CN106971453B - Paper money fragment splicing method and device - Google Patents
Paper money fragment splicing method and device Download PDFInfo
- Publication number
- CN106971453B CN106971453B CN201710221042.1A CN201710221042A CN106971453B CN 106971453 B CN106971453 B CN 106971453B CN 201710221042 A CN201710221042 A CN 201710221042A CN 106971453 B CN106971453 B CN 106971453B
- Authority
- CN
- China
- Prior art keywords
- fragment
- paper money
- banknote
- splicing
- image
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D11/00—Devices accepting coins; Devices accepting, dispensing, sorting or counting valuable papers
- G07D11/10—Mechanical details
- G07D11/16—Handling of valuable papers
Abstract
The invention is suitable for the technical field of image processing, and provides a paper money fragment splicing method and a device, wherein the paper money fragment splicing method comprises the following steps: establishing a paper money template; acquiring a paper money fragment image to be spliced; dividing the paper money fragment image into corresponding denomination categories according to the color information of the paper money fragment image; extracting texture features of the banknote fragment images aiming at the banknote fragment images of each denomination type; and splicing the banknote fragment images according to the texture features and the banknote template. The automatic splicing method has the advantages that the automatic splicing of the paper money fragments is realized, the complexity of splicing and the difficulty of matching are reduced, and the secondary damage to the paper money fragments in the manual splicing process is effectively avoided; even under the condition of changing the scanning angle, the image brightness and the scanning visual angle of the paper money fragment image, better paper money fragment image characteristics can still be obtained, and the accuracy and the efficiency of splicing are effectively improved.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a method and a device for splicing paper money fragments.
Background
According to relevant regulations, a bank can exchange damaged coins when the area of the damaged coins reaches more than half of the face of the bill, so that users often need to manually splice broken paper money when encountering damaged coins caused by human or natural reasons.
However, when the number of the broken paper money pieces is large, the manual splicing is time-consuming and labor-consuming, the accuracy is low, and even secondary damage can be caused to the damaged paper money.
Disclosure of Invention
In view of this, the embodiment of the invention provides a method and a device for splicing paper currency fragments, so as to solve the problems of high difficulty, low accuracy and low efficiency in manual splicing of paper currency in the prior art.
In a first aspect of the embodiments of the present invention, a method for splicing banknote fragments is provided, where the method includes:
establishing a paper money template;
acquiring a paper money fragment image to be spliced;
dividing the paper money fragment image into corresponding denomination categories according to the color information of the paper money fragment image;
extracting texture features of the banknote fragment images aiming at the banknote fragment images of each denomination type;
and splicing the banknote fragment images according to the texture features and the banknote template.
Further, the acquiring of the banknote fragment images to be spliced comprises:
and acquiring the paper money fragment images to be spliced in a scanning mode, numbering the paper money fragment images according to the scanning sequence, and generating the paper money fragment images with numbering information.
Further, the dividing the banknote fragment image into corresponding denomination categories according to the color information of the banknote fragment image includes:
performing color space conversion on the paper money fragment image to convert the paper money fragment image from an RGB color space to an HSV color space;
after the banknote fragment image is converted into the HSV color space, comparing the hue component of the banknote fragment image with a preset hue component threshold, and dividing the banknote fragment image into corresponding face value categories according to the comparison result.
Further, the extracting the texture features of the banknote fragment images for each denomination category comprises:
extracting boundary information of the paper currency fragment image according to a preset boundary extraction algorithm;
and for each denomination type of the banknote fragment image, extracting the texture features of the banknote fragment image by adopting a scale-invariant feature conversion algorithm according to the boundary information of the banknote fragment image.
Further, the splicing the banknote fragment images according to the texture features and the banknote templates comprises:
determining the position information of the paper currency fragment image in the paper currency template according to the texture features;
and classifying the position information of the paper money fragment images, and splicing the paper money fragment images according to a classification result.
In a second aspect of the embodiments of the present invention, there is provided an apparatus for splicing paper money fragments, the apparatus including:
the creating module is used for creating a paper money template;
the acquisition module is used for acquiring a paper money fragment image to be spliced;
the classification module is used for dividing the paper money fragment images into corresponding denomination categories according to the color information of the paper money fragment images;
the extraction module is used for extracting the texture features of the paper currency fragment images aiming at the paper currency fragment images of each denomination type;
and the splicing module is used for splicing the paper currency fragment images according to the texture features and the paper currency template.
Further, the obtaining module is specifically configured to:
and acquiring the paper money fragment images to be spliced in a scanning mode, numbering the paper money fragment images according to the scanning sequence, and generating the paper money fragment images with numbering information.
Further, the classification module includes:
the conversion unit is used for carrying out color space conversion on the paper money fragment image so as to convert the paper money fragment image from an RGB color space to an HSV color space;
and the classification unit is used for comparing the hue component of the paper money fragment image with a preset hue component threshold value after the paper money fragment image is converted into the HSV color space, and dividing the paper money fragment image into corresponding face value categories according to the comparison result.
Further, the extraction module comprises:
the boundary information extraction unit is used for extracting the boundary information of the paper money fragment image according to a preset boundary extraction algorithm;
and the texture feature extraction unit is used for extracting the texture features of the banknote fragment images of each denomination type by adopting a scale-invariant feature conversion algorithm according to the boundary information of the banknote fragment images.
Further, the splicing module includes:
the positioning unit is used for determining the position information of the paper money fragment image in the paper money template according to the texture features;
and the splicing unit is used for classifying the position information of the paper money fragment images and splicing the paper money fragment images according to a classification result.
Compared with the prior art, the method and the device have the advantages that the paper money fragment images are divided into the corresponding face value categories according to the color information of the paper money, then the texture features are extracted aiming at the paper money fragment images of the same face value category, and the paper money fragment images are spliced according to the texture features and the paper money template, so that the automatic splicing of the paper money fragments is realized, the complexity of splicing and the difficulty of matching are reduced, and the secondary damage to the paper money fragments in the manual splicing process is effectively avoided; even under the condition of changing the scanning angle, the image brightness and the scanning visual angle of the paper money fragment image, better paper money fragment image characteristics can still be obtained, and the accuracy and the efficiency of splicing are effectively improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flowchart illustrating an implementation of a method for splicing banknote fragments according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a specific implementation of step S103 in the method for splicing the banknote fragments according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating a specific implementation of step S104 in the method for splicing banknote fragments according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating a specific implementation of step S105 in the method for splicing the banknote fragments according to an embodiment of the present invention
Fig. 5 is a block diagram of a banknote fragment splicing apparatus according to a second embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
According to the embodiment of the invention, the paper currency fragment images are divided into corresponding denomination classes according to the color information of the paper currency, then the texture features are extracted aiming at the paper currency fragment images of the same denomination class, and the paper currency fragment images are spliced according to the texture features and the paper currency template, so that the automatic splicing of the paper currency fragments is realized, the complexity of splicing and the difficulty of matching are reduced, and the secondary damage to the paper currency fragments in the manual splicing process is effectively avoided; even under the condition of changing the scanning angle, the image brightness and the scanning visual angle of the paper money fragment image, better paper money fragment image characteristics can still be obtained, and the splicing accuracy and efficiency are effectively improved. The embodiment of the invention also provides a corresponding device, which is respectively explained in detail below.
Fig. 1 shows an implementation flow of a method for splicing banknote fragments according to an embodiment of the present invention. Referring to fig. 1, the method includes:
in step S101, a banknote template is established.
Here, the banknotes are value symbols that are issued by countries or regions and are forcibly used. The banknote template in the embodiment of the invention comprises template images of the current banknotes with different denominations.
In step S102, a banknote fragment image to be spliced is acquired.
Optionally, in the embodiment of the present invention, the banknote fragment images to be spliced are obtained in a scanning manner, and the banknote fragment images are numbered according to the scanning sequence, so as to generate the banknote fragment images with the numbering information. The scanning device used includes, but is not limited to, a scanner or a high-speed scanner. In order to ensure that the details of the paper money fragment image are clear and complete, the embodiment of the invention can adjust the resolution of the paper money fragment image according to the clear condition of the image after the paper money fragment image is acquired.
The embodiment of the invention automatically numbers the paper currency fragment images in the scanning process, is beneficial to subsequently searching the corresponding paper currency fragment images according to the numbers, and can improve the efficiency of searching the fragment images and further improve the splicing efficiency when the recovery work of a large number of paper currency fragments is faced.
In step S103, the banknote fragment images are classified into corresponding denomination categories according to the color information of the banknote fragment images.
Optionally, the embodiment of the present invention uses the hue information of the banknote fragment image to classify denomination categories. Fig. 2 shows a specific implementation flow of step S103 in the method for splicing banknote fragments according to an embodiment of the present invention. Referring to fig. 2, the step S103 includes:
in step S201, the banknote fragment image is subjected to color space conversion to convert the banknote fragment image from an RGB color space to an HSV color space.
In step S202, after the conversion into the HSV color space, the hue component of the banknote fragment image is compared with a preset hue component threshold, and the banknote fragment image is divided into corresponding denomination categories according to the comparison result.
Here, the hue component threshold of the embodiment of the present invention performs denomination classification, and the banknote fragment image obtained by scanning is usually in RGB format, so that the banknote fragment image needs to be converted from RGB color space to HSV color space, and then the banknote fragment image is classified according to the denomination according to the preset different hue component thresholds.
Wherein the hue component threshold comprises a hue component threshold corresponding to each denomination of note.
Illustratively, there are 6 face values of 1 yuan, 5 yuan, 10 yuan, 20 yuan, 50 yuan and 100 yuan for the fifth set of RMB of the new edition. Wherein the 1-membered primary expression color is cyan, the 5-membered primary expression color is violet, the 10-membered primary expression color is blue, the 20-membered primary expression color is yellow, the 50-membered primary expression color is green, and the 100-membered primary expression color is red. In the HSV color space, hue components are measured by angle for different colors, ranging from 0 ° to 360 °, and calculated counterclockwise from red, for example, red is 0 °, green is 120 °, blue is 240 °, and its complement: yellow is 60 °, cyan is 180 °, and magenta is 300 °. Based on this, the hue component thresholds may be set to: a first hue component threshold 180 ° for dividing 1-tuple values, a second hue component threshold 240 ° for dividing 10-tuple values, a third hue component threshold 60 ° for dividing 20-tuple values, a fourth hue component threshold 120 ° for dividing 50-tuple values, a fifth hue component threshold 0 ° for dividing 100-tuple values, etc. In the actual dividing operation, a face value category corresponding to the banknote fragment image can be determined by adopting a comparison mode according to whether the hue component of the banknote fragment image falls within the hue component threshold value and the vicinity range thereof, and the banknote fragment image is divided into the face value categories.
As can be seen, in the RGB color space, colors are represented by three components of R (red), G (green), and B (blue); whereas in the HSV color space, colors are represented by hue (H) components only. According to the embodiment of the invention, the paper money fragment images are converted from the RGB color space to the HSV color space and then classified, so that the color data volume of the paper money fragment images is greatly reduced, the complexity of an algorithm is favorably reduced, the face value confirmation time is shortened, and the splicing efficiency is further improved.
In step S104, for each denomination-specific banknote fragment image, texture features of the banknote fragment image are extracted.
Optionally, in the embodiment of the present invention, the texture features are extracted according to the boundary information of the banknote fragment image, and the texture features are extracted by using a scale-invariant feature conversion algorithm. Fig. 3 shows a specific implementation flow of step S104 in the method for splicing banknote fragments according to an embodiment of the present invention. Referring to fig. 3, the step S104 includes:
in step S301, boundary information of the banknote fragment image is extracted according to a preset boundary extraction algorithm.
The embodiment of the invention adopts a boundary extraction algorithm to extract the boundary information of the paper currency fragment image in advance, eliminates the background area and the noise information of the paper currency fragment image, and is beneficial to conveniently extracting the texture features subsequently.
In step S302, for each denomination type banknote fragment image, a scale-invariant feature conversion algorithm is used to extract texture features of the banknote fragment image according to boundary information of the banknote fragment image.
In the embodiment of the present invention, the Scale-invariant feature transform algorithm is called Scale-invariant feature transform in all english, and is abbreviated as SIFT algorithm. The SIFT algorithm is an algorithm of computer vision, which is used for detecting and describing local features in an image, searching extreme points in a spatial scale, and extracting positions, scales and rotation invariants of the extreme points to obtain texture features of the image. The SIFT algorithm is used for obtaining the texture features of the banknote fragment images in the multi-scale Gaussian difference space, the texture features have scale invariance, and a good detection effect can be obtained even if the rotation angle, the image brightness or the scanning visual angle are changed, so that a stable feature standard is provided for template matching, the difficulty of feature matching is reduced, and the accuracy of banknote fragment splicing is improved.
In step S105, the banknote fragment images are stitched according to the texture features and the banknote template.
According to the embodiment of the invention, the banknote fragment images are spliced by comparing the texture features with the banknote template. Optionally, fig. 4 shows a specific implementation flow of step S105 in the method for splicing banknote fragments according to an embodiment of the present invention. Referring to fig. 4, the step S105 includes:
in step S401, the position information of the banknote fragment image in the banknote template is determined according to the texture features.
Here, according to the texture features, the banknote template is combined, and a preset template matching method is used to perform preliminary positioning on the banknote fragment images, so as to reduce the difficulty of image splicing. After the position information of the paper money fragment image in the paper money template is obtained, the position coordinates of the fragment image are marked, and a curve function of the position is obtained to obtain the position information of the paper money fragment image.
In step S402, the position information of the banknote fragment images is classified, and the banknote fragment images are spliced according to the classification result.
According to the embodiment of the invention, each paper money fragment image is traversed to obtain the corresponding position information. And then classifying the position information by using a clustering analysis method. This classification can be concentrated the same or close positional information, splices based on this categorised result, can further reduce the degree of difficulty of concatenation, improves the efficiency and the degree of accuracy of concatenation.
In summary, the banknote fragment images are divided into corresponding denomination categories according to the color information of the banknotes, then the texture features are extracted for the banknote fragment images of the same denomination category, and the banknote fragment images are spliced according to the texture features and the banknote template, so that the banknote fragments are automatically spliced, the complexity of splicing and the difficulty of matching are reduced, and secondary damage to the banknote fragments in the manual splicing process is effectively avoided; even under the condition of changing the scanning angle, the image brightness and the scanning visual angle of the paper money fragment image, better paper money fragment image characteristics can still be obtained, and the splicing accuracy and efficiency are effectively improved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Fig. 5 shows a block diagram of a device for splicing broken banknotes according to a second embodiment of the present invention, and only the parts related to this embodiment are shown for convenience of description.
In the embodiment of the present invention, the device is used for implementing the method for splicing the banknote fragments in the embodiments of fig. 1 to 4, and the method may be a software unit, a hardware unit or a combination of software and hardware unit built in a computer, a server or a notebook computer. Referring to fig. 5, the apparatus includes:
a creating module 51 for creating a banknote template;
the acquisition module 52 is used for acquiring a banknote fragment image to be spliced;
the classification module 53 is configured to classify the banknote fragment images into corresponding denomination categories according to the color information of the banknote fragment images;
the extraction module 54 is configured to extract, for each denomination type of banknote fragment image, texture features of the banknote fragment image;
and the splicing module 55 is used for splicing the banknote fragment images according to the texture features and the banknote template.
Further, the obtaining module 52 is specifically configured to:
and acquiring the paper money fragment images to be spliced in a scanning mode, numbering the paper money fragment images according to the scanning sequence, and generating the paper money fragment images with numbering information.
The scanning device used includes, but is not limited to, a scanner or a high-speed scanner. In order to ensure that details of the banknote fragment image are clear and complete, in the embodiment of the present invention, after the banknote fragment image is acquired, the acquiring module 52 may further adjust the resolution of the banknote fragment image according to the image clarity status.
The embodiment of the invention automatically numbers the paper currency fragment images in the scanning process, is beneficial to subsequently searching the corresponding paper currency fragment images according to the numbers, and can improve the efficiency of searching the fragment images and further improve the splicing efficiency when the recovery work of a large number of paper currency fragments is faced.
Further, the classification module 53 includes:
a conversion unit 531, configured to perform color space conversion on the banknote fragment image to convert the banknote fragment image from an RGB color space to an HSV color space;
the classifying unit 532 is configured to compare the hue component of the banknote fragment image with a preset hue component threshold after the banknote fragment image is converted into the HSV color space, and divide the banknote fragment image into corresponding denomination categories according to a comparison result.
Here, the banknote fragment image obtained by scanning is usually in RGB format, and therefore, in the embodiment of the present invention, the converting unit 531 converts the banknote fragment image from RGB color space to HSV color space, and then the classifying unit 532 classifies the banknote fragment image according to the denomination according to the preset different hue component thresholds.
Wherein the hue component threshold comprises a hue component threshold corresponding to each denomination of note. For an example of setting the hue component threshold, please refer to the description of the above embodiments, which is not described herein again. In the actual dividing operation, a comparison method may be adopted to determine the denomination category corresponding to the banknote fragment image according to whether the hue component of the banknote fragment image falls within the above hue component threshold and the vicinity thereof, and divide the banknote fragment image into the denomination categories.
As can be seen, in the RGB color space, colors are represented by three components of R (red), G (green), and B (blue); whereas in the HSV color space, colors are represented by hue (H) components only. According to the embodiment of the invention, the paper money fragment images are converted from the RGB color space to the HSV color space and then classified, so that the color data volume of the paper money fragment images is greatly reduced, the complexity of an algorithm is favorably reduced, the face value confirmation time is shortened, and the splicing efficiency is further improved.
Further, the extraction module 54 includes:
a boundary information extraction unit 541 configured to extract boundary information of the banknote fragment image according to a preset boundary extraction algorithm;
and the texture feature extraction unit 542 is configured to, for each denomination type of banknote fragment image, extract texture features of the banknote fragment image by using a scale-invariant feature conversion algorithm according to the boundary information of the banknote fragment image.
According to the embodiment of the invention, the boundary information of the paper currency fragment image is extracted by adopting a boundary extraction algorithm, and the background area and the noise information of the paper currency fragment image are removed, so that the subsequent extraction of the texture features is facilitated.
The scale invariant feature transformation algorithm is a computer vision algorithm, and is used for detecting and describing local features in an image, searching an extreme point in a spatial scale, and extracting position, scale and rotation invariant of the extreme point to obtain texture features of the image. The SIFT algorithm is used for obtaining the texture features of the banknote fragment images in the multi-scale Gaussian difference space, the texture features have scale invariance, and a good detection effect can be obtained even if the rotation angle, the image brightness or the scanning visual angle are changed, so that a stable feature standard is provided for template matching, the difficulty of feature matching is reduced, and the accuracy of banknote fragment splicing is improved.
Further, the splicing module 55 includes:
the positioning unit 551 is used for determining the position information of the banknote fragment image in the banknote template according to the texture features;
the splicing unit 552 is configured to classify the position information of the banknote fragment images and splice the banknote fragment images according to the classification result.
Here, the positioning unit 551 performs preliminary positioning on the banknote fragment image by using a preset template matching method in combination with the banknote template according to the texture features, so as to improve the accuracy of fragment image positioning. After the position information of the paper money fragment image in the paper money template is obtained, the position coordinates of the fragment image are marked, and a curve function of the position is obtained to obtain the position information of the paper money fragment image.
And traversing each paper money fragment image to obtain corresponding position information. The location information is then classified by the stitching unit 552 using a method of cluster analysis. The classification can centralize the same or similar position information, and splicing is carried out based on the classified result, so that the splicing difficulty is reduced, and the splicing efficiency and accuracy are improved.
In summary, the banknote fragment images are divided into corresponding denomination categories according to the color information of the banknotes, then the texture features are extracted for the banknote fragment images of the same denomination category, and the banknote fragment images are spliced according to the texture features and the banknote template, so that the banknote fragments are automatically spliced, the complexity of splicing and the difficulty of matching are reduced, and secondary damage to the banknote fragments in the manual splicing process is effectively avoided; even under the condition of changing the scanning angle, the image brightness and the scanning visual angle of the paper money fragment image, better paper money fragment image characteristics can still be obtained, and the accuracy and the efficiency of splicing are effectively improved.
It should be noted that the apparatus in the embodiment of the present invention may be configured to implement all technical solutions in the foregoing method embodiments, and the functions of each functional module may be implemented specifically according to the method in the foregoing method embodiments, and the specific implementation process may refer to the relevant description in the foregoing example, which is not described herein again.
The present invention also provides a non-transitory computer-readable storage medium storing instructions executable by one or more processors to perform operations comprising:
establishing a paper money template;
acquiring a paper money fragment image to be spliced;
dividing the paper money fragment image into corresponding denomination categories according to the color information of the paper money fragment image;
extracting texture features of the banknote fragment images aiming at the banknote fragment images of each denomination type;
and splicing the banknote fragment images according to the texture features and the banknote template.
Optionally, the acquiring the banknote fragment images to be spliced comprises:
and acquiring the paper money fragment images to be spliced in a scanning mode, numbering the paper money fragment images according to the scanning sequence, and generating the paper money fragment images with numbering information.
Optionally, the dividing the banknote fragment image into corresponding denomination categories according to the color information of the banknote fragment image includes:
performing color space conversion on the paper money fragment image to convert the paper money fragment image from an RGB color space into HSV color space data;
after the banknote fragment image is converted into the HSV color space, comparing the hue component of the banknote fragment image with a preset hue component threshold, and dividing the banknote fragment image into corresponding face value categories according to the comparison result.
Optionally, for each denomination category of banknote fragment images, extracting texture features of the banknote fragment images comprises:
extracting boundary information of the paper currency fragment image according to a preset boundary extraction algorithm;
and for each denomination type of the banknote fragment image, extracting the texture features of the banknote fragment image by adopting a scale-invariant feature conversion algorithm according to the boundary information of the banknote fragment image.
Optionally, the stitching the banknote fragment image according to the texture feature and the banknote template includes:
determining the position information of the paper currency fragment image in the paper currency template according to the texture features;
and classifying the position information of the paper money fragment images, and splicing the paper money fragment images according to a classification result.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present invention may be implemented in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (6)
1. A method of splicing of banknote fragments, the method comprising:
establishing a paper money template;
acquiring a paper money fragment image to be spliced in a scanning mode, numbering the paper money fragment image according to the scanning sequence, and generating a paper money fragment image with numbering information;
dividing the paper money fragment image into corresponding denomination categories according to the color information of the paper money fragment image;
aiming at the banknote fragment images of each denomination type, extracting the texture features of the banknote fragment images by adopting a size-invariant feature conversion algorithm;
splicing the banknote fragment images according to the texture features and the banknote template, and the method comprises the following steps: determining the position information of the paper currency fragment image in the paper currency template according to the texture features; and classifying the position information of the paper money fragment images, and splicing the paper money fragment images according to a classification result.
2. The method for splicing banknote fragments according to claim 1, wherein the dividing the banknote fragment images into corresponding denomination categories according to the color information of the banknote fragment images comprises:
performing color space conversion on the paper money fragment image to convert the paper money fragment image from an RGB color space to an HSV color space;
after the banknote fragment image is converted into the HSV color space, comparing the hue component of the banknote fragment image with a preset hue component threshold, and dividing the banknote fragment image into corresponding face value categories according to the comparison result.
3. The method for splicing banknote fragments according to claim 1, wherein the extracting the texture features of the banknote fragment images for each denomination category comprises:
extracting boundary information of the paper currency fragment image according to a preset boundary extraction algorithm;
and for each denomination type of the banknote fragment image, extracting the texture features of the banknote fragment image by adopting a scale-invariant feature conversion algorithm according to the boundary information of the banknote fragment image.
4. A device for splicing broken banknotes, characterized in that it comprises:
the creating module is used for creating a paper money template;
the acquisition module is used for acquiring the paper money fragment images to be spliced in a scanning mode, numbering the paper money fragment images according to the scanning sequence and generating the paper money fragment images with numbering information;
the classification module is used for dividing the paper money fragment images into corresponding denomination categories according to the color information of the paper money fragment images;
the extraction module is used for extracting the texture features of the paper currency fragment images by adopting a size-invariant feature conversion algorithm aiming at the paper currency fragment images of each denomination type;
the splicing module is used for splicing the paper currency fragment images according to the texture features and the paper currency template;
the splicing module includes:
the positioning unit is used for determining the position information of the paper money fragment image in the paper money template according to the texture features;
and the splicing unit is used for classifying the position information of the paper money fragment images and splicing the paper money fragment images according to a classification result.
5. The apparatus for splicing of banknote fragments of claim 4 wherein said sorting module comprises:
the conversion unit is used for carrying out color space conversion on the paper money fragment image so as to convert the paper money fragment image from an RGB color space to an HSV color space;
and the classification unit is used for comparing the hue component of the paper money fragment image with a preset hue component threshold value after the paper money fragment image is converted into the HSV color space, and dividing the paper money fragment image into corresponding face value categories according to the comparison result.
6. The device for splicing broken banknotes of claim 4, wherein the extraction module comprises:
the boundary information extraction unit is used for extracting the boundary information of the paper money fragment image according to a preset boundary extraction algorithm;
and the texture feature extraction unit is used for extracting the texture features of the banknote fragment images of each denomination type by adopting a scale-invariant feature conversion algorithm according to the boundary information of the banknote fragment images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710221042.1A CN106971453B (en) | 2017-04-06 | 2017-04-06 | Paper money fragment splicing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710221042.1A CN106971453B (en) | 2017-04-06 | 2017-04-06 | Paper money fragment splicing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106971453A CN106971453A (en) | 2017-07-21 |
| CN106971453B true CN106971453B (en) | 2020-01-14 |
Family
ID=59336458
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710221042.1A Active CN106971453B (en) | 2017-04-06 | 2017-04-06 | Paper money fragment splicing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106971453B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112419349B (en) * | 2020-11-19 | 2022-11-22 | 安阳师范学院 | Artificial intelligent object fragment image splicing method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1710596A (en) * | 2005-06-16 | 2005-12-21 | 上海交通大学 | Computer picture-arrangement automatic identifying method based on machine vision |
| EP1672593B1 (en) * | 2004-12-14 | 2010-03-03 | Pitney Bowes Inc. | Method and system for printing an original image and for determining if a printed image is an original or has been altered |
| CN102629368A (en) * | 2012-02-27 | 2012-08-08 | 天津大学 | Color image vignetting recovery method based on illumination surface modeling |
| CN102779349A (en) * | 2012-06-30 | 2012-11-14 | 东南大学 | Foggy day detecting method based on image color spatial feature |
| CN103559697A (en) * | 2013-10-03 | 2014-02-05 | 王浩 | Scrap paper lengthwise cutting splicing and recovering algorithm based on FFT |
| CN103809978A (en) * | 2014-02-20 | 2014-05-21 | 南京乐智云信息科技有限公司 | Method for conducting image graphic seamless chartlet splicing through software |
| EP3017421A1 (en) * | 2013-07-02 | 2016-05-11 | Authentication Industries | Method for printing interdependent security graphics |
| CN105809625A (en) * | 2016-03-07 | 2016-07-27 | 哈尔滨中研普瑞电子工程技术中心有限公司 | Fragment reconstruction method based on local texture pattern |
| CN105894655A (en) * | 2016-04-25 | 2016-08-24 | 浙江大学 | Method for detecting and recognizing bill under complex environments based on RGB-D camera |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103761722B (en) * | 2014-01-16 | 2015-03-11 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Fixed wing unmanned aerial vehicle touring image accurately-splicing method for power transmission line |
| CN105701764B (en) * | 2016-01-05 | 2019-01-04 | 曲阜裕隆生物科技有限公司 | A kind of joining method for medical image |
-
2017
- 2017-04-06 CN CN201710221042.1A patent/CN106971453B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1672593B1 (en) * | 2004-12-14 | 2010-03-03 | Pitney Bowes Inc. | Method and system for printing an original image and for determining if a printed image is an original or has been altered |
| CN1710596A (en) * | 2005-06-16 | 2005-12-21 | 上海交通大学 | Computer picture-arrangement automatic identifying method based on machine vision |
| CN102629368A (en) * | 2012-02-27 | 2012-08-08 | 天津大学 | Color image vignetting recovery method based on illumination surface modeling |
| CN102779349A (en) * | 2012-06-30 | 2012-11-14 | 东南大学 | Foggy day detecting method based on image color spatial feature |
| EP3017421A1 (en) * | 2013-07-02 | 2016-05-11 | Authentication Industries | Method for printing interdependent security graphics |
| CN103559697A (en) * | 2013-10-03 | 2014-02-05 | 王浩 | Scrap paper lengthwise cutting splicing and recovering algorithm based on FFT |
| CN103809978A (en) * | 2014-02-20 | 2014-05-21 | 南京乐智云信息科技有限公司 | Method for conducting image graphic seamless chartlet splicing through software |
| CN105809625A (en) * | 2016-03-07 | 2016-07-27 | 哈尔滨中研普瑞电子工程技术中心有限公司 | Fragment reconstruction method based on local texture pattern |
| CN105894655A (en) * | 2016-04-25 | 2016-08-24 | 浙江大学 | Method for detecting and recognizing bill under complex environments based on RGB-D camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106971453A (en) | 2017-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110046644B (en) | Certificate anti-counterfeiting method and device, computing equipment and storage medium | |
| CN106529380B (en) | Image recognition method and device | |
| CN111488756B (en) | Face recognition-based living body detection method, electronic device, and storage medium | |
| WO2020082577A1 (en) | Seal anti-counterfeiting verification method, device, and computer readable storage medium | |
| Creusen et al. | Color exploitation in hog-based traffic sign detection | |
| Karatzas et al. | ICDAR 2011 robust reading competition-challenge 1: reading text in born-digital images (web and email) | |
| CN108596197B (en) | Seal matching method and device | |
| CN104751142B (en) | A kind of natural scene Method for text detection based on stroke feature | |
| CN102800148B (en) | RMB sequence number identification method | |
| Pun et al. | A two-stage localization for copy-move forgery detection | |
| CN112381775B (en) | Image tampering detection method, terminal device and storage medium | |
| EP3772036A1 (en) | Detection of near-duplicate image | |
| Shen et al. | Improving OCR performance with background image elimination | |
| US9171224B2 (en) | Method of improving contrast for text extraction and recognition applications | |
| US10043071B1 (en) | Automated document classification | |
| CN108830275A (en) | Dot character, the recognition methods of dot matrix digit and device | |
| DK2447884T3 (en) | A method for the detection and recognition of an object in an image and an apparatus and a computer program therefor | |
| CN108230536A (en) | One kind is to light variable security index identification method and device | |
| CN110378351B (en) | Seal identification method and device | |
| Viraktamath et al. | Review on detection of fake currency using image processing techniques | |
| CN106971453B (en) | Paper money fragment splicing method and device | |
| KR101334794B1 (en) | Flower recognition method and apparatus using feature extraction | |
| CN111738079A (en) | Banknote denomination recognition method and device | |
| CN110874602A (en) | Image identification method and device | |
| CN108492445A (en) | The method and device of bank note classification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 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 |