CN108961532B - Method, device and equipment for processing crown word number image and storage medium - Google Patents
Method, device and equipment for processing crown word number image and storage medium Download PDFInfo
- Publication number
- CN108961532B CN108961532B CN201710384027.9A CN201710384027A CN108961532B CN 108961532 B CN108961532 B CN 108961532B CN 201710384027 A CN201710384027 A CN 201710384027A CN 108961532 B CN108961532 B CN 108961532B
- Authority
- CN
- China
- Prior art keywords
- connected domain
- image
- noise
- region
- preset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000004458 analytical method Methods 0.000 claims abstract description 41
- 238000003672 processing method Methods 0.000 claims abstract description 17
- 238000004590 computer program Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002902 bimodal effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
- G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
- G07D7/20—Testing patterns thereon
- G07D7/2008—Testing patterns thereon using pre-processing, e.g. de-blurring, averaging, normalisation or rotation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Inspection Of Paper Currency And Valuable Securities (AREA)
Abstract
The embodiment of the invention discloses a crown word number image processing method, a crown word number image processing device, crown word number image processing equipment and a storage medium, wherein the method comprises the following steps: acquiring a binary image of a crown word number region; performing connected domain analysis on each foreground pixel point in a preset region of the binary image to obtain a connected domain of the preset region; determining a noise connected domain in the connected domain according to the number of the connected domains and the image characteristics of a preset region; and changing the pixel points in the noise connected domain into background pixel points to obtain an updated image. The embodiment of the invention can determine the position of the edge noise by utilizing the connected domain analysis and combining the image characteristics of the preset region and the number of the connected domains in the region, and changes the edge noise into the background pixel, thereby eliminating the influence of the edge noise on the segmentation and identification of the crown word number. Meanwhile, the scheme processes the preset area instead of directly processing the whole image, so that the time complexity is low and the processing efficiency is high.
Description
Technical Field
The embodiment of the invention relates to an image processing technology, in particular to a crown word number image processing method, a crown word number image processing device, crown word number image processing equipment and a storage medium.
Background
The existing cash counter, cash checker, ATM, etc. usually have the function of checking the cash, namely identifying the serial number of the cash so as to identify the truth of the cash. The crown word number is identified, an image of a crown word number area needs to be intercepted from a paper money image, and then the crown word number is extracted from the image for identification.
However, when a crown word number image is captured, other foreground points other than the crown word number are often captured, for example, patterns extending to the crown word number area are often captured, so that when the foreground points are extracted, the required crown word number cannot be accurately separated due to the influence of the edge foreground points, the accurate positioning of the character boundary is further influenced, the crown word number is identified incorrectly or even cannot be identified, and certain difficulty is brought to paper money identification or counterfeit identification.
Disclosure of Invention
The embodiment of the invention provides a crown word number image processing method, a crown word number image processing device, crown word number image processing equipment and a crown word number image processing storage medium, which can distinguish edge foreground points and eliminate the influence of the edge foreground points on crown word number segmentation and identification.
In a first aspect, an embodiment of the present invention provides a crown word number image processing method, including:
acquiring a binary image of a crown word number region;
performing connected domain analysis on each foreground pixel point in a preset region of the binary image to obtain a connected domain of the preset region;
determining a noise connected domain in the connected domain according to the number of the connected domains and the image characteristics of the preset region;
and changing the pixel points in the noise connected domain into background pixel points to obtain an updated image.
Further, before acquiring the binary image of the crown word number region, the method further comprises: and setting the preset area according to the noise position, wherein the preset area at least comprises partial characters.
Further, determining a noise connected domain in the connected domain according to the number of the connected domains and the image characteristics of the preset region, including:
if the number of the connected domains is one, determining that no noise connected domain exists;
if the number of the connected domains is two or more, expanding the preset area by pixels with the preset number, analyzing the expanded area by the connected domains, and determining the noise connected domains according to the new connected domain analysis result.
Further, determining a noise connected component according to the new connected component analysis result includes:
under the condition that the number of the original connected domains is two, if the number of the new connected domains is one, determining that no noise connected domain exists; if the number of the new connected domains is two, determining a noise connected domain according to the image characteristics of the preset region;
under the condition that the number of the original connected domains is three or more, judging the intersection condition of the original connected domains according to the new connected domains; if the intersection exists, determining the connected domain without the intersection in the original connected domain as a noise connected domain; and if the intersection does not exist, determining a noise connected domain according to the image characteristics of the preset region.
Further, performing connected domain analysis on each foreground pixel point in a preset region of the binary image, including: and carrying out connected domain analysis on each foreground pixel point in the preset area of the binary image by adopting an eight-connected domain or a four-connected domain.
Further, acquiring a binary image of the prefix number region, including: intercepting a gray scale image of the crown word number area from the paper money gray scale image; and carrying out binarization on the gray map of the crown word number region to obtain a binary image of the crown word number region.
In a second aspect, an embodiment of the present invention further provides a crown word number image processing apparatus, including:
the image acquisition module is used for acquiring a binary image of the crown word number region;
the connected domain analysis module is used for carrying out connected domain analysis on each foreground pixel point in a preset region of the binary image to obtain a connected domain of the preset region;
the noise connected domain determining module is used for determining the noise connected domains in the connected domains according to the number of the connected domains, the image characteristics of the preset regions and a preset rule;
and the image updating module is used for changing the pixel points in the noise connected domain into background pixel points to obtain an updated image.
Further, the noise connected component determining module includes:
a first connected domain determining unit configured to determine that there is no noise connected domain when the number of connected domains is one;
and the second connected domain determining unit is used for expanding the preset area by a preset number of pixels under the condition that the number of the connected domains is two or more, analyzing the expanded area by the connected domain, and determining the noise connected domain according to a new connected domain analysis result.
In a third aspect, an embodiment of the present invention further provides an apparatus, where the apparatus includes:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a crown word number image processing method as provided by any embodiment of the invention.
In a fourth aspect, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements the crown word number image processing method provided in any embodiment of the present invention.
According to the crown word number image processing method, the crown word number image processing device, the crown word number image processing equipment and the storage medium, the position of the edge noise can be determined by utilizing connected domain analysis and combining the image characteristics of the preset area and the number of the connected domains in the area, and the edge noise is changed into the background pixel, so that the influence of the edge noise on the segmentation and the identification of the crown word number is eliminated. Meanwhile, the scheme processes the preset area instead of directly processing the whole image, so that the time complexity is low and the processing efficiency is high.
Drawings
Fig. 1 is a flowchart of a crown word number image processing method according to an embodiment of the present invention;
fig. 2 is a block diagram of a crown word number image processing apparatus according to a third embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an apparatus according to a fourth embodiment of the present invention;
FIG. 4 is a schematic illustration of a partial gray scale representation of a banknote provided in accordance with a sixth embodiment of the present invention;
FIG. 5 is a schematic diagram of a gray scale representation of a crown word number region provided by the sixth embodiment of the present invention;
fig. 6 is a schematic diagram of a binary image of a crown word number region according to a sixth embodiment of the present invention;
FIG. 7 is a schematic diagram of a default region and a connected domain according to a sixth embodiment of the present invention;
fig. 8 is a schematic diagram of an updated binary image according to a sixth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a crown-type-number image processing method according to an embodiment of the present invention, which is applicable to a case where an edge foreground point (also referred to as edge noise) exists in a crown-type-number region, where the edge foreground point is located at an edge of an image except for a crown type number in the crown-type-number region, an edge foreground point is generally not connected to a crown-type-number character, and the edge foreground point may affect segmentation and recognition of the crown type number, for example, other patterns intercepted when the crown-type-number region is intercepted due to characteristics of a banknote itself, and a foreground point at the upper left corner in the image shown in fig. 5 is an edge foreground point. The method may be performed by a prefix image processing apparatus, and may be an apparatus having calculation and processing functions, such as a computer or the like. As shown in fig. 1, the method specifically includes the following steps:
and step 110, acquiring a binary image of the crown word number region.
In this step, the gray map of the crown word number region can be intercepted from the paper money gray map, and binarization is performed on the gray map of the crown word number region to obtain a binary image of the crown word number region. Specifically, the approximate position of the crown word number on the banknote gray scale image can be known according to the characteristics of the banknote, so that the gray scale image of the crown word number area can be cut from the banknote gray scale image. The binarization may be performed by using an existing binarization algorithm, for example, a bimodal method, a P parameter method, an Otsu method, a maximum entropy threshold method, an iterative method (optimal threshold method), and the like, and the binarization process is not described in detail in the embodiments of the present invention.
And 120, performing connected domain analysis on each foreground pixel point in the preset region of the binary image to obtain a connected domain of the preset region.
In this step, the preset region is a part of the binary image that may contain edge noise, and the position and size of the preset region may be set according to the actual situation of the banknote (such as the edge noise position), for example, for a banknote of a certain currency and/or denomination, the position where the edge noise occurs is generally fixed and not connected to the prefix character, and then the region containing the position and part of the character may be set as the preset region for subsequent processing. The shape of the preset region is not limited in the embodiment of the present invention, and may be generally rectangular, square, or the like. The connected domain refers to an image region which is formed by foreground pixel points with the same pixel value and adjacent positions in an image. Connected component analysis refers to accessing all foreground pixel points of the image by row or column, finding out all connected components and marking. Specifically, eight connected domains or four connected domains may be adopted to perform connected domain analysis on each foreground pixel point in the preset region of the binary image. The connected component analysis process is the same as that in the prior art, and this will not be described in detail in the embodiment of the present invention.
And step 130, determining a noise connected domain in the connected domain according to the number of the connected domains and the image characteristics of the preset region.
In this step, the image characteristics may include: the edge noise is generally positioned at the edge position of the image, each character in the crown word size can be regarded as a connected domain, the edge noise is not connected with the character, and the preset region at least comprises part of the character. The image characteristics of the preset area and the number of connected domains are combined, whether the preset area contains noise can be determined, if the preset area contains noise, which connected domain is a noise connected domain can be determined, namely, the position of edge noise is determined in the binary image.
In this step, the connected domain changes the pixel point in the noise connected domain into the background pixel point for the foreground pixel in the binary image, that is, changes the value of the foreground pixel in the noise connected domain into the value corresponding to the background pixel, for example, the background pixel value in the binary image is 0, the foreground pixel value is 1, and the value of the pixel point in the noise connected domain is changed into 0, so that the edge noise is set as the background, and the obtained image does not contain the edge noise.
The crown word number image processing method of the embodiment can determine the position of the edge noise by utilizing connected component analysis and combining the image characteristics of the preset area and the number of the connected components in the area, and changes the edge noise into the background pixel, thereby eliminating the influence of the edge noise on the segmentation and identification of the crown word number. Meanwhile, the method processes the preset area instead of directly processing the whole image, and is low in time complexity and high in processing efficiency.
Preferably, before step 110, a preset region may be set according to the noise position, wherein the preset region includes at least a part of the characters. For a crown word number region which does not contain edge noise when an image is intercepted, a preset region only comprises partial characters; for the crown word number area containing the edge noise when the image is intercepted, the preset area comprises the edge noise and partial characters.
For banknotes of the same currency and/or denomination, the position of the edge noise is generally substantially consistent when the image is truncated. Specifically, the position of edge noise that can be easily intercepted can be counted through experiments, and then the position, size, and shape of the preset region are set in advance according to the position of edge noise. The corresponding edge noise position can also be determined according to the currency and/or the face value of the paper money, in practical application, corresponding preset areas can be preset through an input device aiming at the paper money with different currency and/or face values, the corresponding preset areas are stored, when the paper money is checked, the corresponding preset areas are read according to the currency and/or the face value, the edge noise is determined and eliminated, and then the crown word number is divided and identified. Or, in the using process, the corresponding preset area is reset through the input device aiming at the currency and/or face value to be detected at present, and then the steps of image acquisition, image processing and crown word number segmentation and recognition are executed.
In the preferred embodiment, the preset area can be set by itself, so that the flexibility of the method is improved, and the accuracy of eliminating the edge noise is improved.
Taking a currency detector as an example, the currency detector receives a plurality of banknotes, some banknotes may have edge noise, and some banknotes do not have edge noise, in the processing process, the method described in the embodiment is executed according to the preset region for all the received banknotes, according to the image characteristics of the preset region and the number of the connected domains in the region, whether the banknote crown word number region has edge noise can be determined, if the edge noise exists, the position of the edge noise is determined, the edge noise is changed into background pixels, and the influence of the edge noise on the segmentation and identification of the crown word number is eliminated.
Example two
In this embodiment, on the basis of the first embodiment, preferably, the step 130 may include the following steps: if the number of the connected domains is one, determining that no noise connected domain exists; if the number of the connected domains is two or more, expanding the preset area by the pixels with the preset number, analyzing the expanded area by the connected domains, and determining the noise connected domains according to the new connected domain analysis result.
Since the preset region at least contains partial characters, for the crown word number region without edge noise, the obtained connected domain should be the connected domain corresponding to the partial characters, and therefore, if only one connected domain exists, it indicates that the preset region has no edge noise. If the number of the connected domains is two or more, expanding the preset region, and analyzing the connected domains again, because the single character is connected, if the new connected domain analysis result shows that the original connected domains have intersection, the connected domains with the intersection may be characters instead of edge noise, and thus the original connected domains without any intersection can be determined to be the connected domains corresponding to the edge noise. The pixels with the preset number can be set as required. The direction of expansion is not limited in the present invention, and for example, as shown in fig. 5, if the edge noise is located between the characters 3 and 4 and close to the edge of the image, the preset region can be expanded along the left side, the right side and the lower side.
Preferably, determining the noise connected component according to the new connected component analysis result may include the following cases:
(1) under the condition that the number of the original connected domains is two, if the number of the new connected domains is one, determining that no noise connected domain exists; and if the number of the new connected domains is two, determining the noise connected domains according to the image characteristics of the preset region.
For example, as shown in fig. 5, in the edge noise, the position of the preset region is the upper left corner, connected domain analysis is performed on the expanded preset region to obtain two new connected domains, and according to the characteristic that the edge noise is at the edge of the image and is not connected with the character, and a single character is a connected domain, the connected domain labeled 1 can be determined as a noise connected domain; for another example, the edge noise is located in the lower right corner of the crown word number region, the preset region is a region with the size of the lower right corner being 20 × 20, and if the number of the new connected domains is two, the connected domain with the reference number 2 can be determined as the noise connected domain according to the image characteristics.
(2) And under the condition that the number of the original connected domains is three or more, judging the intersection condition of the original connected domains according to the new connected domains. And if the intersection exists, determining that the connected domain without the intersection in the original connected domain is the noise connected domain. If no intersection exists, determining a noise connected domain according to the image characteristics of the preset region, for example, continuing to expand the region and then performing connected domain analysis to determine the intersection, or determining a connected domain close to the edge of the preset region as a noise connected domain, taking fig. 7 as an example, and determining the connected domains labeled 1 and 3 as noise connected domains.
The method for determining the edge noise according to the number of the connected domains and the image characteristics of the preset region is simple to implement.
EXAMPLE III
Fig. 2 is a block diagram of a crown word size image processing apparatus according to a third embodiment of the present invention, which is applicable to a case where edge noise exists in a crown word size region, as shown in fig. 2, the apparatus includes: an image acquisition module 210, a connected component analysis module 220, a noise connected component determination module 230, and an image update module 240.
An image obtaining module 210, configured to obtain a binary image of the prefix number region;
the connected component analysis module 220 is configured to perform connected component analysis on each foreground pixel point in a preset region of the binary image to obtain a connected component of the preset region;
a noise connected domain determining module 230, configured to determine a noise connected domain in the connected domain according to the number of connected domains, the image characteristics of the preset region, and a preset rule;
and the image updating module 240 is configured to change the pixel points in the noise connected domain into background pixel points, so as to obtain an updated image.
The image processing apparatus for the crown word number in this embodiment can determine the position of the edge noise by using connected component analysis, and combining the image characteristics of the preset region itself and the number of connected components in the region, and change the edge noise into the background pixel, thereby eliminating the influence of the edge noise on the segmentation and identification of the crown word number. Meanwhile, the device processes the preset area instead of directly processing the whole image, and is low in time complexity and high in processing efficiency.
Preferably, the apparatus may further include: and the preset region setting module is used for setting a preset region according to the noise position, wherein the preset region at least comprises part of characters.
The noise connected component determining module 230 may include: the device comprises a first connected domain determining unit and a second connected domain determining unit, wherein the first connected domain determining unit is used for determining that no noise connected domain exists under the condition that the number of the connected domains is one; and the second connected domain determining unit is used for expanding the preset area by the pixels of the preset number under the condition that the number of the connected domains is two or more, analyzing the expanded area by the connected domain, and determining the noise connected domain according to a new connected domain analysis result.
The second connected component determining unit is specifically configured to: under the condition that the number of the original connected domains is two, if the number of the new connected domains is two, determining a noise connected domain according to the image characteristics of a preset region; if the number of the new connected domains is one, determining that no noise connected domain exists; under the condition that the number of the original connected domains is three or more, judging the intersection condition of the original connected domains according to the new connected domains; if the intersection exists, determining the connected domain without the intersection in the original connected domain as a noise connected domain; and if the intersection does not exist, determining a noise connected domain according to the image characteristics of the preset region.
Preferably, the connected component analysis module 220 may specifically perform connected component analysis on each foreground pixel point in the preset region of the binary image by using an eight connected component or a four connected component.
The image acquisition module 210 is specifically configured to: intercepting a gray scale image of the crown word number area from the paper money gray scale image; and carrying out binarization on the gray map of the crown word number region to obtain a binary image of the crown word number region.
The crown word number image processing device can execute the crown word number image processing method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects for executing the method.
Example four
Fig. 3 is a schematic structural diagram of an apparatus according to a fourth embodiment of the present invention, and as shown in fig. 3, the apparatus includes: a processor 310, a memory 320, an input device 330, and an output device 340. The number of the processors 310 in the device may be one or more, and one processor 310 is taken as an example in fig. 3; the processor 310, the memory 320, the input device 330 and the output device 340 may be connected by a bus or other means, and fig. 3 illustrates an example of a bus connection.
The memory 320 is a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the crown word number image processing method in the embodiment of the present invention (for example, the image acquisition module 210, the connected component analysis module 220, the noise connected component determination module 230, and the image update module 240 in the crown word number image processing apparatus). The processor 310 executes various functional applications of the device and data processing by executing software programs, instructions, and modules stored in the memory 320, that is, implements the prefix number image processing methods of the above-described embodiments one and two.
The memory 320 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 320 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the memory 320 may further include memory located remotely from the processor 310, which may be connected to the device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 330 may be used to receive input information and generate key signal inputs related to user settings and function control of the apparatus, for example, receiving user information about preset region settings. The output device 340 may include a display device such as a display screen, for example, to display a grayscale map, a binary image, a crown word number recognition result, and the like. The device can also comprise an image acquisition device for acquiring the image of the paper money.
EXAMPLE five
Fifth embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor, implements the crown word number image processing method as described in first and second embodiments.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the above-mentioned prefix image processing apparatus, the included units and modules are only divided according to the functional logic, but are not limited to the above-mentioned division as long as the corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
EXAMPLE six
The present embodiment provides a specific example based on the first to fifth embodiments, and the following describes the processing procedure of the prefix image with reference to the drawings.
As shown in fig. 4, there are other patterns near the crown word size, and a gray scale image of the region of the crown word size can be taken from fig. 4 according to the banknote image and the position of the crown word size on the banknote, as shown in fig. 5. The gray scale image of the crown word number region shown in fig. 5 is binarized to obtain the binary image shown in fig. 6, and obviously, edge noise exists at the upper left corner of the image, which may affect crown word number segmentation.
The preset region set in advance is a square region with the size of 12 × 12 from the upper left corner of the binary image, and as shown in fig. 7, eight connected domains are adopted to perform connected domain analysis on the preset region to obtain three connected domains, and the labels are 1, 2 and 3 respectively. Expanding the preset region by N pixel points, for example, expanding 5 pixel points to obtain a 17 × 17 region, performing connected domain analysis on the 17 × 17 region to obtain two new connected domains, where the pixel point with the reference number 2 and the pixel point with the reference number 3 have an intersection, that is, the two connected domains are two parts in the character "3", so that it can be determined that the pixel point with the reference number 1 is edge noise, and the pixel point with the reference number 1 is marked as a background point. The relabeled image is shown in fig. 8, eliminating edge foreground points. If the new connected domain analysis results still have no intersection, the pixel points marked with the numbers 1 and 3 close to the image edge can be marked as background points according to the characteristics of the crown word number region.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (8)
1. A crown word number image processing method is characterized by comprising the following steps:
acquiring a binary image of a crown word number region;
performing connected domain analysis on each foreground pixel point in a preset region of the binary image to obtain a connected domain of the preset region;
if the number of the connected domains is one, determining that no noise connected domain exists;
if the number of the connected domains is two or more, expanding the preset area by pixels with a preset number, analyzing the expanded area by the connected domains, and determining the noise connected domains according to the new connected domain analysis result;
and changing the pixel points in the noise connected domain into background pixel points to obtain an updated image.
2. The method of claim 1, wherein prior to obtaining the binary image of the crown-symbol region, the method further comprises:
and setting the preset area according to the noise position, wherein the preset area at least comprises partial characters.
3. The method of claim 1, wherein determining a noise connected component from the new connected component analysis result comprises:
under the condition that the number of the original connected domains is two, if the number of the new connected domains is one, determining that no noise connected domain exists; if the number of the new connected domains is two, determining a noise connected domain according to the image characteristics of the preset region;
under the condition that the number of the original connected domains is three or more, judging the intersection condition of the original connected domains according to the new connected domains; if the intersection exists, determining the connected domain without the intersection in the original connected domain as a noise connected domain; and if the intersection does not exist, determining a noise connected domain according to the image characteristics of the preset region.
4. The method according to claim 1, wherein performing connected domain analysis on each foreground pixel in a preset region of the binary image comprises:
and carrying out connected domain analysis on each foreground pixel point in the preset area of the binary image by adopting an eight-connected domain or a four-connected domain.
5. The method of claim 1, wherein obtaining a binary image of a prefix region comprises:
intercepting a gray scale image of the crown word number area from the paper money gray scale image;
and carrying out binarization on the gray map of the crown word number region to obtain a binary image of the crown word number region.
6. A crown-word-number image processing apparatus, comprising:
the image acquisition module is used for acquiring a binary image of the crown word number region;
the connected domain analysis module is used for carrying out connected domain analysis on each foreground pixel point in a preset region of the binary image to obtain a connected domain of the preset region;
a noise connected domain determination module, the noise connected domain determination module comprising:
a first connected domain determining unit configured to determine that there is no noise connected domain when the number of connected domains is one;
a second connected domain determining unit, configured to expand the preset region by a preset number of pixels when the number of connected domains is two or more, perform connected domain analysis on the expanded region, and determine a noise connected domain according to a new connected domain analysis result;
and the image updating module is used for changing the pixel points in the noise connected domain into background pixel points to obtain an updated image.
7. An apparatus, characterized in that the apparatus comprises:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement the crown word number image processing method of any one of claims 1 to 5.
8. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the crown-symbol image processing method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710384027.9A CN108961532B (en) | 2017-05-26 | 2017-05-26 | Method, device and equipment for processing crown word number image and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710384027.9A CN108961532B (en) | 2017-05-26 | 2017-05-26 | Method, device and equipment for processing crown word number image and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108961532A CN108961532A (en) | 2018-12-07 |
| CN108961532B true CN108961532B (en) | 2020-11-17 |
Family
ID=64494309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710384027.9A Active CN108961532B (en) | 2017-05-26 | 2017-05-26 | Method, device and equipment for processing crown word number image and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108961532B (en) |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194118B (en) * | 2010-03-02 | 2013-04-10 | 方正国际软件(北京)有限公司 | Method and device for extracting information from image |
| CN104574282B (en) * | 2013-10-22 | 2019-06-07 | 鸿富锦精密工业（深圳）有限公司 | Point cloud noise spot removes system and method |
| JP6352695B2 (en) * | 2014-06-19 | 2018-07-04 | 株式会社東芝 | Character detection apparatus, method and program |
| KR101590715B1 (en) * | 2014-06-30 | 2016-02-01 | 주식회사 엘지씨엔에스 | Apparatus and method for recognizing media, financial device |
| CN104268978B (en) * | 2014-09-24 | 2017-02-15 | 苏州佳世达光电有限公司 | Method for identifying serial number on bill |
| CN105303533B (en) * | 2015-11-03 | 2018-11-30 | 华中科技大学 | A kind of ultrasound image filtering method |
| CN105913093B (en) * | 2016-05-03 | 2019-06-21 | 电子科技大学 | A kind of template matching method for Text region processing |
| CN106023204B (en) * | 2016-05-20 | 2018-11-09 | 陕西师范大学 | A kind of method and system removing mosquito noise based on edge detection algorithm |
-
2017
- 2017-05-26 CN CN201710384027.9A patent/CN108961532B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108961532A (en) | 2018-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107437294B (en) | Character segmentation method, device, equipment and storage medium | |
| CN109740606B (en) | Image identification method and device | |
| CN107103683B (en) | Paper money identification method and device, electronic equipment and storage medium | |
| CN106952393B (en) | Paper money identification method and device, electronic equipment and storage medium | |
| CN110909692A (en) | Abnormal license plate recognition method and device, computer storage medium and electronic equipment | |
| CN108717744B (en) | Method and device for identifying seal serial number on financial document and terminal equipment | |
| CN109447080B (en) | Character recognition method and device | |
| CN108830275B (en) | Method and device for identifying dot matrix characters and dot matrix numbers | |
| CN108091033B (en) | Paper money identification method and device, terminal equipment and storage medium | |
| CN114387591A (en) | License plate recognition method, system, equipment and storage medium | |
| CN110738222B (en) | Image matching method and device, computer equipment and storage medium | |
| CN108268868B (en) | Method and device for acquiring inclination value of identity card image, terminal and storage medium | |
| CN110909816B (en) | Picture identification method and device | |
| CN108961532B (en) | Method, device and equipment for processing crown word number image and storage medium | |
| CN110084157B (en) | Data processing method and device for image re-recognition | |
| CN111768345A (en) | Method, device and equipment for correcting back image of identity card and storage medium | |
| US10176399B1 (en) | Method and apparatus for optical character recognition of dot text in an image | |
| JP5414631B2 (en) | Character string search method, character string search device, and recording medium | |
| CN108960222B (en) | Image binarization method, device, equipment and storage medium | |
| CN108961531B (en) | Method, device and equipment for identifying serial number of paper currency and storage medium | |
| CN108230538B (en) | Paper money identification method, device, equipment and storage medium | |
| CN108074323B (en) | Paper money facing identification method and device thereof | |
| CN111967460A (en) | Text detection method and device, electronic equipment and computer storage medium | |
| US10223618B1 (en) | Method and apparatus for transformation of dot text in an image into stroked characters based on dot pitches | |
| US10192132B1 (en) | Method and apparatus for detection of dots in an image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |