CN111028186A - Image enhancement method and device - Google Patents
Image enhancement method and device Download PDFInfo
- Publication number
- CN111028186A CN111028186A CN201911165004.4A CN201911165004A CN111028186A CN 111028186 A CN111028186 A CN 111028186A CN 201911165004 A CN201911165004 A CN 201911165004A CN 111028186 A CN111028186 A CN 111028186A
- Authority
- CN
- China
- Prior art keywords
- image
- enhanced
- channel
- color space
- calculating
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000004364 calculation method Methods 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 13
- 238000001514 detection method Methods 0.000 claims abstract description 12
- 230000004927 fusion Effects 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 abstract description 10
- 238000003709 image segmentation Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 18
- 230000000694 effects Effects 0.000 description 13
- 238000012015 optical character recognition Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 4
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 description 3
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 102000005717 Myeloma Proteins Human genes 0.000 description 1
- 108010045503 Myeloma Proteins Proteins 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
The invention discloses an image enhancement method and device, and relates to the technical field of computers. One embodiment of the method comprises: calculating a fluctuating image of an image to be enhanced and a background shading image of a corresponding area of the image to be enhanced in a first color space; calculating the character image of the corresponding area of the image to be enhanced in a second color space; and fusing the fluctuating image, the background shading image and the character image according to a preset rule to obtain an enhanced image. The method and the device can make full use of the color information of the image to be enhanced, avoid the enhancement of the image to be enhanced and the background shading, solve the problems that the contrast of the image to be enhanced is low, the character segmentation of the image to be enhanced is incomplete, and the image region to be enhanced is always interfered in a large amount after an image segmentation algorithm is adopted, reduce the calculation complexity, improve the accuracy of character detection and the accuracy of character recognition, and further improve the structured output level of the image OCR recognition result data.
Description
Technical Field
The invention relates to the technical field of computers, in particular to an image enhancement method and device.
Background
The seal is a form of enterprise authorization, is universally existed on various invoice surfaces, and the validity of the invoice can be proved only by pressing the seal of the enterprise. The seal is generally engraved with information such as a business name, a seal type, a seal number and the like, although an OCR (Optical Character Recognition) technology is quite mature and applied to a plurality of fields, such as identification of hospital laboratory sheets, personal examination sheets and the like, a medical charging bill is still a field which is difficult to be covered by the OCR technology, wherein an important reason is that a bill OCR system requires that a plurality of key fields are difficult to be completely satisfied in the same bill. For example, the ticket issuing machine of a plurality of medical charging tickets in provinces or direct prefectures (Beijing, Guangdong, Chongqing, etc.) does not directly print the key information of 'hospital name' but appears in the form of stamp characters, and almost all medical ticket OCR systems have difficulty in extracting and identifying stamp images because of low contrast of stamp images and characters.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art:
the traditional image enhancement method (such as histogram equalization, homomorphic filtering and the like) is complex in calculation, and color information of an image to be enhanced is not fully utilized, so that the image to be enhanced and background shading are enhanced together, and characters of a subsequent image to be enhanced are difficult to effectively segment.
Disclosure of Invention
In view of this, embodiments of the present invention provide an image enhancement method and apparatus, which can fully utilize color information of an image to be enhanced, avoid enhancing the image to be enhanced together with background shading, solve the problems of low contrast of the image to be enhanced, incomplete text segmentation of the image to be enhanced, and a large amount of interference often remaining in an image region to be enhanced after an image segmentation algorithm is adopted, reduce computational complexity, improve accuracy of text detection and accuracy of text recognition, and further improve a structured output level of image OCR recognition result data.
To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided an image enhancement method.
An image enhancement method, comprising: calculating a fluctuating image of the image to be enhanced by utilizing the component values of each channel of the image to be enhanced in the first color space; calculating a background shading image of a corresponding area of the image to be enhanced by using two channel component values selected by the image to be enhanced in the first color space; calculating a preset channel component image of the image to be enhanced in a second color space to obtain a character image of a region corresponding to the image to be enhanced; and fusing the fluctuating image, the background shading image and the character image according to a preset rule to obtain an enhanced image.
Optionally, the calculating a fluctuation image of the image to be enhanced by using the channel component values of the image to be enhanced in the first color space includes: in the RGB color space, the variance of R, G, B three-channel numerical values of each pixel point in the image to be enhanced is calculated to obtain a fluctuating image of the image to be enhanced in the form of a variance matrix.
Optionally, the calculating a fluctuation image of the image to be enhanced by using the channel component values of the image to be enhanced in the first color space includes: in the RGB color space, calculating the RGB three-channel mean value of the image to be enhanced; and calculating the variance of the RGB three-channel numerical values of the image to be enhanced by using R, G, B each single-channel numerical value and the three-channel mean value to obtain the fluctuating image of the image to be enhanced.
Optionally, the calculating a background shading image of a corresponding region of the image to be enhanced by using two channel component values selected by the image to be enhanced in the first color space includes: calculating a G component and a B component of the image to be enhanced in an RGB color space; and obtaining a background shading image of the corresponding area of the image to be enhanced according to the difference value of the G component and the B component.
Optionally, the calculating a preset channel component image of the image to be enhanced in a second color space to obtain a text image of a region corresponding to the image to be enhanced includes: and calculating an M component image and/or a C component image of the image to be enhanced in a CMYK color space, and obtaining a character image of a corresponding area of the image to be enhanced according to the M component image and/or the C component image.
Optionally, before calculating the fluctuating image, the background shading image, and the text image, the method further includes: detecting the outline area of the image to be enhanced through a preset detection algorithm to obtain an outline area image; counting the numerical value of each channel of the first color space of each pixel point of the contour region image to mark the numerical maximum channel of each pixel point of the contour region image; and confirming that the channel with the largest number is the designated channel, and the proportion of the number of pixels corresponding to the channel with the largest number in the total number of the pixels of the image in the outline area is greater than a preset proportion threshold value.
Optionally, the step of fusing the fluctuating image, the background shading image, and the text image according to a preset rule to obtain an enhanced image includes: performing data type conversion on the character image to obtain a converted character image; and carrying out weighted summation on the fluctuating image, the background shading image and the converted character image, wherein the weighting coefficient of the converted character image is 1, the weighting coefficient of the fluctuating image is a positive value, and the weighting coefficient of the background shading image is a negative value.
According to another aspect of the embodiments of the present invention, there is provided an image enhancement apparatus.
An image enhancement apparatus comprising: the fluctuating image calculation module is used for calculating the fluctuating image of the image to be enhanced by utilizing the component values of each channel of the image to be enhanced in the first color space; the background shading image calculation module is used for calculating a background shading image of a corresponding area of the image to be enhanced by utilizing two channel component numerical values selected by the image to be enhanced in the first color space; the character image calculation module is used for calculating a preset channel component image of the image to be enhanced in a second color space to obtain a character image of a region corresponding to the image to be enhanced; and the image fusion module is used for fusing the fluctuating image, the background shading image and the character image according to a preset rule so as to obtain an enhanced image.
Optionally, the fluctuating image computing module is further configured to: in the RGB color space, the variance of R, G, B three-channel numerical values of each pixel point in the image to be enhanced is calculated to obtain a fluctuating image of the image to be enhanced in the form of a variance matrix.
Optionally, the fluctuating image computing module is further configured to: in the RGB color space, calculating the RGB three-channel mean value of the image to be enhanced; and calculating the variance of the RGB three-channel numerical values of the image to be enhanced by using R, G, B each single-channel numerical value and the three-channel mean value to obtain the fluctuating image of the image to be enhanced.
Optionally, the background shading image calculation module is further configured to: calculating a G component and a B component of the image to be enhanced in an RGB color space; and obtaining a background shading image of the corresponding area of the image to be enhanced according to the difference value of the G component and the B component.
Optionally, the text image calculation module is further configured to: and calculating an M component image and/or a C component image of the image to be enhanced in a CMYK color space, and obtaining a character image of a corresponding area of the image to be enhanced according to the M component image and/or the C component image.
Optionally, the image enhancement determining module is further included, configured to: detecting the outline area of the image to be enhanced through a preset detection algorithm to obtain an outline area image; counting the numerical value of each channel of the first color space of each pixel point of the contour region image to mark the numerical maximum channel of each pixel point of the contour region image; and confirming that the channel with the largest number is the designated channel, and the proportion of the number of pixels corresponding to the channel with the largest number in the total number of the pixels of the image in the outline area is greater than a preset proportion threshold value.
Optionally, the image fusion module is further configured to: performing data type conversion on the character image to obtain a converted character image; and carrying out weighted summation on the fluctuating image, the background shading image and the converted character image, wherein the weighting coefficient of the converted character image is 1, the weighting coefficient of the fluctuating image is a positive value, and the weighting coefficient of the background shading image is a negative value.
According to yet another aspect of an embodiment of the present invention, an electronic device is provided.
An electronic device, comprising: one or more processors; a memory for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the image enhancement methods provided by embodiments of the present invention.
According to yet another aspect of an embodiment of the present invention, a computer-readable medium is provided.
A computer-readable medium, on which a computer program is stored, which, when executed by a processor, implements the image enhancement method provided by embodiments of the invention.
One embodiment of the above invention has the following advantages or benefits: calculating a fluctuating image of the image to be enhanced and a background shading image of a region corresponding to the image to be enhanced in a first color space, calculating a character image of the region corresponding to the image to be enhanced in a second color space, and fusing the fluctuating image, the background shading image and the character image to obtain an enhanced image. The color information of the image to be enhanced can be fully utilized, the image to be enhanced and the background shading are prevented from being enhanced together, the problems that the contrast of the image to be enhanced is low, the image character to be enhanced is not completely segmented and the image region to be enhanced is always interfered in a large amount after an image segmentation algorithm is adopted are solved, the calculation complexity is reduced, the accuracy of character detection and the accuracy of character recognition are improved, and the data structured output level of an image OCR recognition result is further improved.
Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
FIG. 1 is a schematic diagram of the main steps of an image enhancement method according to one embodiment of the present invention;
FIG. 2 is a schematic diagram of a stamp image enhancement process according to one embodiment of the present invention;
FIGS. 3a, 3b, and 3c are schematic diagrams illustrating the enhancement and segmentation effects of various stamp images according to an embodiment of the present invention;
FIG. 4 is a schematic block diagram of an image enhancement apparatus according to an embodiment of the present invention;
FIG. 5 is an exemplary system architecture diagram in which embodiments of the present invention may be employed;
fig. 6 is a schematic block diagram of a computer system suitable for use in implementing a terminal device or server of an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention are described below with reference to the accompanying drawings, in which various details of embodiments of the invention are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
Fig. 1 is a schematic diagram of the main steps of an image enhancement method according to an embodiment of the present invention.
As shown in fig. 1, the image enhancement method according to an embodiment of the present invention mainly includes the following steps S101 to S104.
Step S101: and calculating the fluctuation image of the image to be enhanced by utilizing the component values of each channel of the image to be enhanced in the first color space.
Step S102: and calculating the background shading image of the corresponding area of the image to be enhanced by utilizing the two channel component values selected by the image to be enhanced in the first color space.
Step S103: and calculating a preset channel component image of the image to be enhanced in the second color space to obtain a character image of a region corresponding to the image to be enhanced.
Step S104: and fusing the fluctuating image of the image to be enhanced, the background shading image of the region corresponding to the image to be enhanced and the character image of the region corresponding to the image to be enhanced according to a preset rule to obtain an enhanced image.
The image to be enhanced can be a seal image, such as a seal image on a bill, and the bill can be a value-added tax invoice, a medical bill and other bills with various purposes.
The execution sequence of the steps S101, S102, and S103 in the embodiment of the present invention may be interchanged.
The first color space may be specifically an RGB color space, the second color space may be specifically a CMYK color space, CMYK representing four colors used on printing, C representing Cyan (Cyan), M representing Magenta (Magenta), Y representing Yellow (Yellow), and K representing Black (Black).
In one embodiment, before calculating the fluctuating image, the background shading image and the text image, it may be determined whether the image to be enhanced meets the set image enhancement condition. Specifically, a contour region of the image to be enhanced can be detected through a preset detection algorithm to obtain a contour region image; counting the numerical value of each channel in the first color space of each pixel point of the contour region image to mark the numerical maximum channel of each pixel point of the contour region image; and judging whether the marked channel with the largest number is a designated channel, if not, not performing image enhancement operation on the image to be enhanced, namely not performing the image enhancement steps from the step S101 to the step S104. If the channel with the largest number is marked as the designated channel, calculating the proportion of the number of pixels corresponding to the channel with the largest number in the total number of the pixels of the image in the outline area, and judging whether the proportion is larger than a preset proportion threshold value, if so, performing image enhancement operation on the image to be enhanced, namely, performing the image enhancement steps from the step S101 to the step S104, otherwise, not performing the image enhancement operation on the image to be enhanced.
The predetermined detection algorithm may be an ellipse detection algorithm based on arc support line segments, which can detect ellipses and circles, with the input being an image and the output being the parameters (cx, cy, a, b) of the detected ellipse, where cx and cy are the abscissa and ordinate of the center of the circle, respectively, and a and b are the radii of the major and minor axes of the ellipse, respectively (the same numerical values of a and b are circles). Taking a stamp image with an image to be enhanced as an elliptical outline as an example, the inner edge and the outer edge of the elliptical outline of the stamp image (namely, elliptical rings) can be detected through the algorithm, and then an outline area image of the elliptical stamp, namely, an area image between the elliptical rings is determined.
The embodiment of the invention can carry out image enhancement on the seal with the appointed color type in a targeted manner by judging whether the image to be enhanced meets the set image enhancement condition in advance. For example, in a scene that an image enhancement needs to be performed on a red stamp image, taking a first color space as an RGB color space as an example, after a contour region of the to-be-enhanced stamp image is detected according to the above method and the contour region image is obtained, determining a three-channel numerical value size relationship of each pixel R, G, B in the contour region image to mark a maximum channel of a numerical value of each pixel point of the contour region image, for example, if the R channel numerical value is the maximum in each channel numerical value of R, G, B of a certain pixel point, the maximum channel of the numerical value of the pixel point is marked as an R channel, marking each pixel point of the contour region image with one channel according to the method, and counting which channel the marked channel is the most numerous. Because the red stamp image needs to be subjected to image enhancement, namely, the designated channel is an R channel, whether the channel with the largest number is the R channel is judged, if so, the proportion of the number of the pixels of the R channel marked in the outline area image to the total number of the pixels of the outline area image is counted, if the proportion is larger than a preset proportion threshold value, the stamp image to be enhanced is determined to be a pre-designated red stamp image, and the red stamp image is continuously subjected to image enhancement processing. If the marked channel with the largest number is not the R channel or the ratio is not larger than the preset ratio threshold value, the image enhancement processing is not carried out. The embodiment of the invention can fully meet the requirement of image enhancement on the stamp image with a specific color type.
In one embodiment, the step of calculating a fluctuating image of the image to be enhanced by using the values of the channel components of the image to be enhanced in the first color space may include: in the RGB color space, the variance of R, G, B three-channel numerical values of each pixel point in the image to be enhanced is calculated to obtain a fluctuating image of the image to be enhanced in the form of a variance matrix.
Variance matrix MstdMay be in the form of:
wherein, the variance of each pixel point is:
wherein i belongs to [0, m-1 ]; j is belonged to [0, n-1 ];
in another embodiment, a more simplified fluctuation image calculation method is adopted, so that the time consumption of the operation can be reduced. Specifically, firstly, in an RGB color space, an RGB three-channel mean value of the image to be enhanced is calculated, and then a variance of the RGB three-channel numerical values in the image to be enhanced is calculated by using R, G, B each single-channel numerical value and the three-channel mean value, so as to obtain a fluctuating image of the image to be enhanced.
For example, Mean _ RGB represents the RGB three-channel Mean value of the image to be enhanced, R _ img, G _ img, and B _ img represent the single-channel value of R, G, B of the image to be enhanced, respectively, then the variance S of the RGB three-channel value of the image to be enhanced, i.e. the fluctuating image, is obtained by the following operations:
R_mean＝abs(R_img-Mean_rgb)；
G_mean＝abs(G_img-Mean_rgb)；
B_mean＝abs(B_img-Mean_rgb)；
S＝(R_mean+G_mean+B_mean)./sqrt(3)；
where abs represents the absolute value of the calculation, and sqrt represents the open square root.
The variance image of R, G, B three-channel components is calculated in the color space RGB, the seal image color change information can be effectively reflected, the interference factors such as bill highlight background, bill machine typewriting (type) and the like are small in three-channel numerical value difference, and the interference factors can be eliminated by calculating the variance image, so that the image enhancement effect is improved.
The step of calculating the background shading image of the corresponding region of the image to be enhanced by using the two channel component values selected by the image to be enhanced in the first color space may include: calculating a G component and a B component of an image to be enhanced in an RGB color space; and obtaining a background shading image of the corresponding area of the image to be enhanced according to the difference value of the G component and the B component. The difference image of G, B components is calculated in the color space RGB, so that the background shading information of the stamp image can be effectively reflected.
In one embodiment, calculating a preset channel component image of the image to be enhanced in the second color space to obtain a text image of a region corresponding to the image to be enhanced specifically includes: and calculating the M component image of the image to be enhanced in the CMYK color space to obtain the character image of the corresponding area of the image to be enhanced.
In another embodiment, calculating a preset channel component image of the image to be enhanced in the second color space to obtain a text image of a region corresponding to the image to be enhanced specifically includes: and calculating the C component image of the image to be enhanced in the CMYK color space to obtain the character image of the corresponding area of the image to be enhanced.
In another embodiment, calculating a preset channel component image of the image to be enhanced in the second color space to obtain a text image of a region corresponding to the image to be enhanced specifically includes: and calculating an M component image and a C component image of the image to be enhanced in the CMYK color space, and adding the M component image and the C component image to obtain a character image of the corresponding area of the image to be enhanced.
The step of fusing the fluctuating image, the background shading image and the text image according to a preset rule to obtain an enhanced image may include: performing data type conversion on the character image in the region corresponding to the image to be enhanced to obtain a converted character image; weighting and summing a fluctuation image of an image to be enhanced, a background shading image of a corresponding area of the image to be enhanced and the converted character image, wherein the weighting coefficient of the converted character image is 1, the weighting coefficient of the background shading image and the weighting coefficient of the fluctuation image can be set according to an empirical value, and the specifically set rule meets the following requirements: the weighting coefficient of the fluctuating image is a positive value, and the weighting coefficient of the background shading image is a negative value.
In a preferred embodiment, the weighting coefficients for the fluctuating image and the background shading image are 1 and-1, respectively. In this case, the image fusion effect is optimal, and thus the image enhancement effect is also optimal.
The data type conversion of the character image in the corresponding area of the image to be enhanced refers to adjusting the original data type (double type) of the character image to unsigned integer to meet the requirement of image fusion operation.
The prior art bill image seal image contrast is low, the seal characters are cut apart incompletely and adopt the image to cut apart the problem that the seal region often remains a large amount of interferences behind the algorithm, and the reason mainly divide into two aspects: firstly, bill images often have complex texture backgrounds; secondly, the stamp is generally covered above the preprinted characters and the machine-printed characters of the bill, so that the characters of the stamp are difficult to distinguish. When the image enhancement method provided by the embodiment of the invention is applied to the segmentation of the note image seal, the technical problems of low seal character contrast and difficulty in effective segmentation and extraction caused by complex background shading and various face characters of the note can be solved.
The image enhancement method of the embodiment of the invention utilizes the characteristic that the numerical difference of three channels of components of the stamp image in the color space RGB is larger to calculate the variance image of the stamp, then calculate the difference image of G, B components, then calculate the M component and/or C component image in the color space CMYK, and finally fuse the calculation results of all links, thus obtaining the enhancement effect of the stamp character image.
FIG. 2 shows a stamp image enhancement process according to an embodiment of the present invention.
According to an embodiment of the present invention, after receiving the input stamp image, as shown in fig. 2, the stamp image enhancement process includes steps S201 to S204 as follows.
Step S201: in the RGB color space, the variance of the stamp image is calculated, and the fluctuation image of R, G, B three-channel components of the stamp image is obtained.
Step S202: in the RGB color space, the difference value of the components of the stamp image G, B is calculated, and the background shading image of the stamp area is obtained.
Step S203: in the CMYK color space, M components of the stamp image are calculated, and the character image of the stamp area is obtained.
Step S204: and carrying out weighted summation on the fluctuating image, the shading image and the character image so as to obtain the stamp enhanced image.
Taking the seal image of the charge bill for medical (emergency) consultation as an example, the variance of the three-channel numerical value of R, G, B of each pixel point of the seal image is calculated in the RGB color space, and a variance matrix M is obtainedstd：
The variance of each pixel is:
wherein the content of the first and second substances,
i∈[0,m-1]；j∈[0,n-1]；
in RGB color space, a difference M of the components of stamp image G, B is calculatedgb：
Mgb＝|G-B|
Calculating stamp image M component image M in CMYK color spacem：
Wherein the content of the first and second substances,
R'＝R/255.0
G'＝G/255.0
B'＝B/255.0
K＝1-max(R',G',B')
calculating variance image MstdDifference image MgbAnd M component image MmTo obtain a stamp enhanced image Men：
Men＝Mm×255+α×Mstd+β×Mgb
Wherein α and β are weighting coefficients, which are empirical values and are set to 1 and-1. M, respectively, in this embodimentmX 255 for M component image MmFor the purpose of converting M into data typesmThe original data type (double type) is adjusted to unsigned integer for image fusion.
As an alternative embodiment, the stamp image C component image M is computed in the CMYK color spacec：
The obtained seal enhanced image MenM in the formula (1)mCan be replaced by Mc。
As another alternative embodiment, the above-mentioned stamp enhanced image M is obtainedenM in the formula (1)mCan be replaced by Mc+Mm。
The stamp image of the embodiment of the present invention may be a red stamp or a blue stamp, and the image enhancement and segmentation effects for various stamps are shown in fig. 3a, 3b, and 3c, where fig. 3a is a red stamp image enhancement and segmentation effect diagram for a medical department emergency charge ticket, fig. 3b is a red stamp image enhancement and segmentation effect diagram for a national value-added tax special invoice, fig. 3c is a blue stamp image enhancement and segmentation effect diagram for a medical department emergency charge ticket, in fig. 3a, 3b, and 3c, the first image in each drawing is an original image of a stamp, the second image is an enhancement effect diagram of a stamp, and the third image is a segmentation effect diagram of a stamp. The embodiment of the invention has better image enhancement effect on red and blue seals commonly existing in bills in the fields of current medical treatment claim settlement, financial reimbursement and the like.
The method based on the combination of the color space RGB and the CMYK can greatly inhibit the interference of the bill shading and the bill surface characters on the division of the seal characters, improve the contrast of the image characters of the seal, has low calculation complexity, meets the real-time processing requirement of a bill OCR system, lays a foundation for the subsequent bill OCR system to the detection and the recognition of the seal characters, is suitable for most bill OCR systems, is favorable for improving the recognition rate of the seal characters, effectively improves the level of structured output of the bill recognition result data, and further improves the manual substitution rate of the bill OCR system.
Fig. 4 is a schematic block diagram of a main block of an image enhancement apparatus according to an embodiment of the present invention.
As shown in fig. 4, the image enhancement apparatus 400 according to an embodiment of the present invention mainly includes: a fluctuating image calculation module 401, a background shading image calculation module 402, a character image calculation module 403 and an image fusion module 404.
The fluctuating image calculating module 401 is configured to calculate a fluctuating image of the image to be enhanced by using each channel component value of the image to be enhanced in the first color space.
A background shading image calculating module 402, configured to calculate a background shading image of a region corresponding to an image to be enhanced by using two channel component values selected by the image to be enhanced in the first color space.
The text image calculating module 403 is configured to calculate a preset channel component image of the image to be enhanced in the second color space, so as to obtain a text image of a region corresponding to the image to be enhanced.
The image fusion module 404 is configured to fuse a fluctuating image of the image to be enhanced, a background shading image of a region corresponding to the image to be enhanced, and a text image of a region corresponding to the image to be enhanced according to a preset rule, so as to obtain an enhanced image.
The image to be enhanced can be a seal image, such as a seal image on a bill, and the bill can be a value-added tax invoice, a medical bill and other bills with various purposes.
In one embodiment, the image enhancement apparatus 400 may further include an image enhancement determining module configured to: detecting a contour region of an image to be enhanced through a preset detection algorithm to obtain a contour region image; counting the numerical value of each channel in the first color space of each pixel point of the contour region image to mark the numerical maximum channel of each pixel point of the contour region image; and confirming that the channel with the largest number is the designated channel, and the proportion of the number of pixels corresponding to the channel with the largest number in the total number of the pixels of the image in the contour region is larger than a preset proportion threshold value.
In one embodiment, the fluctuating image computation module 401 is specifically configured to: in the RGB color space, the variance of R, G, B three-channel numerical values of each pixel point in the image to be enhanced is calculated to obtain a fluctuating image of the image to be enhanced in the form of a variance matrix.
In another embodiment, the fluctuation image calculation module 401 may further calculate the fluctuation image in a more simplified fluctuation image calculation manner, so as to reduce the time consumption of the operation. Specifically, firstly, in an RGB color space, an RGB three-channel mean value of the image to be enhanced is calculated, and then a variance of the RGB three-channel numerical values in the image to be enhanced is calculated by using R, G, B each single-channel numerical value and the three-channel mean value, so as to obtain a fluctuating image of the image to be enhanced.
The background shading image calculation module 402 is specifically configured to: calculating a G component and a B component of an image to be enhanced in an RGB color space; and obtaining a background shading image of the corresponding area of the image to be enhanced according to the difference value of the G component and the B component.
In an embodiment, the text image calculation module 403 may be specifically configured to: and calculating the M component of the image to be enhanced in the CMYK color space to obtain the character image of the corresponding area of the image to be enhanced.
In another embodiment, the text image calculation module 403 may be specifically configured to: and calculating the C component image of the image to be enhanced in the CMYK color space to obtain the character image of the corresponding area of the image to be enhanced.
In another embodiment, the text image calculation module 403 may be specifically configured to: and calculating an M component image and a C component image of the image to be enhanced in the CMYK color space, and adding the M component image and the C component image to obtain a character image of the corresponding area of the image to be enhanced.
The image fusion module 404 may be specifically configured to: performing data type conversion on the character image in the region corresponding to the image to be enhanced to obtain a converted character image; weighting and summing a fluctuation image of an image to be enhanced, a background shading image of a corresponding area of the image to be enhanced and the converted character image, wherein the weighting coefficient of the converted character image is 1, the weighting coefficient of the background shading image and the weighting coefficient of the fluctuation image can be set according to an empirical value, and the specifically set rule meets the following requirements: the weighting coefficient of the fluctuating image is a positive value, and the weighting coefficient of the background shading image is a negative value.
In a preferred embodiment, the weighting coefficients of the fluctuating image and the background shading image are 1 and-1, respectively.
The data type conversion of the character image in the corresponding area of the image to be enhanced refers to adjusting the original data type (double type) of the character image to unsigned integer to meet the requirement of image fusion operation.
In addition, the detailed implementation of the image enhancement apparatus in the embodiment of the present invention has been described in detail in the above-mentioned image enhancement method, and therefore, the repeated content will not be described again.
Fig. 5 shows an exemplary system architecture 500 to which the image enhancement method or image enhancement apparatus of an embodiment of the present invention may be applied.
As shown in fig. 5, the system architecture 500 may include terminal devices 501, 502, 503, a network 504, and a server 505. The network 504 serves to provide a medium for communication links between the terminal devices 501, 502, 503 and the server 505. Network 504 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 501, 502, 503 to interact with a server 505 over a network 504 to receive or send messages or the like. The terminal devices 501, 502, 503 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 501, 502, 503 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 505 may be a server providing various services, such as a background management server (for example only) providing support for shopping websites browsed by users using the terminal devices 501, 502, 503. The backend management server may analyze and perform other processing on the received data such as the product information query request, and feed back a processing result (for example, target push information, product information — just an example) to the terminal device.
It should be noted that the image enhancement method provided by the embodiment of the present invention is generally executed by the server 505, and accordingly, the image enhancement apparatus is generally disposed in the server 505.
It should be understood that the number of terminal devices, networks, and servers in fig. 5 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 6, shown is a block diagram of a computer system 600 suitable for use in implementing a terminal device or server of an embodiment of the present application. The terminal device or the server shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The above-described functions defined in the system of the present application are executed when the computer program is executed by the Central Processing Unit (CPU) 601.
It should be noted that the computer readable medium shown in the present invention can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules described in the embodiments of the present invention may be implemented by software or hardware. The described modules may also be provided in a processor, which may be described as: a processor comprises a fluctuating image computing module, a background shading image computing module, a character image computing module and an image fusion module. The names of these modules do not in some cases constitute a limitation on the module itself, for example, the fluctuation image calculation module may also be described as "a module for calculating a fluctuation image of an image to be enhanced using each channel component value of the image to be enhanced in the first color space".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to comprise: calculating a fluctuating image of the image to be enhanced by utilizing the component values of each channel of the image to be enhanced in the first color space; calculating a background shading image of a corresponding area of the image to be enhanced by using two channel component values selected by the image to be enhanced in the first color space; calculating a preset channel component image of the image to be enhanced in a second color space to obtain a character image of a region corresponding to the image to be enhanced; and fusing the fluctuating image, the background shading image and the character image according to a preset rule to obtain an enhanced image.
According to the technical scheme of the embodiment of the invention, the fluctuating image of the image to be enhanced and the background shading image of the corresponding area of the image to be enhanced are calculated in the first color space, the character image of the corresponding area of the image to be enhanced is calculated in the second color space, and the fluctuating image, the background shading image and the character image are fused to obtain the enhanced image. The color information of the image to be enhanced can be fully utilized, the image to be enhanced and the background shading are prevented from being enhanced together, the problems that the contrast of the image to be enhanced is low, the image character to be enhanced is not completely segmented and the image region to be enhanced is always interfered in a large amount after an image segmentation algorithm is adopted are solved, the calculation complexity is reduced, the accuracy of character detection and the accuracy of character recognition are improved, and the data structured output level of an image OCR recognition result is further improved.
The above-described embodiments should not be construed as limiting the scope of the invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions can occur, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An image enhancement method, comprising:
calculating a fluctuating image of the image to be enhanced by utilizing the component values of each channel of the image to be enhanced in the first color space;
calculating a background shading image of a corresponding area of the image to be enhanced by using two channel component values selected by the image to be enhanced in the first color space;
calculating a preset channel component image of the image to be enhanced in a second color space to obtain a character image of a region corresponding to the image to be enhanced;
and fusing the fluctuating image, the background shading image and the character image according to a preset rule to obtain an enhanced image.
2. The method according to claim 1, wherein calculating a fluctuating image of the image to be enhanced by using each channel component value of the image to be enhanced in the first color space comprises:
in the RGB color space, the variance of R, G, B three-channel numerical values of each pixel point in the image to be enhanced is calculated to obtain a fluctuating image of the image to be enhanced in the form of a variance matrix.
3. The method according to claim 1, wherein calculating a fluctuating image of the image to be enhanced by using each channel component value of the image to be enhanced in the first color space comprises:
in the RGB color space, calculating the RGB three-channel mean value of the image to be enhanced;
and calculating the variance of the RGB three-channel numerical values of the image to be enhanced by using R, G, B each single-channel numerical value and the three-channel mean value to obtain the fluctuating image of the image to be enhanced.
4. The method according to claim 1, wherein the calculating the background shading image of the corresponding region of the image to be enhanced by using the two selected channel component values in the first color space of the image to be enhanced comprises:
calculating a G component and a B component of the image to be enhanced in an RGB color space;
and obtaining a background shading image of the corresponding area of the image to be enhanced according to the difference value of the G component and the B component.
5. The method according to claim 1, wherein the calculating a preset channel component image of the image to be enhanced in a second color space to obtain a text image of a region corresponding to the image to be enhanced comprises:
and calculating an M component image and/or a C component image of the image to be enhanced in a CMYK color space, and obtaining a character image of a corresponding area of the image to be enhanced according to the M component image and/or the C component image.
6. The method according to claim 1, wherein before calculating the fluctuating image, the background shading image, and the text image, further comprising:
detecting the outline area of the image to be enhanced through a preset detection algorithm to obtain an outline area image;
counting the numerical value of each channel of the first color space of each pixel point of the contour region image to mark the numerical maximum channel of each pixel point of the contour region image;
and confirming that the channel with the largest number is the designated channel, and the proportion of the number of pixels corresponding to the channel with the largest number in the total number of the pixels of the image in the outline area is greater than a preset proportion threshold value.
7. The method according to claim 1, wherein the step of fusing the fluctuating image, the background shading image and the text image according to a preset rule to obtain an enhanced image comprises:
performing data type conversion on the character image to obtain a converted character image;
and carrying out weighted summation on the fluctuating image, the background shading image and the converted character image, wherein the weighting coefficient of the converted character image is 1, the weighting coefficient of the fluctuating image is a positive value, and the weighting coefficient of the background shading image is a negative value.
8. An image enhancement apparatus, comprising:
the fluctuating image calculation module is used for calculating the fluctuating image of the image to be enhanced by utilizing the component values of each channel of the image to be enhanced in the first color space;
the background shading image calculation module is used for calculating a background shading image of a corresponding area of the image to be enhanced by utilizing two channel component numerical values selected by the image to be enhanced in the first color space;
the character image calculation module is used for calculating a preset channel component image of the image to be enhanced in a second color space to obtain a character image of a region corresponding to the image to be enhanced;
and the image fusion module is used for fusing the fluctuating image, the background shading image and the character image according to a preset rule so as to obtain an enhanced image.
9. An electronic device, comprising:
one or more processors;
a memory for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method recited in any of claims 1-7.
10. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911165004.4A CN111028186B (en) | 2019-11-25 | 2019-11-25 | Image enhancement method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911165004.4A CN111028186B (en) | 2019-11-25 | 2019-11-25 | Image enhancement method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111028186A true CN111028186A (en) | 2020-04-17 |
| CN111028186B CN111028186B (en) | 2023-07-04 |
Family
ID=70203443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911165004.4A Active CN111028186B (en) | 2019-11-25 | 2019-11-25 | Image enhancement method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111028186B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111611866A (en) * | 2020-04-23 | 2020-09-01 | 淮阴工学院 | Flame detection and identification method and system based on YCrCb and LAB color spaces |
| CN112116542A (en) * | 2020-09-24 | 2020-12-22 | 西安宇视信息科技有限公司 | Image contrast enhancement method, device, electronic equipment and storage medium |
| CN114882127A (en) * | 2022-05-19 | 2022-08-09 | 北京奥乘智能技术有限公司 | Image processing method, image processing device, storage medium and computing equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070160285A1 (en) * | 2002-05-01 | 2007-07-12 | Jay Stephen Gondek | Method and apparatus for associating image enhancement with color |
| CN105445277A (en) * | 2015-11-12 | 2016-03-30 | 湖北工业大学 | Visual and intelligent detection method for surface quality of FPC (Flexible Printed Circuit) |
| US20160171663A1 (en) * | 2014-12-16 | 2016-06-16 | Sogang University Research Foundation | Image processing devices for suppressing color fringe, and image sensor modules and electronic devices including the same |
| CN105791710A (en) * | 2016-04-11 | 2016-07-20 | 北京英泰智科技股份有限公司 | Signal lamp image enhancement processing method |
| US20160379593A1 (en) * | 2014-10-14 | 2016-12-29 | Digital Vision Enhancement Inc | Image transforming vision enhancement device |
| CN107220646A (en) * | 2017-05-25 | 2017-09-29 | 杭州健培科技有限公司 | A kind of medical image Text region Enhancement Method for going ambient interferences |
| CN111191657A (en) * | 2019-11-19 | 2020-05-22 | 泰康保险集团股份有限公司 | Character recognition method and device and computer readable storage medium |
-
2019
- 2019-11-25 CN CN201911165004.4A patent/CN111028186B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070160285A1 (en) * | 2002-05-01 | 2007-07-12 | Jay Stephen Gondek | Method and apparatus for associating image enhancement with color |
| US20160379593A1 (en) * | 2014-10-14 | 2016-12-29 | Digital Vision Enhancement Inc | Image transforming vision enhancement device |
| US20160171663A1 (en) * | 2014-12-16 | 2016-06-16 | Sogang University Research Foundation | Image processing devices for suppressing color fringe, and image sensor modules and electronic devices including the same |
| CN105445277A (en) * | 2015-11-12 | 2016-03-30 | 湖北工业大学 | Visual and intelligent detection method for surface quality of FPC (Flexible Printed Circuit) |
| CN105791710A (en) * | 2016-04-11 | 2016-07-20 | 北京英泰智科技股份有限公司 | Signal lamp image enhancement processing method |
| CN107220646A (en) * | 2017-05-25 | 2017-09-29 | 杭州健培科技有限公司 | A kind of medical image Text region Enhancement Method for going ambient interferences |
| CN111191657A (en) * | 2019-11-19 | 2020-05-22 | 泰康保险集团股份有限公司 | Character recognition method and device and computer readable storage medium |
Non-Patent Citations (2)
| Title |
|---|
| SUMIT KUSHWAHA等: "Study and Analysis of Various Image Enhancement Method using MATLAB", 《INTERNATIONAL JOURNAL OF COMPUTER SCIENCES AND ENGINEERING》, vol. 3, no. 1, pages 15 - 19 * |
| 朱振杰;王红茹;: "基于暗原色先验原理的水下图像增强", 图学学报, no. 03, pages 76 - 85 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111611866A (en) * | 2020-04-23 | 2020-09-01 | 淮阴工学院 | Flame detection and identification method and system based on YCrCb and LAB color spaces |
| CN112116542A (en) * | 2020-09-24 | 2020-12-22 | 西安宇视信息科技有限公司 | Image contrast enhancement method, device, electronic equipment and storage medium |
| CN112116542B (en) * | 2020-09-24 | 2024-03-08 | 西安宇视信息科技有限公司 | Image contrast enhancement method, device, electronic equipment and storage medium |
| CN114882127A (en) * | 2022-05-19 | 2022-08-09 | 北京奥乘智能技术有限公司 | Image processing method, image processing device, storage medium and computing equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111028186B (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111028186B (en) | Image enhancement method and device | |
| CA3018437C (en) | Optical character recognition utilizing hashed templates | |
| WO2022156178A1 (en) | Image target comparison method and apparatus, computer device and readable storage medium | |
| CN106991423A (en) | Whether the method and device of watermark is included in identification specification picture | |
| CN105046553A (en) | Cloud intelligent invoice recognition inspection system and method based on mobile phone | |
| CN110895696A (en) | Image information extraction method and device | |
| Tang et al. | Robust image hashing with singular values of quaternion SVD | |
| CN111724396B (en) | Image segmentation method and device, computer readable storage medium and electronic equipment | |
| CN110895811B (en) | Image tampering detection method and device | |
| CN110222694A (en) | Image processing method, device, electronic equipment and computer-readable medium | |
| Chatterjee et al. | LSB based steganography with OCR: an intelligent amalgamation | |
| CN101320425B (en) | Image processing apparatus, image forming apparatus, and image processing method | |
| CN102541480B (en) | Filtering method and device for printing | |
| CN110599478B (en) | Image area copying and pasting tampering detection method | |
| CN111898544B (en) | Text image matching method, device and equipment and computer storage medium | |
| CN110069907A (en) | Big data source tracing method and system based on digital watermarking | |
| CN112581344A (en) | Image processing method and device, computer equipment and storage medium | |
| Oh et al. | Low-complexity and robust comic fingerprint method for comic identification | |
| CN112132000B (en) | Living body detection method, living body detection device, computer readable medium and electronic equipment | |
| CN113065407B (en) | Financial bill seal erasing method based on attention mechanism and generation countermeasure network | |
| CN112215237B (en) | Image processing method and device, electronic equipment and computer readable storage medium | |
| CN110826569A (en) | Bill image preprocessing method and device, medium and electronic equipment | |
| CN111126151A (en) | Method, apparatus, device and medium for identifying field in bill image | |
| CN113591849A (en) | File review method, device, equipment and storage medium based on signature identification | |
| CN114764839A (en) | Dynamic video generation method and device, readable storage medium and terminal equipment |
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 |