CN105513010A - Document scanning processing apparatus and processing method - Google Patents
Document scanning processing apparatus and processing method Download PDFInfo
- Publication number
- CN105513010A CN105513010A CN201510989613.7A CN201510989613A CN105513010A CN 105513010 A CN105513010 A CN 105513010A CN 201510989613 A CN201510989613 A CN 201510989613A CN 105513010 A CN105513010 A CN 105513010A
- Authority
- CN
- China
- Prior art keywords
- file
- picture
- interface
- card
- max
- 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
- 238000003672 processing method Methods 0.000 title abstract 3
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims abstract description 20
- 230000006870 function Effects 0.000 claims abstract description 20
- 230000005540 biological transmission Effects 0.000 claims abstract description 11
- 238000000034 method Methods 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 11
- 230000002708 enhancing effect Effects 0.000 claims description 10
- 230000008878 coupling Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 6
- 238000005859 coupling reaction Methods 0.000 claims description 6
- 230000007704 transition Effects 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000004321 preservation Methods 0.000 claims description 4
- 238000011084 recovery Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 241001292396 Cirrhitidae Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/14—Transformations for image registration, e.g. adjusting or mapping for alignment of images
- G06T3/147—Transformations for image registration, e.g. adjusting or mapping for alignment of images using affine transformations
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Character Input (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a document scanning processing apparatus and processing method. The document scanning processing apparatus is provided with an embedded system. The embedded system includes a CPU, a DDR or NandFlash memory, a camera connected with the CPU through an I/O interface, an SD card/CF card storage interface, a USB interface and an Internet or WIFI transmission interface; the DDR or NandFlash memory is connected with the CPU through a memory interface; and an operating system and a computer vision dedicated function library are solidified in the DDR or NandFlash memory. The document scanning processing method includes the following steps that: an original color document image is obtained; the original color document image is grayed; matching enhancement is performed on the gray document image, so that an enhanced gray document image can be obtained; overall binarization is performed on the enhanced gray document image, so that a binarized document edge image can be obtained; the maximum contour and boundary points of an effective area are determined; affine restoration transform is performed on the original image; and histogram equalization is performed on an image obtained through the affine restoration transform, and contrast and brightness adjustment is carried out, so that an adjusted color document image can be obtained, and the adjusted color document image is transmitted through a USB, an Ethernet or WiFi, or is saved to an SD card or a CF card.
Description
Technical field
The present invention relates to the treatment facility and disposal route that are applied to file scanning, especially relate to a kind of in file scanning process, image exists affine deformation distortion, inclination, brightness is lower, contrast is lower etc. file scanning treatment facility that defect carries out to be improved and disposal route.
Background technology
Along with the electronic degree of daily life and working environment is more and more higher, people can face by after the scanning of a large amount of paper document with stored in computing machine, with stored in computing machine after document scanning of materials, make the more convenient and specification of the preservation of file, transmission and management.Electronic document preserve with backup in information department, treasurer's department, the department such as file administration and other industrial and commercial enterprises popularize gradually.In prior art, because the putting position of document is not fixed, its imaging in camera often has the phenomenon such as larger affine deformation and certain inclination, luminance shortage, makes the Word message of file and picture be not easy to observation and reads, and the reading and the backup that reduce electronic document are worth.
The file and picture that current file scanning equipment many employings embedded circuit board acquires taking pictures carries out simple transmission, and adopt special software program to process image at PC end, artificial setting is needed to need the region of rotational correction and the type of rectification in processing procedure, lack certain artificial intelligence, work efficiency is lower.
CN1908964A discloses a kind of method of linearity geometry deformation automatic straightening on February 7th, 2007, has specifically separated a kind of method of linearity geometry deformation automatic straightening, has comprised the following steps:
(1) image information of image capture device collection identification object, and object images is converted to bianry image;
(2) object images step (1) obtained carries out similarity judgement with the target image prestored in systems in which, if similar, then enter step (3), if dissimilar, then system directly determines that object images is different from the target image prestored in system, and described target image is bianry image;
(3) deformation behaviour of analytic target image, determine the linear deformation relation between object images and target image, in plane coordinate system, calculating object image and the relative deformation of target image in X, Y-axis, thus calculate the relative deformation coefficient in X, Y-axis;
(4) using one of target image and object images as reference standard, the deformation coefficient according to obtaining in step (3) carries out mathematical interpolation rectification to another image, obtains the optimum matching of two images;
(5) utilize system to identify the image after optimum matching, judge object images and the identical of target image or difference, thus correctly judge the authenticity of object images.
This method provide adaptive line geometry deformation relative between target image with object images to correct, but cannot automatically effectively process phenomenons such as the affine deformation in scanning process and certain inclination, luminance shortage.
Summary of the invention
The present invention is directed to the deficiencies in the prior art, design a kind of file scanning treatment facility and disposal route, in file scanning process, the defects such as image exists affine deformation distortion, inclination, brightness is lower, contrast is lower are improved.
In order to solve the problems of the technologies described above, on the one hand, the invention provides a kind of file scanning treatment facility, it has embedded system, and described embedded system comprises CPU processor; Be connected with described CPU processor by memory interface, and have cured DDR or the NandFlash memory in operating system and computer vision special purpose function storehouse; The camera be connected by I/O interface with described CPU processor, SD card/CF card memory interface, USB interface, Ethernet or WIFI transmission interface.
As optimal technical scheme, file scanning treatment facility provided by the invention, described CPU processor is arm processor.
In order to solve the problems of the technologies described above, on the other hand, the invention provides a kind of file scanning disposal route, based on the application of file scanning treatment facility, described file scanning treatment facility has embedded system, and described embedded system comprises CPU processor; Be connected with described CPU processor by memory interface, and have cured DDR or the NandFlash memory in operating system and computer vision special purpose function storehouse; The camera be connected by I/O interface with described CPU processor, SD card/CF card memory interface, USB interface, Ethernet or WIFI transmission interface, is characterized in that: file scanning process comprises the following steps:
1) original color file and picture is obtained by camera;
2) by original color file and picture gray processing, gray scale file and picture is obtained;
3) adopt
coupling strengthen operator K
matchcarry out coupling to described gray scale file and picture to strengthen, the gray scale that is enhanced file and picture;
4) Da-Jin algorithm is adopted to obtain the overall binaryzation threshold values T of described enhancing gray scale file and picture, and with new threshold values T
1=k
1t and T
2=k
2t carries out segmentation binaryzation, by gray-scale value at T to described enhancing gray scale file and picture
1and T
2between pixel assignment be 1, all the other gray-value pixel assignment are 0, obtain the document edges image of binaryzation; Wherein 0.5≤k
1< 1,1 < k
2≤ 1.5;
5) profile in described computer vision special purpose function storehouse is adopted to find function to described document edges image, find out its all profile, and preservation enters structure contours, contains the coordinate of frontier point corresponding to each profile in structure contours;
6) calculate the area that each profile surrounds, and adopt traversal to compare to draw and there is maximum area and the frontier point coordinate of profile for quadrilateral, and obtain four frontier point coordinate P corresponding to maximum area profile according to the relative position order of coordinate points
1, P
2, P
3, P
4, wherein P
i_x and P
i_y represents x coordinate and the y coordinate of i-th frontier point respectively, i=1,2,3,4;
7) according to P
ithe coordinate position of point, obtains the breadth extreme W treating affine recovery region
maxwith maximum height H
max, W
max=max{W
1, W
2, H
max=max{H
1, H
2;
Wherein width
8) objective matrix that initialization one is empty, wherein the original width of this matrix is W
max, be highly H
max, and obtain the affine transition matrix from gray scale file and picture to objective matrix according to affine transformational relation function;
9) according to affine transition matrix, original color file and picture is converted to targeted color file and picture;
10) the histogram equalization function of standard is used, histogram equalization is carried out to targeted color file and picture, adjusts its contrast and brightness, the color document images after being adjusted, color document images after adjustment through USB, Ethernet or wifi transmission, or is saved in SD card or CF card.
As optimal technical scheme, file scanning disposal route provided by the invention, adopts Da-Jin algorithm to obtain the overall binaryzation threshold values T of described enhancing gray scale file and picture, and with new threshold values T
1=k
1t and T
2=k
2t carries out in segmentation binarization to described enhancing gray scale file and picture, k
1=0.8, k
2=1.25.
Technical scheme provided by the invention, propose embedded circuit board and carry embedded OS, by transplanting, computer vision function library etc. is installed, online process and affine rectification can be carried out to scanning the image obtained in embedded circuit board, and its brightness and contrast is adjusted automatically, be convenient to manual read and later stage Intelligent Character detection.
Accompanying drawing explanation
Accompanying drawing is used to provide a further understanding of the present invention, and form a application's part, schematic description and description of the present invention for explaining the present invention, but does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is embodiment file scanning treatment facility composition schematic diagram;
Fig. 2 is the relative position figure of quadrangular configuration four anchor points in embodiment.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail.
File scanning treatment facility as shown in Figure 1, has embedded system, and described embedded system comprises arm processor; Be connected with arm processor by memory interface, and have cured DDR or the NandFlash memory in operating system and computer vision special purpose function storehouse; The camera be connected by I/O interface with arm processor, SD card/CF card memory interface, USB interface, Ethernet and WIFI transmission interface.
File scanning treatment facility adopts the embedded OS based on ARM kernel, as WindowsCE, Windows10, Linux, Android etc., and all kinds of computer vision storehouse of installation can be transplanted on this embedded OS, as OpenCV, HALCON etc., to manipulate camera more efficient quick and to carry out image procossing.File scanning process comprises the following steps:
1) original color file and picture is obtained by camera;
2) by original color file and picture gray processing, gray scale file and picture is obtained;
3) adopt
coupling strengthen operator K
matchcarry out coupling to described gray scale file and picture to strengthen, the gray scale that is enhanced file and picture;
4) Da-Jin algorithm is adopted to obtain the overall binaryzation threshold values T of described enhancing gray scale file and picture, and with new threshold values T
1=k
1t and T
2=k
2t carries out segmentation binaryzation, by gray-scale value at T to described enhancing gray scale file and picture
1and T
2between pixel assignment be 1, all the other gray-value pixel assignment are 0, obtain the document edges image of binaryzation; Wherein 0.5≤k
1< 1,1 < k
2≤ 1.5;
5) profile in described computer vision special purpose function storehouse is adopted to find function to described document edges image, find out its all profile, and preservation enters structure contours, contains the coordinate of frontier point corresponding to each profile in structure contours;
6) calculate the area that each profile surrounds, and adopt traversal to compare to draw and there is maximum area and the frontier point coordinate of profile for quadrilateral, and obtain four frontier point coordinate P corresponding to maximum area profile according to the relative position order of coordinate points
1, P
2, P
3, P
4, refer to Fig. 2, use P
i_x and P
i_y represents x coordinate and the y coordinate of i-th frontier point respectively, i=1,2,3,4;
7) according to P
ithe coordinate position of point, obtains the breadth extreme W treating affine recovery region
maxwith maximum height H
max, W
max=max{W
1, W
2, H
max=max{H
1, H
2;
Wherein width
8) objective matrix that initialization one is empty, wherein the original width of this matrix is W
max, be highly H
max, and obtain the affine transition matrix from gray scale file and picture to objective matrix according to affine transformational relation function;
9) according to affine transition matrix, original color file and picture is converted to targeted color file and picture;
10) the histogram equalization function of standard is used, histogram equalization is carried out to targeted color file and picture, adjusts its contrast and brightness, the color document images after being adjusted, color document images after adjustment through USB, Ethernet or wifi transmission, or is saved in SD card or CF card.
Technical scheme provided by the invention, propose embedded circuit board and carry embedded OS, by transplanting, computer vision function library etc. is installed, online process and affine rectification can be carried out to scanning the image obtained in embedded circuit board, and its brightness and contrast is adjusted automatically, saving to the time of document process, is convenient to manual read and later stage Intelligent Character detection on PC.
Obviously, the invention is not restricted to above preferred implementation, in the spirit that also can limit in the claims in the present invention and instructions, carry out conversion and the improvement of various ways, can same technical matters be solved, and obtain the technique effect of expection, therefore not repeat.Those of ordinary skill in the art can from content disclosed by the invention directly or all schemes associated, as long as within the spirit limited in claim, also belong to protection scope of the present invention.
Claims (4)
1. a file scanning treatment facility, has embedded system, it is characterized in that: described embedded system comprises CPU processor; Be connected with described CPU processor by memory interface, and have cured DDR or the NandFlash memory in operating system and computer vision special purpose function storehouse; The camera be connected by I/O interface with described CPU processor, SD card/CF card memory interface, USB interface, Ethernet or WIFI transmission interface.
2. file scanning treatment facility according to claim 1, is characterized in that: described CPU processor is arm processor.
3. a file scanning disposal route, based on the application of file scanning treatment facility, described file scanning treatment facility has embedded system, and described embedded system comprises CPU processor; Be connected with described CPU processor by memory interface, and have cured DDR or the NandFlash memory in operating system and computer vision special purpose function storehouse; The camera be connected by I/O interface with described CPU processor, SD card/CF card memory interface, USB interface, Ethernet or WIFI transmission interface, is characterized in that: file scanning process comprises the following steps:
1) original color file and picture is obtained by camera;
2) by original color file and picture gray processing, gray scale file and picture is obtained;
3) adopt
coupling strengthen operator K
matchcarry out coupling to described gray scale file and picture to strengthen, the gray scale that is enhanced file and picture;
4) Da-Jin algorithm is adopted to obtain the overall binaryzation threshold values T of described enhancing gray scale file and picture, and with new threshold values T
1=k
1t and T
2=k
2t carries out segmentation binaryzation, by gray-scale value at T to described enhancing gray scale file and picture
1and T
2between pixel assignment be 1, all the other gray-value pixel assignment are 0, obtain the document edges image of binaryzation; Wherein 0.5≤k
1< 1,1 < k
2≤ 1.5;
5) profile in described computer vision special purpose function storehouse is adopted to find function to described document edges image, find out its all profile, and preservation enters structure contours, contains the coordinate of frontier point corresponding to each profile in structure contours;
6) calculate the area that each profile surrounds, and adopt traversal to compare to draw and there is maximum area and the frontier point coordinate of profile for quadrilateral, and obtain four frontier point coordinate P corresponding to maximum area profile according to the relative position order of coordinate points
1, P
2, P
3, P
4, wherein P
i_x and P
i_y represents x coordinate and the y coordinate of i-th frontier point respectively, i=1,2,3,4;
7) according to P
ithe coordinate position of point, obtains the breadth extreme W treating affine recovery region
maxwith maximum height H
max, W
max=max{W
1, W
2, H
max=max{H
1, H
2;
Wherein width
8) objective matrix that initialization one is empty, wherein the original width of this matrix is W
max, be highly H
max, and obtain the affine transition matrix from gray scale file and picture to objective matrix according to affine transformational relation function;
9) according to affine transition matrix, original color file and picture is converted to targeted color file and picture;
10) the histogram equalization function of standard is used, histogram equalization is carried out to targeted color file and picture, adjusts its contrast and brightness, the color document images after being adjusted, color document images after adjustment through USB, Ethernet or wifi transmission, or is saved in SD card or CF card.
4. file scanning disposal route according to claim 3, is characterized in that: adopt Da-Jin algorithm to obtain the overall binaryzation threshold values T of described enhancing gray scale file and picture, and with new threshold values T
1=k
1t and T
2=k
2t carries out in segmentation binarization to described enhancing gray scale file and picture, k
1=0.8, k
2=1.25.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510989613.7A CN105513010B (en) | 2015-12-28 | 2015-12-28 | A kind of file scanning processing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510989613.7A CN105513010B (en) | 2015-12-28 | 2015-12-28 | A kind of file scanning processing method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105513010A true CN105513010A (en) | 2016-04-20 |
CN105513010B CN105513010B (en) | 2019-01-18 |
Family
ID=55720968
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510989613.7A Active CN105513010B (en) | 2015-12-28 | 2015-12-28 | A kind of file scanning processing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105513010B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113259539A (en) * | 2020-02-12 | 2021-08-13 | 北京小米移动软件有限公司 | Document scanning method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1790378A (en) * | 2005-12-21 | 2006-06-21 | 北大方正集团有限公司 | Binary method and system for image |
US20090185736A1 (en) * | 2008-01-18 | 2009-07-23 | Grigori Nepomniachtchi | Methods for mobile image capture and processing of documents |
CN101504716A (en) * | 2009-03-13 | 2009-08-12 | 重庆大学 | QR two-dimension bar code recognition method and system based on field programmable gate array |
CN103295001A (en) * | 2013-06-03 | 2013-09-11 | 哈尔滨理工大学 | Invoice information recognition equipment and invoice information recognition method both applied to handhold equipment |
-
2015
- 2015-12-28 CN CN201510989613.7A patent/CN105513010B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1790378A (en) * | 2005-12-21 | 2006-06-21 | 北大方正集团有限公司 | Binary method and system for image |
US20090185736A1 (en) * | 2008-01-18 | 2009-07-23 | Grigori Nepomniachtchi | Methods for mobile image capture and processing of documents |
CN101504716A (en) * | 2009-03-13 | 2009-08-12 | 重庆大学 | QR two-dimension bar code recognition method and system based on field programmable gate array |
CN103295001A (en) * | 2013-06-03 | 2013-09-11 | 哈尔滨理工大学 | Invoice information recognition equipment and invoice information recognition method both applied to handhold equipment |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113259539A (en) * | 2020-02-12 | 2021-08-13 | 北京小米移动软件有限公司 | Document scanning method and device |
Also Published As
Publication number | Publication date |
---|---|
CN105513010B (en) | 2019-01-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108335331B (en) | Binocular vision positioning method and equipment for steel coil | |
US11156564B2 (en) | Dirt detection on screen | |
CN107945194A (en) | Bill dividing method based on OpenCV technologies | |
WO2017012581A1 (en) | Method and system for decoding qr code based on weighted average grey method | |
CN105184787A (en) | Identification camera capable of automatically carrying out portrait cutout and method thereof | |
CN108133216B (en) | Nixie tube reading identification method capable of realizing decimal point reading based on machine vision | |
CN105447489B (en) | A kind of character of picture OCR identifying system and background adhesion noise cancellation method | |
CN107169488A (en) | A kind of correction system and antidote of bill scan image | |
CN111879777A (en) | Soft material fitting defect detection method, device, equipment and storage medium | |
CN110674812B (en) | Civil license plate positioning and character segmentation method facing complex background | |
CN107977648B (en) | Identification card definition distinguishing method and system based on face recognition | |
WO2023280080A1 (en) | Shadow elimination device and method, empty disk recognition device and method | |
CN113766209B (en) | Camera offset processing method and device | |
CN112419207A (en) | Image correction method, device and system | |
CN108319945A (en) | A kind of separate type OCR recognition methods and its system | |
CN109741273A (en) | A kind of mobile phone photograph low-quality images automatically process and methods of marking | |
CN108229460A (en) | A kind of watermarking images OCR recognition methods and its system | |
CN108460735A (en) | Improvement dark defogging method based on single image | |
CN112288726B (en) | Method for detecting foreign matters on belt surface of underground belt conveyor | |
CN113393430A (en) | Thermal imaging image enhancement training method and device for fan blade defect detection | |
CN105513010A (en) | Document scanning processing apparatus and processing method | |
CN110610163B (en) | Table extraction method and system based on ellipse fitting in natural scene | |
CN115984806B (en) | Dynamic detection system for road marking damage | |
WO2023280081A1 (en) | Apparatus and method for identifying empty tray | |
CN102880355B (en) | Based on touch hot spot extracting method and the system of camera location |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right | ||
TR01 | Transfer of patent right |
Effective date of registration: 20190218 Address after: 410100 Room 401, Unit 1, Block B1, Jinke Yida Science and Technology City, 77 South Section of Dongliu Road, Changsha County, Changsha City, Hunan Province Patentee after: Changsha Tianzhi Zhichuang Electronic Technology Co., Ltd. Address before: 410129 No. 2 Xinghu Road, Rongli Street, Changsha Economic and Technological Development Zone, Changsha City, Hunan Province Patentee before: Star view creation (Changsha) Intelligent Equipment Co., Ltd. |