WO2018107574A1 - 一种对印防伪特征的检测方法及装置 - Google Patents
一种对印防伪特征的检测方法及装置 Download PDFInfo
- Publication number
- WO2018107574A1 WO2018107574A1 PCT/CN2017/073054 CN2017073054W WO2018107574A1 WO 2018107574 A1 WO2018107574 A1 WO 2018107574A1 CN 2017073054 W CN2017073054 W CN 2017073054W WO 2018107574 A1 WO2018107574 A1 WO 2018107574A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- counterfeiting
- feature
- detected
- generate
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000001514 detection method Methods 0.000 claims abstract description 61
- 230000009466 transformation Effects 0.000 claims abstract description 10
- 238000000605 extraction Methods 0.000 claims description 18
- 230000004927 fusion Effects 0.000 claims description 18
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 2
- 230000000717 retained effect Effects 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 abstract description 8
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000002441 reversible effect Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 101100070244 Mus musculus Hcn3 gene Proteins 0.000 description 4
- 101100102805 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) VPS36 gene Proteins 0.000 description 4
- 230000006870 function Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000000295 complement effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000001968 nicotinic acid Nutrition 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Definitions
- the invention relates to the technical field of anti-counterfeiting detection, in particular to a method and a device for detecting anti-counterfeiting features.
- the anti-counterfeiting technology mainly divides a complete anti-counterfeiting pattern into several sub-areas, some sub-areas are printed on the front side of the banknote, and some sub-areas are printed on the reverse side of the banknote, and the joints of the front and back sub-areas are neither broken and white.
- the bits overlap and the sub-areas combine to form a complete anti-counterfeiting pattern.
- Multinational currencies have the characteristics of anti-counterfeiting, such as the Hong Kong government's 10 yuan plastic coins, the euro's denomination of digital prints, the renminbi 99 version, the 05 version of the yin and yang complementary ancient coins on the printed pattern, the renminbi 15 version of the denomination digital pattern.
- This type of anti-counterfeiting feature belongs to the public security feature. Under normal circumstances, the anti-counterfeiting judgment can be performed by the human eye without using professional equipment and instruments. The viewing method is to observe the integrity of the printed pattern by the human eye, and to check whether the image overlaps or not.
- the existing printing detection methods generally use visible light transmission image sensor and visible light reflection image sensor for image acquisition, and use image stitching and other techniques to complete the visible light reflection image stitching, and the visible light reflection prints the visible image and the visible light.
- the images are matched to achieve detection of the security feature.
- an additional visible light transmission sensor is needed, and the visible light transmission sensor has no outstanding anti-counterfeiting capability for the remaining anti-counterfeiting features, and the image splicing technique in the scheme often adopts a complex algorithm such as a checkpoint detection to process data of the device. The requirements are higher.
- the object of the present invention is to provide a method and a device for detecting an anti-counterfeiting feature, without setting
- the visible light transmission sensor can realize the detection of the anti-counterfeiting feature, reduce the equipment cost, and reduce the performance requirements of the digital signal processor.
- the present invention provides a method for detecting an anti-counterfeiting feature, comprising:
- the fused security feature image is matched with the standard security feature image in the pre-stored template, and the authenticity of the object to be detected is determined according to the matching result.
- the extracting the anti-counterfeiting feature information of the first detected image, and generating the first anti-counterfeiting feature image includes:
- Feature extraction is performed on the first pair of printed anti-counterfeiting areas to generate a first anti-counterfeiting feature image.
- the extracting the anti-counterfeiting feature information of the second detected image and performing mirror image transformation to generate the second anti-counterfeiting feature image includes:
- the merging the first security feature image and the second security feature image to generate the fused security feature image includes:
- the pixel values of the pixels at the same position of the processed image are respectively subjected to a large operation to generate a fused security feature image.
- performing the binarization processing on the first anti-counterfeiting feature image and the second anti-counterfeiting feature image includes:
- a pixel value of a pixel point higher than the binarization threshold is set to 0, and pixel values of the remaining pixel points are retained as original values.
- the method before the matching the anti-counterfeit feature image in the pre-existing template with the standard anti-counterfeit feature image, and determining the authenticity of the object to be detected according to the matching result, the method further includes:
- the matching the anti-counterfeit feature image with the standard anti-counterfeit feature image in the pre-stored template, and determining the authenticity of the object to be detected according to the matching result includes:
- the method further includes:
- the invention also provides a detecting device for printing anti-counterfeiting features, comprising:
- An image acquisition module configured to acquire a first detection image and a second detection image of the object to be detected, where the first detection image and the second detection image are front and back images respectively corresponding to the anti-counterfeiting area;
- a first extraction module configured to extract anti-counterfeiting feature information of the first detected image, and generate a first anti-counterfeiting feature image
- a second extraction module configured to extract the anti-counterfeiting feature information of the second detected image and perform image conversion to generate a second anti-counterfeiting feature image
- a fusion module configured to fuse the first security feature image and the second security feature image to generate a fusion security feature image
- the detecting module is configured to match the merged anti-counterfeiting feature image with the standard anti-counterfeiting feature image in the pre-stored template, and determine the authenticity of the object to be detected according to the matching result.
- the method and device for detecting the anti-counterfeiting feature acquires the anti-counterfeiting feature information of the first detected image by acquiring the first detected image and the second detected image of the object to be detected, and generates a first anti-counterfeiting feature image; Secondly, detecting the anti-counterfeiting feature information of the image and performing mirror image transformation to generate a second anti-counterfeiting feature image; fusing the first anti-counterfeiting feature image and the second anti-counterfeiting feature image to generate a fusion anti-counterfeiting feature image; and integrating the anti-counterfeiting feature image with the pre-stored feature image
- the standard anti-counterfeiting feature images are matched, and the authenticity of the object to be detected is judged according to the matching result.
- the application only needs to collect the visible light reflection images on the front and back sides, and does not need to collect the visible light transmission images.
- the cost of the equipment is effectively reduced, and the complicated algorithm in the image mosaic technology is not needed. Reduced performance requirements for digital signal processors.
- FIG. 1 is a flow chart of a specific implementation manner of a method for detecting an anti-counterfeiting feature provided by the present invention
- FIG. 2 is a flowchart of extracting anti-counterfeiting feature information of a first detected image according to an embodiment of the present invention
- FIG. 3 is a flowchart of a specific implementation manner of extracting anti-counterfeiting feature information of a second detected image according to an embodiment of the present invention
- FIG. 4 is a flow chart of another specific implementation manner of a method for detecting an anti-counterfeiting feature provided by the present invention.
- FIG. 5 is still another specific implementation method of the method for detecting the anti-counterfeiting feature provided by the present invention.
- FIG. 6 is a schematic view showing the position of a front side printing area in the method for detecting the anti-counterfeiting feature provided by the present invention
- FIG. 7 is a schematic diagram showing the position of a counter-printing area of a genuine banknote in a method for detecting an anti-counterfeiting feature provided by the present invention
- FIG. 8 is a schematic diagram showing the position of a counterfeit banknote in the detection method of the anti-counterfeiting feature provided by the present invention.
- FIG. 9 is a schematic view showing the fusion of the front side printing area and the reverse facing printing area of the genuine banknote in the method for detecting the anti-counterfeiting feature provided by the present invention.
- FIG. 10 is a schematic view showing the fusion of the front printing area and the reverse facing area of the counterfeit banknote in the method for detecting the anti-counterfeiting feature provided by the present invention
- FIG. 11 is a structural block diagram of a device for detecting an anti-counterfeiting feature according to an embodiment of the present invention.
- FIG. 1 A flowchart of a specific implementation manner of a method for detecting an anti-counterfeiting feature provided by the present invention is shown in FIG. 1 , and the method includes:
- Step S101 Acquire a first detection image of the object to be detected and a second detection image, where the first detection image and the second detection image are front and back images respectively corresponding to the anti-counterfeiting area;
- the CIS sensor may be used to collect the front and back visible light reflection images of the printed anti-counterfeit logo pattern to generate a first detection image and a second detection image.
- Step S102 Extracting the anti-counterfeiting feature information of the first detected image to generate a first anti-counterfeiting feature image
- the process of extracting the anti-counterfeiting feature information of the first detected image in the embodiment may specifically include:
- Step S1021 Acquire version information of the object to be detected, and determine first position information of the anti-counterfeiting area in the first detection image according to the version information;
- Step S1022 Searching the first detected image by using a projection and a sliding window search manner according to the first position information, and determining a first pair of printed anti-counterfeiting areas;
- Step S1023 Perform feature extraction on the first pair of printed anti-counterfeiting areas to generate a first anti-counterfeiting feature image.
- the pre-stored template information is searched in the database, and the first location information of the anti-counterfeiting area in the first detected image is determined.
- the projection and the sliding window search mode are used for searching, and the first pair of printed anti-counterfeiting areas are marked, and the area is subjected to feature extraction to obtain a first anti-counterfeiting feature image.
- Step S103 Extracting the anti-counterfeiting feature information of the second detected image and performing image conversion to generate a second anti-counterfeiting feature image;
- FIG. 3 A specific implementation manner of generating a second anti-counterfeiting feature image provided in this embodiment is as shown in FIG. 3, and specifically includes:
- Step S1131 Determine, according to the first location information, coordinate information, and determine second location information of the anti-counterfeiting area in the second detected image;
- Step S1132 Perform feature extraction on the second pair of printed anti-counterfeiting areas in the second detected image and perform image conversion to generate a second anti-counterfeiting feature image.
- the position information of the second pair of printed anti-counterfeiting areas corresponding to the first position information may be acquired, and the second pair of printed anti-counterfeiting areas are extracted according to the position information, and the image is transformed.
- a second security feature image is generated.
- the step S103 needs to be performed after the step S102 is executed, and the first location information is acquired.
- Step S104 merging the first anti-counterfeiting feature image and the second anti-counterfeiting feature image to generate a fused anti-counterfeiting feature image;
- the process of the fusion may be specifically: performing binarization processing on the first security feature image and the second security feature image; and performing a large operation on the pixel values of the pixel positions at the same position of the processed image to generate a large operation Incorporate anti-counterfeiting feature images.
- Step S105 Match the merged anti-counterfeiting feature image with the standard anti-counterfeiting feature image in the pre-stored template, and determine the authenticity of the object to be detected according to the matching result.
- Calculating a correlation coefficient between the fusion security feature image and the standard security feature image comparing the correlation coefficient with a preset threshold, and determining the to-be-detected when the correlation coefficient is greater than or equal to the preset threshold The object is true; when the correlation coefficient is less than the preset threshold, it is determined that the object to be detected is false.
- the method for detecting the anti-counterfeiting feature obtains the first anti-counterfeiting feature information of the first detected image by acquiring the first detected image and the second detected image of the object to be detected, and generates a first anti-counterfeiting feature image;
- the anti-counterfeiting feature information of the image is mirror-transformed to generate a second anti-counterfeiting feature image;
- the first anti-counterfeiting feature image and the second anti-counterfeiting feature image are fused to generate a fused anti-counterfeiting feature image;
- the fused anti-counterfeiting feature image and the standard anti-counterfeiting feature in the pre-stored template The feature image is matched, and the authenticity of the object to be detected is determined according to the matching result.
- the application only needs to collect the visible light reflection images on the front and back sides, and does not need to collect the visible light transmission images.
- the cost of the equipment is effectively reduced, and the complicated algorithm in the image mosaic technology is not needed. Reduced performance requirements for digital signal processors.
- the object to be detected may be specifically a banknote, such as 100 yuan.
- the first detection image and the second detection image respectively correspond to the front side and the back side of the banknote.
- the first detected image is taken as the front image of the banknote as an example.
- the process of detecting the security features of the banknotes is further elaborated.
- FIG. 4 A flow chart of another specific implementation manner of the method for detecting the anti-counterfeiting feature provided by the present invention is as shown in FIG. 4, and specifically includes:
- Step S201 Perform image acquisition on the front side and the back side of the banknote to generate a front side detection image and a reverse side detection image.
- the front and back visible light reflection image acquisition is performed by using the CIS sensor, and the front image I A and the reverse image I B are obtained , and I(i, j) is the pixel value of the pixel point (i, j).
- Step S202 Acquire version information including a face value of the banknote, and retrieve location information of the front side print image in the pre-existing database according to the version information;
- Application vector Indicates the position of a version of the front image to the print search area, where x is the abscissa of the search area, y is the ordinate of the search area, ⁇ x is the width of the search area, and ⁇ y is the height of the search area;
- Step S203 applying a projection and sliding window search mode to the front-to-back image search area to complete the front-to-back image search, realizing the image registration, marking the front image position information, and performing front-side printing image extraction according to the position information;
- the window size ⁇ y 1 is the height information of the printed image, pre-stored in the storage module, when i satisfies the following conditions
- the window size ⁇ x 1 is the width information of the printed image, pre-existing in the storage module when i satisfies the following conditions
- Step S204 performing coordinate transformation according to position information of the front side printed image, acquiring position information of the reverse facing area corresponding to the front position information of the printed image, performing image extraction of the reverse facing area according to the position information, and performing mirror image conversion;
- w is the width information of the banknote, and the area is mirror-transformed horizontally to obtain a mirror image of the anti-printing area:
- Step S205 Binarize the front side print image, set the image pixel higher than the binarization threshold to 0, and retain the remaining pixels, normalize the non-zero pixels, and adopt the same processing in the opposite printing area;
- the binarization method is used to process the front-to-print area image I A1 to obtain a binarization threshold T A1 .
- [g 0 , g 0 + g 1 ] is the stretching range of the image stretching
- the binarization method is used to process the anti-printing area image I C1 to obtain a binarization threshold T C1 .
- Step S206 The pixels of the same position of the two images that are segmented and normalized by the threshold are subjected to a large operation to form a fused image;
- Step S207 Matching the normalized fused image with the pre-stored template, and determining that the banknote is true when the matching output result reaches a preset threshold.
- Transverse projection template matching correlation coefficient calculation first obtain lateral projection data
- [f 0 , f 0 + f 1 ] is a stretching range in which the projection data is stretched
- the lateral projection template f VAC3 pre-existing in the storage module is retrieved , and the correlation coefficient calculation of the template matching is performed.
- the horizontal projection template f HAC3 pre-existing in the storage module is retrieved , and the correlation coefficient calculation of the template matching is performed.
- pre-storage template is generated in a manner similar to steps S201-S206, and is collected for standard banknotes, and is pre-stored in the storage module.
- the banknote size information of the pre-stored template can be pre-stored in the database, and the size of the sliding area of the search area and the image to be printed can be converted according to the size and pre-stored size of the input banknote, and the fused image is obtained when the template matching step is performed.
- the feature and the length information of the pre-stored template are subjected to interpolation and normalization, and then the matching is performed.
- FIG. 5 a schematic diagram of still another specific embodiment of the present invention is shown. The detailed operation steps are as follows;
- the pre-stored template information corresponds to the banknote size information of the template information, and the pre-stored banknote image has a width W, a banknote height H, and a front search area.
- the CIS sensor is used to complete the front and back visible light reflection image acquisition, and the front image I A and the reverse image I B are obtained , and I(i, j) is the pixel value of the pixel point (i, j).
- the front side print image is binarized, the image pixels higher than the binarization threshold are set to 0, the remaining pixels are reserved, and the non-zero pixels are normalized, and the opposite processing is performed in the opposite printing area;
- the binarization method is used to process the front-to-print area image I A1 to obtain a binarization threshold T A1 .
- the binarization method is used to process the anti-printing area mirror image I C1 to obtain a binarization threshold T C1 .
- the pixels of the same position of the two images are enlarged to form a fused image, and the normalization of the image size is completed;
- the normalized fused image is matched with the pre-stored template, and the matching output result reaches a preset threshold to determine that the banknote is true.
- Transverse projection template matching correlation coefficient calculation first obtain lateral projection data
- the length of the template is normalized, and the horizontal projection data E VAC3 of the fused image is interpolated, and the data length interpolation is consistent with the length of the horizontal projection data template f VAC3 , and the projection data after the interpolation is F VAC3 .
- the length of the template is normalized, and the longitudinal projection data E HAC3 of the fused image is interpolated, and the data length interpolation is consistent with the length of the longitudinal projection data template f HAC3 , and the projection data after the interpolation is F HAC3 .
- FIG. 6 is a schematic view showing the position of a front side printing area in the method for detecting the printed security feature provided by the present invention
- FIG. 7 is a view showing the position of the genuine banknote reverse facing printing area in the method for detecting the printed security feature provided by the present invention
- FIG. 8 is a schematic view showing the position of the counterfeit banknote printing area in the method for detecting the printed security feature provided by the present invention
- FIG. 9 is a view showing the true banknote in the method for detecting the printed security feature provided by the present invention.
- FIG. 10 is a schematic view showing the fusion of the front side printing area and the reverse facing area of the counterfeit banknote in the method for detecting the printed security feature provided by the present invention. It can be seen that the present invention can realize the identification of the authenticity of the banknote without using the visible light projection sensor and the image splicing technology.
- the device for detecting the anti-counterfeiting feature provided by the embodiment of the present invention is described below.
- the detecting device for the anti-counterfeiting feature described below and the detecting method for the anti-counterfeiting feature described above can be referred to each other.
- FIG. 11 is a structural block diagram of a device for detecting an anti-counterfeiting feature according to an embodiment of the present invention.
- the image acquisition module 100 is configured to acquire a first detection image and a second detection image of the object to be detected, where the first detection image and the second detection image are front and back images respectively corresponding to the anti-counterfeiting area;
- the first extraction module 200 is configured to extract the anti-counterfeiting feature information of the first detected image to generate a first anti-counterfeiting feature image
- the second extraction module 300 is configured to extract the anti-counterfeiting feature information of the second detected image and perform image conversion to generate a second anti-counterfeiting feature image;
- the fusion module 400 is configured to fuse the first security feature image and the second security feature image to generate a fusion security feature image
- the detecting module 500 is configured to match the merged anti-counterfeiting feature image with the standard anti-counterfeiting feature image in the pre-stored template, and determine the authenticity of the object to be detected according to the matching result.
- the detecting device for the anti-counterfeiting feature of the present embodiment is used to implement the foregoing method for detecting the anti-counterfeiting feature. Therefore, the specific embodiment of detecting the anti-counterfeiting feature can be seen as an embodiment of the method for detecting the anti-counterfeiting feature in the foregoing.
- the image acquisition module 100, the first extraction module 200, the second extraction module 300, the fusion module 400, and the detection module 500 are respectively used to implement the above-mentioned method for detecting the anti-counterfeiting feature in steps S101, S102, S103, and S104. And S105, so the specific implementation manners can refer to the description of the respective partial embodiments, and details are not described herein again.
- the device for detecting the anti-counterfeiting feature obtains the first anti-counterfeiting feature information of the first detected image by acquiring the first detected image and the second detected image of the object to be detected, and generates a first anti-counterfeiting feature image;
- the anti-counterfeiting feature information of the image is mirror-transformed to generate a second anti-counterfeiting feature image;
- the first anti-counterfeiting feature image and the second anti-counterfeiting feature image are fused to generate a fused anti-counterfeiting feature image;
- the fused anti-counterfeiting feature image and the standard anti-counterfeiting feature in the pre-stored template The feature image is matched, and the authenticity of the object to be detected is determined according to the matching result.
- the application only needs to collect the visible light reflection images on the front and back sides, and does not need to collect the visible light transmission images.
- the cost of the equipment is effectively reduced, and the complicated algorithm in the image mosaic technology is not needed. Reduced performance requirements for digital signal processors.
- the steps of a method or algorithm described in connection with the embodiments disclosed herein can be implemented directly in hardware, a software module executed by a processor, or a combination of both.
- the software module can be placed in random access memory (RAM), memory, read only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or technical field. Any other form of storage medium known.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
一种对印防伪特征的检测方法及装置，该方法通过获取待检测物体的第一检测图像以及第二检测图像，提取第一检测图像的防伪特征信息，生成第一防伪特征图像；提取第二检测图像的防伪特征信息并进行镜像变换，生成第二防伪特征图像；将第一防伪特征图像以及第二防伪特征图像进行融合，生成融合防伪特征图像；将融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断待检测物体的真伪。本申请只需进行正反面可见光反射图像的采集，无需进行可见光透射图像的采集，在保障对印检测防伪性能的情况下，有效降低了设备的成本，并且无需采用图像拼接技术中的复杂算法，降低了对数字信号处理器的性能要求。
Description
本申请要求于2016年12月16日提交中国专利局、申请号为201611168869.2、发明名称为“一种对印防伪特征的检测方法及装置“的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
本发明涉及防伪检测技术领域，特别是涉及一种对印防伪特征的检测方法及装置。
对印防伪技术主要是将一个完整的防伪图案分割为若干个子区域，部分子区域印刷在钞票的正面，部分子区域印刷在钞票的反面，正面反面各子区域连接处既不断裂留白又不错位交叠，各子区域组合形成完整防伪图案。
多国货币具备对印防伪特征，例如香港政府10元塑料币的奔马图案，欧元的面额数字对印图案，人民币99版、05版阴阳互补古钱币对印图案，人民币15版面额数字图案等。该类型防伪特征属于公众防伪特征，在一般情况下无需借助专业设备仪器通过人眼即可进行防伪判断，查看方法为人眼迎光观察对印图案的完整性，查看图像有无错位交叠等。
从仿生学角度出发，现有的对印检测方法一般采用可见光透射图像传感器和可见光反射图像传感器进行图像采集，采用图像拼接等技术完成可见光反射图像拼接，将可见光反射对印图像与可见光透射对印图像进行匹配，实现该防伪特征的检测。这种防伪检测方案中，需要额外设置可见光透射传感器，而可见光透射传感器对于其余防伪特征没有突出的防伪能力，且该方案中的图像拼接技术往往采用校点检测等复杂算法，对设备数据处理能力要求较高。
发明内容
本发明的目的是提供一种对印防伪特征的检测方法及装置，无需设置
可见光透射传感器即可实现对印防伪特征检测，降低了设备成本，同时降低了对数字信号处理器的性能要求。
为解决上述技术问题，本发明提供一种对印防伪特征的检测方法，包括：
获取待检测物体的第一检测图像以及第二检测图像，所述第一检测图像以及所述第二检测图像为分别与对印防伪区域相对应的正反面图像；
提取所述第一检测图像的防伪特征信息，生成第一防伪特征图像；
提取所述第二检测图像的防伪特征信息并进行镜像变换，生成第二防伪特征图像；
将所述第一防伪特征图像以及所述第二防伪特征图像进行融合，生成融合防伪特征图像；
将所述融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断所述待检测物体的真伪。
可选地，所述提取所述第一检测图像的防伪特征信息，生成第一防伪特征图像包括：
获取所述待检测物体的版本信息，根据所述版本信息确定所述第一检测图像中对印防伪区域的第一位置信息；
根据所述第一位置信息，采用投影以及滑动窗搜索方式对所述第一检测图像进行搜索，确定第一对印防伪区域；
对所述第一对印防伪区域进行特征提取，生成第一防伪特征图像。
可选地，所述提取所述第二检测图像的防伪特征信息并进行镜像变换，生成第二防伪特征图像包括：
根据所述第一位置信息，进行坐标变换后确定所述第二检测图像中对印防伪区域的第二位置信息；
对所述第二检测图像中的第二对印防伪区域进行特征提取并进行镜像变换，生成第二防伪特征图像。
可选地，所述将所述第一防伪特征图像以及所述第二防伪特征图像进行融合，生成融合防伪特征图像包括：
将所述第一防伪特征图像以及所述第二防伪特征图像进行二值化处
理；
对处理后的图像相同位置的像素点的像素值分别进行取大的运算，生成融合防伪特征图像。
可选地，所述将所述第一防伪特征图像以及所述第二防伪特征图像进行二值化处理包括：
采用阈值分割法确定所述第一防伪特征图像以及所述第二防伪特征图像的二值化阈值；
将高于所述二值化阈值的像素点的像素值置为0，其余像素点的像素值保留原值。
可选地，在所述将所述融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断所述待检测物体的真伪之前还包括：
对所述融合防伪特征图像中的各像素点的像素值进行归一化处理。
可选地，所述将所述融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断所述待检测物体的真伪包括：
计算所述融合防伪特征图像与所述标准防伪特征图像的相关系数；
将所述相关系数与预设阈值进行比较，当所述相关系数大于或等于所述预设阈值时，判定所述待检测物体为真；当所述相关系数小于所述预设阈值时，判定所述待检测物体为假。
可选地，在获取待检测物体的第一检测图像以及第二检测图像之后还包括：
将所述第一检测图像、所述第二检测图像的尺寸大小与所述预存模板中的标准物体的尺寸大小进行对比，确定图像的拉伸系数；
根据所述拉伸系数对各图像中对应的坐标进行校正。
本发明还提供了一种对印防伪特征的检测装置，包括：
图像获取模块，用于获取待检测物体的第一检测图像以及第二检测图像，所述第一检测图像以及所述第二检测图像为分别与对印防伪区域相对应的正反面图像；
第一提取模块，用于提取所述第一检测图像的防伪特征信息，生成第一防伪特征图像；
第二提取模块，用于提取所述第二检测图像的防伪特征信息并进行镜像变换，生成第二防伪特征图像；
融合模块，用于将所述第一防伪特征图像以及所述第二防伪特征图像进行融合，生成融合防伪特征图像；
检测模块，用于将所述融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断所述待检测物体的真伪。
本发明所提供的对印防伪特征的检测方法及装置，通过获取待检测物体的第一检测图像以及第二检测图像，提取第一检测图像的防伪特征信息，生成第一防伪特征图像；提取第二检测图像的防伪特征信息并进行镜像变换，生成第二防伪特征图像；将第一防伪特征图像以及第二防伪特征图像进行融合，生成融合防伪特征图像；将融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断待检测物体的真伪。本申请只需进行正反面可见光反射图像的采集，无需进行可见光透射图像的采集，在保障对印检测防伪性能的情况下，有效降低了设备的成本，并且无需采用图像拼接技术中的复杂算法，降低了对数字信号处理器的性能要求。
为了更清楚的说明本发明实施例或现有技术的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单的介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本发明所提供的对印防伪特征的检测方法的一种具体实施方式的流程图；
图2为本发明实施例中提取第一检测图像的防伪特征信息的流程图；
图3为本发明实施例中提取第二检测图像的防伪特征信息的一种具体实施方式流程图；
图4为本发明所提供的对印防伪特征的检测方法的另一种具体实施方式流程图；
图5为本发明所提供的对印防伪特征的检测方法的又一种具体实施方
式示意图；
图6为本发明所提供的对印防伪特征的检测方法中正面对印区域位置示意图；
图7为本发明所提供的对印防伪特征的检测方法中真钞反面对印区域位置示意图；
图8为本发明所提供的对印防伪特征的检测方法中假钞反面对印区域位置示意图；
图9为本发明所提供的对印防伪特征的检测方法中真钞正面对印区域与反面对印区域的融合示意图；
图10为本发明所提供的对印防伪特征的检测方法中假钞正面对印区域与反面对印区域的融合示意图；
图11为本发明实施例提供的对印防伪特征的检测装置的结构框图。
为了使本技术领域的人员更好地理解本发明方案，下面结合附图和具体实施方式对本发明作进一步的详细说明。显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
本发明所提供的对印防伪特征的检测方法的一种具体实施方式的流程图如图1所示，该方法包括：
步骤S101：获取待检测物体的第一检测图像以及第二检测图像，所述第一检测图像以及所述第二检测图像为分别与对印防伪区域相对应的正反面图像；
具体可以采用CIS传感器对待检测物体具有对印防伪标识图案的正面、反面可见光反射图像进行采集，生成第一检测图像以及第二检测图像。
步骤S102：提取所述第一检测图像的防伪特征信息，生成第一防伪特征图像；
作为一种具体实施方式，如图2所示，本实施例中提取第一检测图像的防伪特征信息的过程可以具体包括：
步骤S1021：获取所述待检测物体的版本信息，根据所述版本信息确定所述第一检测图像中对印防伪区域的第一位置信息；
步骤S1022：根据所述第一位置信息，采用投影以及滑动窗搜索方式对所述第一检测图像进行搜索，确定第一对印防伪区域；
步骤S1023：对所述第一对印防伪区域进行特征提取，生成第一防伪特征图像。
本实施例中根据待检测物体的版本信息，在数据库中查找预先存储的模板信息，确定第一检测图像中对印防伪区域的第一位置信息。在第一检测图像中，采用投影以及滑动窗搜索方式进行搜索，标记第一对印防伪区域，对该区域进行特征提取，得到第一防伪特征图像。
步骤S103：提取所述第二检测图像的防伪特征信息并进行镜像变换，生成第二防伪特征图像；
本实施例所提供的生成第二防伪特征图像的一种具体实施方式如图3所示，其具体包括：
步骤S1131：根据所述第一位置信息，进行坐标变换后确定所述第二检测图像中对印防伪区域的第二位置信息；
步骤S1132：对所述第二检测图像中的第二对印防伪区域进行特征提取并进行镜像变换，生成第二防伪特征图像。
对第一位置信息进行坐标变换后，即可获取与第一位置信息对应的第二对印防伪区域的位置信息，根据该位置信息对第二对印防伪区域进行特征提取，并进行镜像变换后生成第二防伪特征图像。此种实施方式中步骤S103需在步骤S102执行后，获取到第一位置信息的基础上进行。
步骤S104：将所述第一防伪特征图像以及所述第二防伪特征图像进行融合，生成融合防伪特征图像；
融合的过程可以具体为：将所述第一防伪特征图像以及所述第二防伪特征图像进行二值化处理；对处理后的图像相同位置的像素点的像素值分别进行取大的运算，生成融合防伪特征图像。
步骤S105：将所述融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断所述待检测物体的真伪。
判断的过程具体为：
计算所述融合防伪特征图像与所述标准防伪特征图像的相关系数；将所述相关系数与预设阈值进行比较，当所述相关系数大于或等于所述预设阈值时，判定所述待检测物体为真；当所述相关系数小于所述预设阈值时，判定所述待检测物体为假。
本发明所提供的对印防伪特征的检测方法，通过获取待检测物体的第一检测图像以及第二检测图像，提取第一检测图像的防伪特征信息，生成第一防伪特征图像；提取第二检测图像的防伪特征信息并进行镜像变换，生成第二防伪特征图像；将第一防伪特征图像以及第二防伪特征图像进行融合，生成融合防伪特征图像；将融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断待检测物体的真伪。本申请只需进行正反面可见光反射图像的采集，无需进行可见光透射图像的采集，在保障对印检测防伪性能的情况下，有效降低了设备的成本，并且无需采用图像拼接技术中的复杂算法，降低了对数字信号处理器的性能要求。
本发明所提供的对印防伪特征的检测方法，待检测物体可以具体为钞票，如100元人民币。第一检测图像、第二检测图像分别对应钞票的正面、反面。本实施例中以第一检测图像为钞票的正面图像为例。对钞票对印防伪特征的检测过程进行进一步详细阐述。
本发明所提供的对印防伪特征的检测方法的另一种具体实施方式流程图如图4所示，具体包括：
步骤S201：对钞票正面、反面进行图像采集，生成正面检测图像以及反面检测图像。
采用CIS传感器完成正面、反面可见光反射图像采集，采集得到正面图像IA和反面图像IB，I(i,j)为像素点(i,j)的像素值。
步骤S202：获取包含钞票面值面向的版本信息，根据版本信息调取预存在数据库中的正面对印图像的位置信息；
应用向量
表示某版本正面图像对印搜索区域的位置，其中x为搜索区域的横坐标，y为搜索区域的纵坐标，Δx为搜索区域的宽度，Δy为搜索区域的高度；
步骤S203：对正面对印图像搜索区域应用投影和滑动窗搜索方式完成正面对印图像搜索，实现对印图像定位，标记正面图像位置信息，并根据该位置信息进行正面对印图像提取；
对区域
进行图像像素的水平投影，
应用滑动窗搜索方法完成纵向位置定位，窗口大小Δy1为对印图像的高度信息，预存在存储模块中，当i满足如下条件时
记录y1＝i为对印图像顶点的纵坐标；
对区域
进行图像像素的垂直投影，
应用滑动窗搜索方法完成横向位置定位，窗口大小Δx1为对印图像的宽度信息，预存在存储模块中当i满足如下条件时
记录x1＝i为对印图像顶点的横坐标；由此，完成正面区域对印图像的区域确定，正面区域对印图像区域为
提取正面对印图像IA1，
IA1(i,j)＝I(i+x1,j+y1)，i＝0,...,Δx1，j＝0,...,Δy1
步骤S204：根据正面对印图像的位置信息，进行坐标变换，获取与正面对印图像位置信息对应的反面对印区域位置信息，根据该位置信息进行反面对印区域图像提取并进行镜像变换；
首先根据正面对印图像的位置
进行如下坐标变换
获取与正面对印位置信息对应的反面区域位置信息
提取反面对印图像IB1(i,j)，
IB1(i,j)＝IB(i+w-x1-Δx1,y1)，i＝0,...,Δx1，j＝0,...,Δy1
上式中，w为钞票的宽度信息，对该区域进行水平方向镜像变换，得到反面对印区域镜像图像：
IC1(i,j)＝IB1(Δx1-i,j)，i＝0,...,Δx1，j＝0,...,Δy1
步骤S205：将正面对印图像二值化处理，将高于二值化阈值的图像像素置0，其余像素保留，对非0像素进行归一化处理，反面对印区域采取相同处理；
首先应用二值化方法处理正面对印区域图像IA1，得到二值化阈值TA1，
对正面对印区域图像进行阈值分割，得到正面对印区域的分割图像
对分割图像进行归一化处理
上式中，[g0,g0+g1]为图像拉伸的拉伸范围；
应用二值化方法处理反面对印区域图像IC1，得到二值化阈值TC1，
对反面对印区域镜像图像进行阈值分割，得到反面对印区域的分割图像
对分割图像进行归一化处理
步骤S206：将阈值分割并归一化的两幅图像相同位置的像素进行取大运算，形成融合图像；
IAC3(i,j)＝max(IA3(i,j),IC3(i,j)),i＝0,...,Δx1，j＝0,...,Δy1
步骤S207：将归一化的融合图像与预存模版进行匹配，匹配输出结果达到预设阈值时判断该张钞票为真。
横向投影模版匹配相关系数计算，首先获取横向投影数据
对横向投影数据进行归一化处理，
上式中，[f0,f0+f1]为投影数据拉伸的拉伸范围；
调取预存在存储模块中的横向投影模版fVAC3，进行模版匹配相关系数计算
纵向投影模版匹配相关系数计算，首先获取纵向投影数据
对纵向投影进行归一化处理，
调取预存在存储模块中的横向投影模版fHAC3，进行模版匹配相关系数计算
当相关系数满足如下条件时，判断该张钞票为真
需要指出的是，预存模版生成的方式与步骤S201-S206类似，针对标准钞票进行采集，预存在存储模块中。
对于横向进钞或纵向进钞装置，因图像采样频率一致，走钞速度不一致时，存在图像较实际分辨率尺寸拉伸或缩短的情况，即钞票实际尺寸可能与预存模版对应的钞票尺寸不一致的问题。鉴于此，可将预存模版的钞票尺寸信息预存至数据库，根据投入钞票的尺寸和预存尺寸，对搜索区域和对印图像索搜的滑动窗尺寸进行变换，在进行模版匹配步骤时，将融合图像特征与预存模版的长度信息进行插值归一化，再完成匹配，如图5本发明所提供的又一种具体实施方式示意图所示，其详细操作步骤如下；
预存模版信息与该模版信息对应的钞票尺寸信息，记预存钞票图像宽度为W，钞票高度H，正面搜索区域
对印图像尺寸宽度Δm1，对印图像尺寸高度Δm1；
应用CIS传感器完成正面、反面可见光反射图像采集，获得正面图像IA和反面图像IB，I(i,j)为像素点(i,j)的像素值。
获取钞票面值面向版本信息与尺寸信息，根据面值面向信息版本尺寸信息确定正面对印图像搜索区域；
计算实际钞票尺寸信息为图像宽度W1，钞票高度H1，获取变换宽度变换系数ηW＝W1/W，高度变换系数ηH＝H1/H,则正面对印搜索区域的位置
其中ηWm为搜索区域的横坐标，ηHn为搜索区域的纵坐标，ηWΔm为搜索区域的宽度，ηHΔn为搜索区域的高度；为方便下面表述，记x＝ηWm，y＝ηHn,Δx＝ηWΔm,Δy＝ηHΔn；
应用投影定位结合滑动窗搜索方式完成正面对印图像搜索，实现对印图像定位，标记正面图像位置信息，并根据该位置信息进行正面对印图像提取；
以正像为例，首先对区域
进行图像像素的水平投影，
应用高度变换系数确定正面对印区域的搜索高度为ηHΔn1,令Δy1＝ηHΔn1，应用滑动窗搜索方法完成纵向位置定位，当i满足如下条件时
记录y1＝i为对印图像顶点的纵坐标；
对区域
进行图像像素的垂直投影，
应用高度变换系数确定正面对印区域的搜索高度为ηWΔm1,令Δy1＝ηWΔm1，应用滑动窗搜索方法完成横向位置定位，当i满足如下条件时
记录x1＝i为对印图像顶点的横坐标；由此，完成正面区域对印图像的区域确定，
截取图像为IA1，
IA1(i,j)＝I(i+x1,j+y1)，i＝0,...,Δx1，j＝0,...,Δy1
根据正面对印图像的位置信息，进行坐标变换，获取与正面对印图像位置信息对应的反面区域位置信息，并根据该位置信息进行反面对印区域图像提取并进行镜像变换；
首先根据正面对印图像的位置
进行如下坐标变换
获取与正面对印位置信息对应的反面区域位置信息，
IB1(i,j)＝IB(i+w-x1-Δx1,j+y1)，i＝0,...,Δx1，j＝0,...,Δy1
并对该区域进行水平方向镜像变换，得到反面对印区域图像。
IC1(i,j)＝IB1(Δx1-i,j)，i＝0,...,Δx1，j＝0,...,Δy1
将正面对印图像二值化处理，将高于二值化阈值的图像像素置0，其余像素保留，对非0像素进行归一化处理，反面对印区域采取相同处理；
首先应用二值化方法处理正面对印区域图像IA1，得到二值化阈值TA1，
对正面对印区域图像进行阈值分割，得到正面对印区域的分割图像
对分割图像进行归一化处理
应用二值化方法处理反面对印区域镜像图像IC1，得到二值化阈值TC1，
对反面对印区域镜像图像进行阈值分割，得到反面对印区域的分割图像
对分割图像进行归一化处理
将两幅图像相同位置的像素进行取大，形成融合图像，并完成图像大小的归一化；
IAC3(i,j)＝max(IA3(i,j),IC3(i,j)),i＝0,...,Δx1，j＝0,...,Δy1
将归一化的融合图像与预存模版进行匹配，匹配输出结果达到预设阈值是判断该张钞票为真。
横向投影模版匹配相关系数计算，首先获取横向投影数据
对横向投影进行归一化处理，
模版长度归一化，对融合图像的横向投影数据EVAC3进行插值，将数据长度插值为与横向投影数据模版fVAC3长度一致，记插值后的投影数据为FVAC3，
纵向投影模版匹配相关系数计算，首先获取纵向投影数据
对纵向投影进行归一化处理，
模版长度归一化，对融合图像的纵向投影数据EHAC3进行插值，将数据长度插值为与纵向投影数据模版fHAC3长度一致，记插值后的投影数据为FHAC3，
当相关系数满足如下条件时，判断该张钞票为真：
本申请中识别结果在嵌入式系统中完成，嵌入式系统将控制机械运动模块实现钞票真假的区分。通过对坐标进行校正，能够避免由于图像获取过程中的拉伸或压缩导致的匹配结果不准确的问题，提高了检测结果准确性。
图6示出了本发明所提供的对印防伪特征的检测方法中正面对印区域位置示意图，图7示出了本发明所提供的对印防伪特征的检测方法中真钞反面对印区域位置示意图，图8示出了本发明所提供的对印防伪特征的检测方法中假钞反面对印区域位置示意图，而图9示出了本发明所提供的对印防伪特征的检测方法中真钞正面对印区域与反面对印区域的融合示意图，图10示出了本发明所提供的对印防伪特征的检测方法中假钞正面对印区域与反面对印区域的融合示意图。可见，本申请无需采用可见光投射传感器以及图像拼接技术，即可实现对钞票真伪的识别。
下面对本发明实施例提供的对印防伪特征的检测装置进行介绍，下文描述的对印防伪特征的检测装置与上文描述的对印防伪特征的检测方法可相互对应参照。
图11为本发明实施例提供的对印防伪特征的检测装置的结构框图，参照图11对印防伪特征的检测装置可以包括：
图像获取模块100，用于获取待检测物体的第一检测图像以及第二检测图像，所述第一检测图像以及所述第二检测图像为分别与对印防伪区域相对应的正反面图像；
第一提取模块200，用于提取所述第一检测图像的防伪特征信息，生成第一防伪特征图像；
第二提取模块300，用于提取所述第二检测图像的防伪特征信息并进行镜像变换，生成第二防伪特征图像；
融合模块400，用于将所述第一防伪特征图像以及所述第二防伪特征图像进行融合，生成融合防伪特征图像；
检测模块500，用于将所述融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断所述待检测物体的真伪。
本实施例的对印防伪特征的检测装置用于实现前述的对印防伪特征的检测方法，因此对印防伪特征的检测中的具体实施方式可见前文中的对印防伪特征的检测方法的实施例部分，例如，图像获取模块100，第一提取模块200，第二提取模块300，融合模块400，检测模块500，分别用于实现上述对印防伪特征的检测方法中步骤S101，S102，S103，S104以及S105，所以，其具体实施方式可以参照相应的各个部分实施例的描述，在此不再赘述。
本发明所提供的对印防伪特征的检测装置，通过获取待检测物体的第一检测图像以及第二检测图像，提取第一检测图像的防伪特征信息，生成第一防伪特征图像；提取第二检测图像的防伪特征信息并进行镜像变换，生成第二防伪特征图像；将第一防伪特征图像以及第二防伪特征图像进行融合，生成融合防伪特征图像；将融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断待检测物体的真伪。本申请只需进行正反面可见光反射图像的采集，无需进行可见光透射图像的采集，在保障对印检测防伪性能的情况下，有效降低了设备的成本，并且无需采用图像拼接技术中的复杂算法，降低了对数字信号处理器的性能要求。
本说明书中各个实施例采用递进的方式描述，每个实施例重点说明的都是与其它实施例的不同之处，各个实施例之间相同或相似部分互相参见即可。对于实施例公开的装置而言，由于其与实施例公开的方法相对应，所以描述的比较简单，相关之处参见方法部分说明即可。
专业人员还可以进一步意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现
不应认为超出本发明的范围。
结合本文中所公开的实施例描述的方法或算法的步骤可以直接用硬件、处理器执行的软件模块，或者二者的结合来实施。软件模块可以置于随机存储器(RAM)、内存、只读存储器(ROM)、电可编程ROM、电可擦除可编程ROM、寄存器、硬盘、可移动磁盘、CD-ROM、或技术领域内所公知的任意其它形式的存储介质中。
以上对本发明所提供的对印防伪特征的检测方法以及装置进行了详细介绍。本文中应用了具体个例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的方法及其核心思想。应当指出，对于本技术领域的普通技术人员来说，在不脱离本发明原理的前提下，还可以对本发明进行若干改进和修饰，这些改进和修饰也落入本发明权利要求的保护范围内。
Claims (9)
- 一种对印防伪特征的检测方法，其特征在于，包括：获取待检测物体的第一检测图像以及第二检测图像，所述第一检测图像以及所述第二检测图像为分别与对印防伪区域相对应的正反面图像；提取所述第一检测图像的防伪特征信息，生成第一防伪特征图像；提取所述第二检测图像的防伪特征信息并进行镜像变换，生成第二防伪特征图像；将所述第一防伪特征图像以及所述第二防伪特征图像进行融合，生成融合防伪特征图像；将所述融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断所述待检测物体的真伪。
- 如权利要求1所述的对印防伪特征的检测方法，其特征在于，所述提取所述第一检测图像的防伪特征信息，生成第一防伪特征图像包括：获取所述待检测物体的版本信息，根据所述版本信息确定所述第一检测图像中对印防伪区域的第一位置信息；根据所述第一位置信息，采用投影以及滑动窗搜索方式对所述第一检测图像进行搜索，确定第一对印防伪区域；对所述第一对印防伪区域进行特征提取，生成第一防伪特征图像。
- 如权利要求2所述的对印防伪特征的检测方法，其特征在于，所述提取所述第二检测图像的防伪特征信息并进行镜像变换，生成第二防伪特征图像包括：根据所述第一位置信息，进行坐标变换后确定所述第二检测图像中对印防伪区域的第二位置信息；对所述第二检测图像中的第二对印防伪区域进行特征提取并进行镜像变换，生成第二防伪特征图像。
- 如权利要求1至3任一项所述的对印防伪特征的检测方法，其特征在于，所述将所述第一防伪特征图像以及所述第二防伪特征图像进行融合，生成融合防伪特征图像包括：将所述第一防伪特征图像以及所述第二防伪特征图像进行二值化处 理；对处理后的图像相同位置的像素点的像素值分别进行取大的运算，生成融合防伪特征图像。
- 如权利要求4所述的对印防伪特征的检测方法，其特征在于，所述将所述第一防伪特征图像以及所述第二防伪特征图像进行二值化处理包括：采用阈值分割法确定所述第一防伪特征图像以及所述第二防伪特征图像的二值化阈值；将高于所述二值化阈值的像素点的像素值置为0，其余像素点的像素值保留原值。
- 如权利要求1所述的对印防伪特征的检测方法，其特征在于，在所述将所述融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断所述待检测物体的真伪之前还包括：对所述融合防伪特征图像中的各像素点的像素值进行归一化处理。
- 如权利要求6所述的对印防伪特征的检测方法，其特征在于，所述将所述融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断所述待检测物体的真伪包括：计算所述融合防伪特征图像与所述标准防伪特征图像的相关系数；将所述相关系数与预设阈值进行比较，当所述相关系数大于或等于所述预设阈值时，判定所述待检测物体为真；当所述相关系数小于所述预设阈值时，判定所述待检测物体为假。
- 如权利要求1至3任一项所述的对印防伪特征的检测方法，其特征在于，在获取待检测物体的第一检测图像以及第二检测图像之后还包括：将所述第一检测图像、所述第二检测图像的尺寸大小与所述预存模板中的标准物体的尺寸大小进行对比，确定图像的拉伸系数；根据所述拉伸系数对各图像中对应的坐标进行校正。
- 一种对印防伪特征的检测装置，其特征在于，包括：图像获取模块，用于获取待检测物体的第一检测图像以及第二检测图像，所述第一检测图像以及所述第二检测图像为分别与对印防伪区域相对 应的正反面图像；第一提取模块，用于提取所述第一检测图像的防伪特征信息，生成第一防伪特征图像；第二提取模块，用于提取所述第二检测图像的防伪特征信息并进行镜像变换，生成第二防伪特征图像；融合模块，用于将所述第一防伪特征图像以及所述第二防伪特征图像进行融合，生成融合防伪特征图像；检测模块，用于将所述融合防伪特征图像与预存模板中的标准防伪特征图像进行匹配，根据匹配结果判断所述待检测物体的真伪。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611168869.2A CN106599923B (zh) | 2016-12-16 | 2016-12-16 | 一种对印防伪特征的检测方法及装置 |
| CN201611168869.2 | 2016-12-16 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2018107574A1 true WO2018107574A1 (zh) | 2018-06-21 |
Family
ID=58599586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2017/073054 WO2018107574A1 (zh) | 2016-12-16 | 2017-02-07 | 一种对印防伪特征的检测方法及装置 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106599923B (zh) |
| WO (1) | WO2018107574A1 (zh) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115223018A (zh) * | 2022-06-08 | 2022-10-21 | 东北石油大学 | 伪装对象协同检测方法及装置、电子设备和存储介质 |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109389153B (zh) * | 2018-08-31 | 2021-03-02 | 众安信息技术服务有限公司 | 一种全息防伪码校验方法及装置 |
| CN110309859B (zh) * | 2019-06-06 | 2023-04-07 | 创新先进技术有限公司 | 一种图像真伪检测方法、装置及电子设备 |
| CN112749690B (zh) * | 2020-03-27 | 2023-09-12 | 腾讯科技（深圳）有限公司 | 一种文本检测方法、装置、电子设备和存储介质 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100157377A1 (en) * | 2008-12-18 | 2010-06-24 | Xerox Corporation | Uv fluorescence encoded background images using adaptive halftoning into disjoint sets |
| CN104574638A (zh) * | 2014-09-30 | 2015-04-29 | 上海层峰金融设备有限公司 | 一种人民币识别方法 |
| CN105184957A (zh) * | 2015-09-28 | 2015-12-23 | 深圳怡化电脑股份有限公司 | 一种纸币鉴伪方法和系统 |
| CN205451254U (zh) * | 2015-12-28 | 2016-08-10 | 浙江维融电子科技股份有限公司 | 一种2015年版人民币胶印对印图案的鉴别装置 |
| CN105931357A (zh) * | 2016-04-19 | 2016-09-07 | 北京新岸线数字图像技术有限公司 | 钞票防伪检测方法及装置 |
| CN205722109U (zh) * | 2016-04-19 | 2016-11-23 | 北京新岸线数字图像技术有限公司 | 钞票防伪检测设备 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6546351B1 (en) * | 2000-07-20 | 2003-04-08 | Currency Systems International | Note-specific currency processing |
| CN106920320A (zh) * | 2015-12-28 | 2017-07-04 | 浙江维融电子科技股份有限公司 | 一种2015年版人民币胶印对印图案的鉴别装置及其鉴别方法 |
| CN205750988U (zh) * | 2016-05-17 | 2016-11-30 | 北京新岸线数字图像技术有限公司 | 一种纸币鉴伪装置 |
-
2016
- 2016-12-16 CN CN201611168869.2A patent/CN106599923B/zh active Active
-
2017
- 2017-02-07 WO PCT/CN2017/073054 patent/WO2018107574A1/zh active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100157377A1 (en) * | 2008-12-18 | 2010-06-24 | Xerox Corporation | Uv fluorescence encoded background images using adaptive halftoning into disjoint sets |
| CN104574638A (zh) * | 2014-09-30 | 2015-04-29 | 上海层峰金融设备有限公司 | 一种人民币识别方法 |
| CN105184957A (zh) * | 2015-09-28 | 2015-12-23 | 深圳怡化电脑股份有限公司 | 一种纸币鉴伪方法和系统 |
| CN205451254U (zh) * | 2015-12-28 | 2016-08-10 | 浙江维融电子科技股份有限公司 | 一种2015年版人民币胶印对印图案的鉴别装置 |
| CN105931357A (zh) * | 2016-04-19 | 2016-09-07 | 北京新岸线数字图像技术有限公司 | 钞票防伪检测方法及装置 |
| CN205722109U (zh) * | 2016-04-19 | 2016-11-23 | 北京新岸线数字图像技术有限公司 | 钞票防伪检测设备 |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115223018A (zh) * | 2022-06-08 | 2022-10-21 | 东北石油大学 | 伪装对象协同检测方法及装置、电子设备和存储介质 |
| CN115223018B (zh) * | 2022-06-08 | 2023-07-04 | 东北石油大学 | 伪装对象协同检测方法及装置、电子设备和存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106599923A (zh) | 2017-04-26 |
| CN106599923B (zh) | 2020-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10699146B2 (en) | Mobile document detection and orientation based on reference object characteristics | |
| US20210383150A1 (en) | Iterative recognition-guided thresholding and data extraction | |
| WO2018216629A1 (ja) | 情報処理装置、情報処理方法、及びプログラム | |
| CN107622489B (zh) | 一种图像篡改检测方法及装置 | |
| US9014459B2 (en) | Identification method for valuable file and identification device thereof | |
| WO2018107574A1 (zh) | 一种对印防伪特征的检测方法及装置 | |
| US11144752B1 (en) | Physical document verification in uncontrolled environments | |
| CN110378351B (zh) | 印章鉴别方法及装置 | |
| WO2015066984A1 (zh) | 一种面向复杂背景的光学字符识别方法及装置 | |
| CN104408728A (zh) | 一种基于噪声估计的伪造图像检测方法 | |
| WO2007146477A2 (en) | Method and apparatus for adaptive hierarchical processing of print images | |
| Muhammad | Multi-scale local texture descriptor for image forgery detection | |
| Isaac et al. | A key point based copy-move forgery detection using HOG features | |
| Rajan et al. | An extensive study on currency recognition system using image processing | |
| Chakraborty et al. | Review of various image processing techniques for currency note authentication | |
| CN111881938B (zh) | 一种基于盲取证技术的图像真伪鉴别的方法 | |
| JP2011107878A (ja) | 位置検出装置、位置検出方法 | |
| Garkoti et al. | Indian currency recognition system using image processing techniques | |
| Berchtold et al. | Smartphone-supported integrity verification of printed documents | |
| Ali et al. | Detection and extraction of pantograph region from bank cheque images | |
| JP2004145592A (ja) | 移動ベクトル抽出装置及び方法及びプログラム及びその記録媒体 | |
| EP4383208A2 (en) | Automatic system and method for document authentication using portrait fraud detection | |
| US11900755B1 (en) | System, computing device, and method for document detection and deposit processing | |
| Brahmapurikar et al. | Currency Recognization for visually impaired People using Tensorflow | |
| Clark et al. | Document to live facial identification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17879691 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 17879691 Country of ref document: EP Kind code of ref document: A1 |