmanned retail and the like are inseparable from our lives, and the shopping and the traveling of people are greatly facilitated. Wherein the success of these emerging technologies is indistinguishable from the popularity and application of two-dimensional codes.
Two-dimensional codes, also known as two-dimensional barcodes, use black and white pixels to represent 0 and 1. The two-dimensional Code most common in life is a QR Code (QRCode). The two-dimensional code can be successfully applied to various occasions, and is mainly attributed to the fact that the two-dimensional code has extremely strong robustness and sufficient information capacity. The sufficient information capacity allows the two-dimensional code to have a sufficient error correction function. This makes the two-dimensional code a fast, efficient and robust information carrier.
However, some specific application scenarios do not depend on high storage and high redundancy of the two-dimensional code, and thus the high redundancy of the information of the two-dimensional code becomes a disadvantage thereof. For example, in an auxiliary visual impairment project based on a two-dimensional code and a mobile phone, the two-dimensional code is used as positioning information and category information and pasted on a common tool, and the acquisition requirement of visual impairment personnel is met. For another example, in patent publication No. CN102735235B, the robot performs indoor navigation using a QR two-dimensional code attached to a location point.
These scenarios have common features: two-dimensional codes are used for positioning or classification, and only limited categories are available in the system, so that high-capacity storage of the two-dimensional codes is not required. Therefore, the direct application of the standard QR code introduces the problem of not robust positioning, and the decoding is also erroneous due to the redundancy of information.
If the two-dimensional code pixels in the image are too low and the target is too small, the two-dimensional code cannot be correctly positioned and decoded by a decoder. A black-and-white pixel block embodied as a two-dimensional code is susceptible to image quality as a minimum unit and cannot be decoded.
Although there are many patents on two-dimensional code positioning and decoding, such as the positioning method with the publication number CN106485183A, the decoding method with the publication number CN105138940A, etc., these methods cannot fundamentally solve the above-mentioned problems.
Therefore, a new two-dimensional pattern recognition method is needed, which can effectively reduce the information redundancy of the two-dimensional code and improve the robustness under low pixels.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a two-dimensional texture code and a coding and decoding method thereof, which can effectively reduce information redundancy and improve robustness under low pixels.
According to an aspect of the present invention, there is provided a two-dimensional texture code, including: the two-dimensional texture code decoding device comprises an L-shaped format correction area and a rectangular texture data area, wherein the format correction area is used for correcting the format of the two-dimensional texture code, the rectangular texture data area is divided into m rectangular sub-areas, each sub-area is occupied by one texture picture, n different types of texture pictures are shared, each type of texture picture corresponds to one decoding character, and n is greater than m.
Preferably, m is 4, and the texture data region is divided into 4 rectangular sub-regions.
Preferably, n is 10, there are 10 different types of texture pictures.
Preferably, the format correction region is a full black L shape surrounding the outside of both sides of the rectangular texture data region.
Preferably, the format correction area is used for correcting the format of the two-dimensional texture code and correcting the two-dimensional texture code to a standard direction and shape.
Preferably, the single texture picture is 200 pixels, and the width of the format correction region is 25 pixels.
According to another aspect of the present invention, there is also provided a two-dimensional texture code encoding method, which is applicable to the two-dimensional texture code, and includes the following steps:
determining a number to be encoded;
and filling the number to be coded into each sub-region according to the texture picture type corresponding to the decoded character.
Preferably, the method further comprises the following steps: determining the m and n according to the number to be coded, wherein n ^ m is larger than the number to be coded.
According to another aspect of the present invention, there is also provided a two-dimensional texture code decoding method, which is applicable to the two-dimensional texture code, and includes the following steps:
positioning the two-dimensional texture code;
detecting the L-shaped format correction area, and correcting the two-dimensional texture code to a standard direction by using the L-shaped format correction area;
classifying texture pictures of each sub-region of the two-dimensional texture code after correction, and obtaining decoding results according to decoding characters corresponding to the types of the texture pictures respectively.
Preferably, the two-dimensional texture code is located using a method such as DenseNet, FPN, or fasternn.
Compared with the prior art, the invention has the following beneficial effects:
the two-dimensional texture code and the coding and decoding methods thereof can effectively reduce the information redundancy of the two-dimensional code and improve the decoding robustness under low pixels.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a two-dimensional texture code according to an embodiment of the present invention;
FIG. 2 shows 10 types of textures and their corresponding decoded characters according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of format correction according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a two-dimensional texture code decoding method according to an embodiment of the present invention;
fig. 5 is a process of deep learning by the texture image classifier according to an embodiment of the invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the spirit of the invention. All falling within the scope of the present invention.
Fig. 1 is a two-dimensional texture code according to an embodiment of the invention, and as shown in fig. 1, the two-dimensional texture code according to an embodiment of the invention is composed of two parts, one part is an L-shaped format correction area for correcting the format of the two-dimensional texture code, and the other part is a texture data area.
The texture data area is a rectangular area and is divided into m rectangular sub-areas.
In a preferred embodiment of the present invention, as shown in fig. 1, m is 4, that is, the texture data area is divided into 4 rectangular sub-areas.
Each sub-region is occupied by a texture picture, and the sub-regions have n types of textures, each type of texture corresponds to a decoding character, and n > m.
In a preferred embodiment of the invention, n-10, i.e. there are 10 different types of textures.
Fig. 2 shows 10 types of textures and their corresponding decoded characters according to an embodiment of the present invention, and as shown in fig. 2, the 10 different types of textures of the present embodiment correspond to decoded characters 1 to 10, respectively.
In an embodiment, the L-shaped format correction area is completely black, and is used for correcting the format of the two-dimensional texture code, and correcting the two-dimensional texture code to a standard direction and shape.
If there is no format correction area, the direction of the texture data area can be arbitrarily rotated, and the sequence of each sub-area cannot be positioned, so that the decoding result is not unique.
Fig. 3 is a schematic diagram of format correction according to an embodiment of the present invention, as shown in fig. 3, in this embodiment, a texture data region may be located by format correction, wherein a sub-region 3 is defined by a right angle of an L shape, so as to determine the remaining sub-regions 1, 2, and 4. By utilizing the positioning point information of the L-shaped format correction area, the two-dimensional texture code can be corrected to the standard direction and shape by adopting perspective transformation.
For any two-dimensional texture code, after the format correction area is corrected, a four-digit decimal result can be obtained by decoding through a decoder, and the decoding result of the two-dimensional texture code is 8694 as shown in fig. 1.
In other embodiments of the present invention, other correction methods may also be used to correct the two-dimensional texture code to a standard direction and shape, which is not limited by the present invention.
In the present embodiment, the texture data area is divided into 4 sub-areas, and 10 texture patterns are used, but in other embodiments of the present invention, the number of sub-areas and the number of types of texture patterns are not limited, and the texture patterns are not fixed and can be adjusted or reselected according to actual situations.
It can be calculated that the data capacity of the two-dimensional texture code of the present embodiment, which includes 4 sub-regions and 10 texture patterns, is 10^ 4.
In practical cases, if the data capacity needs to be enlarged or reduced, the number of the sub-regions or the type of the texture pattern needs to be increased or decreased accordingly. The specific data capacity can be obtained by the following formula:
c＝n^m (1)
where n is the number of texture picture types and m is the number of sub-regions in the texture data region.
To achieve better results, we need to balance the proportional size of the texture data region and the format correction region. If the proportion of the correction area is too large, the decoding of the texture is influenced; if the size of the format correction area is too small, correction is not easy.
In a preferred embodiment, the pixels of the single texture picture are set to 200 pixels, and the width of the format correction region is set to 25 pixels, so that the requirements of decoding and correction can be met simultaneously.
Compared with the prior art, the method can effectively reduce the information redundancy of the two-dimensional code, improves the robustness under low pixels, and is suitable for application scenes which only have limited categories and do not need high-capacity storage in a system.
The invention further provides a two-dimensional texture code encoding method, which is used for the two-dimensional texture code, and in one embodiment of the invention, the two-dimensional texture code encoding method comprises the following steps: determining a number to be encoded; and filling the numbers to be coded into each sub-area according to the texture picture type corresponding to the decoded character.
In this embodiment, the encoding portion of the patent requires the input of four digits to be encoded, ranging from 0000 to 9999 for a total of ten thousand. And according to the input number to be coded, the texture picture passes through the format and forms a final two-dimensional texture code together with the format correction area.
In another embodiment, a process of determining a data capacity may also be included: determining the m and n according to the number to be encoded, wherein n ^ m is larger than the number to be encoded.
The present invention further provides a two-dimensional texture code decoding method, which is used for the two-dimensional texture code, and fig. 4 is a flowchart of the two-dimensional texture code decoding method according to an embodiment of the present invention, and as shown in fig. 4, the method includes the following steps:
and S01, positioning the two-dimensional texture code.
In one embodiment, existing object location techniques, such as DenseNet, FPN, FasterRCNN methods, etc., may be employed for location.
The texture code of the embodiment of the invention has obvious texture information and is easier to position compared with the traditional two-dimensional code.
And S02, detecting the L-shaped format correction area, and correcting the two-dimensional texture code to a standard direction and a standard shape by using the L-shaped format correction area.
In one embodiment, the two-dimensional texture code can be corrected to the standard direction and shape by using a perspective transformation and using positioning point information of the L-shaped correctors by using Hough transformation and threshold detection.
And S03, classifying the texture pictures of each sub-region of the two-dimensional texture code after correction, and obtaining decoding results according to decoding characters corresponding to the types of the texture pictures respectively.
In an embodiment, the texture picture of the two-dimensional texture code after rectification can be classified and decoded by using a deep learning technique.
Specifically, the two-dimensional texture codes of the classifier team which is subjected to deep classification learning can be adopted for classification in the decoding process, and the accuracy and the adaptability of classification can be improved.
In a preferred embodiment, in order to keep the classifier highly accurate and adaptable, the training data may be enhanced during the training process, introducing situations that may be encountered in real situations. Since it is not applicable in practical environment if only the original texture picture is used for training. When the two-dimensional texture code is printed and pasted in a real environment, the two-dimensional texture code can be influenced by nonuniform care, JPEG (joint photographic experts group) compression, geometric distortion and the like. These effects tend to affect the accuracy of deep learning based classifiers.
Fig. 5 is a process of performing deep learning by the texture image classifier according to an embodiment of the invention, and as shown in fig. 5, the deep learning includes the following steps: generating a random number; encoding the random number; generating a two-dimensional texture code; performing data enhancement on the two-dimensional texture code; generating a decoding result; and comparing the decoding result with the random number, and training the classifier.
Compared with the existing two-dimensional code encoding and decoding methods, the embodiment of the invention can effectively reduce the information redundancy of the two-dimensional code, can rapidly and simply encode, and can improve the decoding robustness under low-pixel and complex environments.
The technical features in the embodiments described above may be operated with reference to the embodiments described above, or may be arbitrarily combined according to actual needs, and for brevity of description, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as the scope of the present description as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (7)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911035069.7A CN110866578B (en) | 2019-10-29 | 2019-10-29 | A two-dimensional texture code and its encoding and decoding method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911035069.7A CN110866578B (en) | 2019-10-29 | 2019-10-29 | A two-dimensional texture code and its encoding and decoding method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110866578A CN110866578A (en) | 2020-03-06 |
| CN110866578B true CN110866578B (en) | 2021-07-06 |
Family
ID=69654743
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911035069.7A Active CN110866578B (en) | 2019-10-29 | 2019-10-29 | A two-dimensional texture code and its encoding and decoding method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110866578B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102419823A (en) * | 2010-09-27 | 2012-04-18 | 吴罡 | Digit graphic code |
| CN106485183A (en) * | 2016-07-14 | 2017-03-08 | 深圳市华汉伟业科技有限公司 | A kind of Quick Response Code localization method and system |
| CN106796662A (en) * | 2014-08-06 | 2017-05-31 | 伟德电脑织唛厂有限公司 | Authentication device |
| CN107491801A (en) * | 2017-07-13 | 2017-12-19 | 海南亚元防伪技术研究所（普通合伙） | The endowed method and system of artificial intelligence |
| CN108399637A (en) * | 2018-02-02 | 2018-08-14 | 上海巨幸机器人科技有限公司 | A kind of coordinate method encoded with pattern |
| CN108959949A (en) * | 2018-08-16 | 2018-12-07 | 北京奇虎科技有限公司 | A kind of method and system for the information transmitting carrying out safety by encoding of graphs data |
| CN109739237A (en) * | 2019-01-09 | 2019-05-10 | 华南理工大学 | A AGV visual navigation and positioning method based on a new coding mark |
| CN110348554A (en) * | 2019-07-17 | 2019-10-18 | 北京迈格威科技有限公司 | Digital information decoding method, device, electronic equipment and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096795B (en) * | 2010-11-25 | 2014-09-10 | 西北工业大学 | Method for recognizing worn two-dimensional barcode image |
| CN202495205U (en) * | 2012-03-07 | 2012-10-17 | 海南亚元防伪技术研究所 | Error discoloration internet-of-things anti-counterfeiting gold stamping identifier |
| EP2849121B1 (en) * | 2013-09-11 | 2018-05-02 | Roman Plöckl | Package marking and method for marking a package and verification of a packaged product |
-
2019
- 2019-10-29 CN CN201911035069.7A patent/CN110866578B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102419823A (en) * | 2010-09-27 | 2012-04-18 | 吴罡 | Digit graphic code |
| CN106796662A (en) * | 2014-08-06 | 2017-05-31 | 伟德电脑织唛厂有限公司 | Authentication device |
| CN106485183A (en) * | 2016-07-14 | 2017-03-08 | 深圳市华汉伟业科技有限公司 | A kind of Quick Response Code localization method and system |
| CN107491801A (en) * | 2017-07-13 | 2017-12-19 | 海南亚元防伪技术研究所（普通合伙） | The endowed method and system of artificial intelligence |
| CN108399637A (en) * | 2018-02-02 | 2018-08-14 | 上海巨幸机器人科技有限公司 | A kind of coordinate method encoded with pattern |
| CN108959949A (en) * | 2018-08-16 | 2018-12-07 | 北京奇虎科技有限公司 | A kind of method and system for the information transmitting carrying out safety by encoding of graphs data |
| CN109739237A (en) * | 2019-01-09 | 2019-05-10 | 华南理工大学 | A AGV visual navigation and positioning method based on a new coding mark |
| CN110348554A (en) * | 2019-07-17 | 2019-10-18 | 北京迈格威科技有限公司 | Digital information decoding method, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110866578A (en) | 2020-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR100525694B1 (en) | System and method for user authentication | |
| US9406010B2 (en) | Producing, capturing and using visual identification tags for moving objects | |
| US7702162B2 (en) | Mixed code, and method and apparatus for generating the same | |
| US11216631B2 (en) | Contrast edge barcodes | |
| US20150339838A1 (en) | Image mask providing a machine-readable data matrix code | |
| US7751585B2 (en) | System and method for encoding high density geometric symbol set | |
| CN105989317B (en) | A two-dimensional code identification method and device | |
| CN106778996A (en) | It is embedded with the generation system and method and reading system of the Quick Response Code of visual pattern | |
| CN110765795B (en) | Two-dimensional code identification method and device and electronic equipment | |
| US20150090795A1 (en) | Method and system for detecting detection patterns of qr code | |
| WO2021143212A1 (en) | Quick response code, quick response code encoding method and apparatus, quick response code decoding method and apparatus, and electronic system | |
| CN111291846B (en) | Two-dimensional code generation, decoding and identification method, device and equipment | |
| CN115660933B (en) | Watermark information identification method, device and equipment | |
| CN104992207A (en) | Mobile phone two-dimensional bar code coding and decoding method | |
| Yaldiz et al. | Deepformabletag: end-to-end generation and recognition of deformable fiducial markers | |
| CN113553876A (en) | Bar code identification method, device, equipment and storage medium | |
| CN110866578B (en) | A two-dimensional texture code and its encoding and decoding method | |
| CN104346596A (en) | Identification method and identification device for QR (Quick Response) code | |
| CN112187284B (en) | Coding method, coding pattern, coding pattern reading method and shooting device | |
| CN109635613B (en) | Two-dimensional code generation method, system and device for sphere surface | |
| CN115527197B (en) | Vehicle number identification method and device, computer equipment and truck | |
| CN113780028B (en) | Verification method and device for novel three-dimensional code combined with picture | |
| Mishra | Region Identification and Decoding Of Security Markers Using Image Processing Tools | |
| Li et al. | Aesthetic QR Code Authentication Based on Directed Periodic Texture Pattern | |
| CN115984891A (en) | Bill recognition apparatus and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |