CN109753476A - A kind of bill scans financial special calculator and application method - Google Patents
A kind of bill scans financial special calculator and application method Download PDFInfo
- Publication number
- CN109753476A CN109753476A CN201910027243.7A CN201910027243A CN109753476A CN 109753476 A CN109753476 A CN 109753476A CN 201910027243 A CN201910027243 A CN 201910027243A CN 109753476 A CN109753476 A CN 109753476A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- calculator
- value
- digital
- 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.)
- Pending
Links
Landscapes
- Character Input (AREA)
Abstract
The invention discloses a kind of bills to scan financial special calculator and application method, and calculator includes sequentially connected automatically scanning module, image processing module, digital identification module, automatic computing module, digital display module, manual input module.The method of the invention is that the bill that will be put in order is scanned processing and provides required picture for image processing module, scanned bill is analyzed and processed to and is transferred data to digital identification module and recognizes the need for the number of processing, then number can enter in automatic computing module 4, it is shown through digital display module, data can be deleted or be increased to manual input module.The beneficial effects of the invention are as follows financial staff can be allowed to free from the hard work of input and the arrangement of a large amount of bills and can improve working efficiency；The time and energy that financial staff is manually entered are saved, the accuracy and working efficiency of numeral input are also substantially increased.
Description
Technical field
The invention belongs to calculating fields, and in particular to a kind of bill scans financial special calculator and application method.
Background technique
In daily life, work, calculator application is also brought while offering convenience for people in many industry fields
Some worries.For example, the units Finance Department such as company, colleges and universities, government often arranges a large amount of bill, several full-time people are needed
Member is arranged, is summarized, and the data preparation of especially bill is more cumbersome, and is easy error.Waste a large amount of energy and
Time.To solve this problem, a kind of intelligent scanning calculator for bill is designed.
Such as patent application publication a kind of financial management more function that Chinese Patent Application No. is ZL2014020050186.7
Energy calculator, although carrying out the big, longevity of service of bill quantity etc. when bill accounting also for mitigation finance staff
High-intensitive task and invent.But this application patent is by the transformation to calculator shell to realize that its is multi-functional, such as
Housing side installs metal hose, and hose one end is equipped with desk lamp；Housing upper surface is connected with stand frame, places bill in frame,
And design has the spring clip for clamping bill；Lower part of the housing is additionally provided with storeroom.Accordingly, there exist the accuracy of numeral input compared with
Poor, ineffective disadvantage.
Summary of the invention
The purpose of the present invention is to provide one kind, and the bill of above-mentioned technical problem can be overcome to scan financial special calculator
And application method.
The software configuration of calculator of the present invention includes sequentially connected automatically scanning module, image processing module, number
Word identification module, automatic computing module, digital display module, manual input module.
The hardware configuration of calculator of the present invention includes: calculator, display screen, soft keyboard, power button, voice broadcasting
Device hand-held scanner, scanning lens, starts switch, handle, connecting line, external connection keyboard.
Calculator, display screen, soft keyboard, power button, speech player are fixedly connected；Hand-held scanner and calculator with
USB fabric connection is wirelessly connected；Scanning lens, start switch, handle be arranged on hand-held scanner, external connection keyboard passes through
Connecting line is connected to calculator.
The bill put in order is scanned by automatically scanning module to be handled and provides required picture for image processing module, is schemed
As scanned bill is analyzed and processed and is transferred data to digital identification module by processing module and recognizes the need for locating
The number of reason, then number can enter in automatic computing module, show through digital display module, manual input module energy
It is enough manually entered digital to prevent digital identification module from cannot identify that number or identification mistake occur and be convenient for making change；It is defeated manually
Data can be deleted or increase by entering module.
The method of the invention the following steps are included:
Step 1 clicks power button unlatching calculator, holds the handle of hand-held scanner, then presses scanner switch,
Scanning lens automatically scanning bill, data after display screen display scanning, speech player can play the data of input, soft key
Disk and external connection keyboard can be manually entered change data, and connecting line connects external connection keyboard, automatic scanner and calculator.
Step 2, automatically scanning module provide required picture, image procossing mould by scan camera shooting head for image processing module
Block uses algorithm for image enhancement and gradient correction algorithm to improve the picture quality of automatically scanning module collection, reduce image
It obscures, remove video jitter and improve target locating accuracy.
Step 3, image preprocessing enhancing algorithm are using gray level image method, and the rgb format picture that camera is obtained turns
Be changed to gray level image format, i.e., according to the three-component varying sensitivity of human eye RGB and feature by three components with different weights
It is weighted and averaged；In view of human eye to the sensitivity difference of green, (1) is weighted and averaged tri- components of RGB according to the following formula
It can obtain gray level image, color image gray processing formula are as follows:
I=0.3R+0.59G+0.11B ... (1)；
Wherein, I represents gray matrix, and wherein R is red, and G is green, and B is blue；Formula (1) is represented to three kinds of colors
The gray component matrix obtained after the weighted calculation of component.
Step 4, invoice field area partitioning algorithm, the partitioning algorithm based on projection are the floor projections using image and hang down
It delivers directly shadow and completes partitioning algorithm；
Step 4.1, floor projection are that the gray level image of m*n or bianry image add up the picture of each pixel according to row
Element value, obtains the matrix of a m*1；
Step 4.2, upright projection are that the gray scale of m*n or bianry image add up according to column, obtain the matrix of a 1*n,
Projection localization method the following steps are included:
Step 4.2.1, pretreated image binaryzation will be passed through, since content is complex on invoice, so that field area
Domain is difficult to seek rule in Gray Projection image, its pixel value of the image after binaryzation is 0 or 1, and most of background
All be white be pixel value be 1；
Step 4.2.2, edge removal is carried out, since exposure factor influences, its edge pixel values is not after binaryzation
It is all 0, so that the feature of field area is not obvious in drop shadow curve, therefore edge removal first is carried out to invoice；
Step 4.2.3, floor projection is done to the image behind removal edge；Analysis level drop shadow curve, field area part
0,1 pixel is respectively 50%, and background parts Quan Bai, middle field is black, and different according to different zones projection value complete view
Screen positioning；
Step 4.2.4, upright projection is done, projection result is analyzed, vertical cutting is completed and divides to get to final field area
As a result.
Step 5, the recognizer that digital identification module is field region, recognizer content include field area number
It is accurately positioned, the identification of whole word；Accurate positioning refers to extracts individual digit one by one from field area, carries out Slant Rectify
Divide with individual character；In shooting process, the differential seat angle of camera and made thing body can cause photo target run-off the straight, using level
Correction algorithm, specifically includes the following steps:
Field area is converted binary image by step 5.1, using global binaryzation method threshold value；
Step 5.2, scan image lower boundary, and lower boundary coordinate is included in array D, as the inclined reference line of judgement；
Step 5.3 sets the angle a range of preliminary scan as [- 20,20]；It will be sat in D respectively with the step-length that angle is 1
Mark (x, y) brings formula xcosa+ysina=p into, wherein (x, y) and a are it is known that the p value that can be asked is united in the case where a value is fixed
Count the most p value of frequency of occurrence and corresponding frequency of occurrence n；P represents polar coordinates radius；
Step 5.4 finds out maximum n value, then the corresponding a value of maximum n value is the tilt angle of image, completes judgement
Field area is rotated afterwards.
Step 6, number identification are scanned digital picture using the straight line of several specific positions using threading algorithm
And characteristic quantity is extracted, the characteristic quantity for comparing each number is encoded to complete to identify, comprising the following steps:
Three are horizontal scanning line in step 6.1, scan line, are successively set as X1, X2 from top to bottom, X3 exists respectively
It is from left to right scanned at 1/4H, 1/2H, 3/4H, in addition line vertical scanning from top to bottom at 1/2W, is set as
Y1；
Step 6.2 records when every scan line passes through number the changed number of pixel value and every scan line the
The primary position for passing through digital stroke；
Step 6.3, record rule are as follows: for horizontal scanning line, if passing through the position of character stroke for the first time in the 1st column
It is then denoted as 0 between 1/2W column, otherwise for 1. for vertical scan line, if passing through the position of character stroke for the first time the 1st
It arranges between 1/2H column and is then denoted as 0, be otherwise 1；It is as shown in the table that threading method counts each numerical character characteristic value:
Step 6.4, to digital coding in the five variable tables of comparisons collected, digital judgement can be completed；
Step 7, digital identification module will can be automatically entered into calculator after required number identification, in the program of calculator
In write addition program and can realize the adduction of input data.
The beneficial effects of the invention are as follows financial staff can be allowed to solve from the hard work of input and the arrangement of a large amount of bills
It takes off and working efficiency can be improved；Hand-held scanner of the invention can identify the number in bill and can occur automatically
Into display screen, the time and energy that financial staff is manually entered are saved, the accuracy of numeral input is also substantially increased
And working efficiency.
Detailed description of the invention
Fig. 1 is the software configuration schematic diagram of calculator of the present invention；
The hardware structural diagram of Fig. 2 calculator of the present invention.
Specific embodiment
Embodiments of the present invention are described in detail with reference to the accompanying drawing.As shown in Figure 1, 2, calculating of the present invention
The software configuration of device includes sequentially connected automatically scanning module 1, image processing module 2, digital identification module 3, automatic calculating
Module 4, digital display module 5, manual input module 6.The hardware configuration of calculator of the present invention includes: calculator 7, display
Screen 8, power button 10, speech player 11, hand-held scanner 12, scanning lens 13, starts switch 14, handle at soft keyboard 9
15, connecting line 16, external connection keyboard 17.
Calculator 7, display screen 8, soft keyboard 9, power button 10, speech player 11 are fixedly connected；Hand-held scanner 12
It connect or is wirelessly connected with USB fabric with calculator；Scanning lens 13 starts switch the setting of 14, handle 15 in hand-held scanner
On instrument 12, external connection keyboard 17 is connected to calculator 7 by connecting line 16.
The bill put in order is scanned by automatically scanning module 1 to be handled and provides required picture for image processing module 2,
Scanned bill is analyzed and processed and is transferred data to digital identification module 3 and identify and needed by image processing module 2
Number to be processed, then number can enter in automatic computing module 4, show, be manually entered through digital display module 5
Module 6 can be manually entered digital to prevent digital identification module from cannot identify that number or identification mistake occur and be convenient for making more
Change；Data can be deleted or be increased to manual input module 6.
The method of the invention the following steps are included:
Step 1 clicks the unlatching calculator of power button 10, holds the handle 15 of hand-held scanner 12, then presses scanning
Instrument switch 14,13 automatically scanning bill of scanning lens, data after the display scanning of display screen 8, speech player 11 can play
The data of input, soft keyboard 9 and external connection keyboard 17 can be manually entered change data, connecting line 16 by external connection keyboard 17, from
Dynamic scanner 12 is connect with calculator 7.
Step 2, automatically scanning module 1 are that image processing module 2 provides required picture by scan camera shooting head 13, at image
Reason module 2 uses algorithm for image enhancement and gradient correction algorithm to improve the picture quality of automatically scanning module collection, subtract
Few image obscures, removes video jitter and improves target locating accuracy.
Step 3, image preprocessing enhancing algorithm are using gray level image method, and the rgb format picture that camera is obtained turns
Be changed to gray level image format, i.e., according to the three-component varying sensitivity of human eye RGB and feature by three components with different weights
It is weighted and averaged；In view of human eye to the sensitivity difference of green, (1) is weighted and averaged tri- components of RGB according to the following formula
It can obtain gray level image, color image gray processing formula are as follows:
I=0.3R+0.59G+0.11B ... (1)；
Wherein, I represents gray matrix, and wherein R is red, and G is green, and B is blue；Formula (1) is represented to three kinds of colors
The gray component matrix obtained after the weighted calculation of component.
Step 4, invoice field area partitioning algorithm, the partitioning algorithm based on projection are the floor projections using image and hang down
It delivers directly shadow and completes partitioning algorithm；
Step 4.1, floor projection are that the gray level image of m*n or bianry image add up the picture of each pixel according to row
Element value, obtains the matrix of a m*1；
Step 4.2, upright projection are that the gray scale of m*n or bianry image add up according to column, obtain the matrix of a 1*n,
Projection localization method the following steps are included:
Step 4.2.1, pretreated image binaryzation will be passed through, since content is complex on invoice, so that field area
Domain is difficult to seek rule in Gray Projection image, its pixel value of the image after binaryzation is 0 or 1, and most of background
All be white be pixel value be 1；
Step 4.2.2, edge removal is carried out, since exposure factor influences, its edge pixel values is not after binaryzation
It is all 0, so that the feature of field area is not obvious in drop shadow curve, therefore edge removal first is carried out to invoice；
Step 4.2.3, floor projection is done to the image behind removal edge；Analysis level drop shadow curve, field area part
0,1 pixel is respectively 50%, and background parts Quan Bai, middle field is black, and different according to different zones projection value complete view
Screen positioning；
Step 4.2.4, upright projection is done, projection result is analyzed, vertical cutting is completed and divides to get to final field area
As a result.
Step 5, the recognizer that digital identification module is field region, recognizer content include field area number
It is accurately positioned, the identification of whole word；Accurate positioning refers to extracts individual digit one by one from field area, carries out Slant Rectify
Divide with individual character；In shooting process, the differential seat angle of camera and made thing body can cause photo target run-off the straight, using level
Correction algorithm, specifically includes the following steps:
Field area is converted binary image by step 5.1, using global binaryzation method threshold value；
Step 5.2, scan image lower boundary, and lower boundary coordinate is included in array D, as the inclined reference line of judgement；
Step 5.3 sets the angle a range of preliminary scan as [- 20,20]；It will be sat in D respectively with the step-length that angle is 1
Mark (x, y) brings formula xcosa+ysina=p into, wherein (x, y) and a are it is known that the p value that can be asked is united in the case where a value is fixed
Count the most p value of frequency of occurrence and corresponding frequency of occurrence n；P represents polar coordinates radius；
Step 5.4 finds out maximum n value, then the corresponding a value of maximum n value is the tilt angle of image, completes judgement
Field area is rotated afterwards.
Step 6, number identification are scanned digital picture using the straight line of several specific positions using threading algorithm
And characteristic quantity is extracted, the characteristic quantity for comparing each number is encoded to complete to identify, comprising the following steps:
Three are horizontal scanning line in step 6.1, scan line, are successively set as X1, X2 from top to bottom, X3 exists respectively
It is from left to right scanned at 1/4H, 1/2H, 3/4H, in addition line vertical scanning from top to bottom at 1/2W, is set as
Y1；
Step 6.2 records when every scan line passes through number the changed number of pixel value and every scan line the
The primary position for passing through digital stroke；
Step 6.3, record rule are as follows: for horizontal scanning line, if passing through the position of character stroke for the first time in the 1st column
It is then denoted as 0 between 1/2W column, otherwise for 1. for vertical scan line, if passing through the position of character stroke for the first time the 1st
It arranges between 1/2H column and is then denoted as 0, be otherwise 1；It is as shown in the table that threading method counts each numerical character characteristic value:
Step 6.4, to digital coding in the five variable tables of comparisons collected, digital judgement can be completed；
Step 7, digital identification module 3 will can be automatically entered into calculator 7 after required number identification, in calculator 7
Addition program is write in program can realize the adduction of input data.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
In range disclosed by the invention, the change or replacement that can be readily occurred in should all be contained those familiar with the art
Lid is within the scope of the invention as claimed.
Claims (5)
1. a kind of bill scans financial special calculator, which is characterized in that the software configuration of the calculator includes being sequentially connected
Automatically scanning module, image processing module, digital identification module, automatic computing module, digital display module, be manually entered mould
Block；
The hardware configuration of the calculator includes: that calculator, display screen, soft keyboard, power button, speech player, hand-held are swept
It retouches instrument, scanning lens, start switch, handle, connecting line, external connection keyboard；
Calculator, display screen, soft keyboard, power button, speech player are fixedly connected；Hand-held scanner and calculator are with USB
Structure connection is wirelessly connected；Scanning lens, start switch, handle be arranged on hand-held scanner, external connection keyboard passes through company
Wiring is connected to calculator.
2. the application method that a kind of bill as described in claim 1 scans financial special calculator, which is characterized in that including with
Lower step:
Step 1 clicks power button unlatching calculator, holds the handle of hand-held scanner, then presses scanner switch, scanning
Camera lens automatically scanning bill, data after display screen display scanning, speech player can play the data of input, soft keyboard and
External connection keyboard can be manually entered change data, and connecting line connects external connection keyboard, automatic scanner and calculator；
Step 2, automatically scanning module provide required picture by scan camera shooting head for image processing module, and image processing module is adopted
With algorithm for image enhancement and gradient correction algorithm to improve the picture quality of automatically scanning module collection, reduce image mould
It pastes, remove video jitter and improve target locating accuracy；
Step 3, image preprocessing enhancing algorithm are to be converted to the rgb format picture that camera obtains using gray level image method
Gray level image format is carried out three components with different weights according to the three-component varying sensitivity of human eye RGB and feature
Weighted average；In view of human eye to the sensitivity difference of green, (1) is weighted and averaged and can obtain to tri- components of RGB according to the following formula
To gray level image, color image gray processing formula are as follows:
I=0.3R+0.59G+0.11B ... (1)；
Wherein, I represents gray matrix, and wherein R is red, and G is green, and B is blue；Formula (1) is represented to three kinds of color components
Weighted calculation after obtained gray component matrix；
Step 4, invoice field area partitioning algorithm, the partitioning algorithm based on projection are the floor projection and vertical throwing using image
Shadow completes partitioning algorithm；
Step 5, the recognizer that digital identification module is field region, recognizer content include that field area number is accurate
Positioning, the identification of whole word；Accurate positioning refers to extracts individual digit one by one from field area, carries out Slant Rectify and list
Word segmentation；In shooting process, the differential seat angle of camera and made thing body can cause photo target run-off the straight, using rectification
Algorithm；
Step 6, number identification are scanned and are mentioned to digital picture using the straight line of several specific positions using threading algorithm
Characteristic quantity is taken, the characteristic quantity for comparing each number is encoded to complete to identify；
Step 7, digital identification module will can be automatically entered into calculator after required number identification, be compiled in the program of calculator
The adduction of input data can be realized by writing addition program.
3. according to the method described in claim 2, it is characterized in that, the step 4 the following steps are included:
Step 4.1, floor projection are that the gray level image of m*n or bianry image add up the pixel of each pixel according to row
Value, obtains the matrix of a m*1；
Step 4.2, upright projection are that the gray scale of m*n or bianry image add up according to column, obtain the matrix of a 1*n, project
Dividing method the following steps are included:
Step 4.2.1, pretreated image binaryzation will be passed through, since content is complex on invoice, so that field area exists
Gray Projection image is difficult to seek rule, its pixel value of the image after binaryzation is 0 or 1, and most of background is all
It is 1 for the i.e. pixel value of white；
Step 4.2.2, edge removal is carried out, since exposure factor influences, its edge pixel values and is not all after binaryzation
0, so that the feature of field area is not obvious in drop shadow curve, therefore edge removal first is carried out to invoice；
Step 4.2.3, floor projection is done to the image behind removal edge；Analysis level drop shadow curve, field area part 0,1 picture
Element is respectively 50%, and background parts Quan Bai, middle field is black, is determined according to the different screens of completing of different zones projection value
Position；
Step 4.2.4, upright projection is done, projection result is analyzed, completes vertical cutting to get final field area segmentation knot is arrived
Fruit.
4. according to the method described in claim 2, it is characterized in that, the step 5 the following steps are included:
Field area is converted binary image by step 5.1, using global binaryzation method threshold value；
Step 5.2, scan image lower boundary, and lower boundary coordinate is included in array D, as the inclined reference line of judgement；
Step 5.3 sets the angle a range of preliminary scan as [- 20,20]；With angle be 1 step-length respectively by coordinate in D (x,
Y) formula xcosa+ysina=p is brought into, wherein (x, y) and a are it is known that the p value that can be asked is counted in the case where a value is fixed
The most p value of occurrence number and corresponding frequency of occurrence n；P represents polar coordinates radius；
Step 5.4 finds out maximum n value, then the corresponding a value of maximum n value is the tilt angle of image, and it is right after judging to complete
Field area is rotated.
5. according to the method described in claim 2, it is characterized in that, the step 6 comprises the following steps:
Three are horizontal scanning line in step 6.1, scan line, are successively set as X1 from top to bottom, X2, X3 respectively in 1/4H, 1/2H,
It is from left to right scanned at 3/4H, in addition line vertical scanning from top to bottom at 1/2W, is set as Y1；
Step 6.2 records the changed number of pixel value and every scan line first time when every scan line passes through number
Across the position of digital stroke；
Step 6.3, record rule are as follows: for horizontal scanning line, if passing through the position of character stroke for the first time in the 1st column to the
It is then denoted as 0 between 1/2W column, otherwise for 1. for vertical scan line, if the position for passing through character stroke for the first time is arrived in the 1st column
It is then denoted as 0 between 1/2H column, is otherwise 1；
Step 6.4, to digital coding in the five variable tables of comparisons collected, digital judgement can be completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910027243.7A CN109753476A (en) | 2019-01-11 | 2019-01-11 | A kind of bill scans financial special calculator and application method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910027243.7A CN109753476A (en) | 2019-01-11 | 2019-01-11 | A kind of bill scans financial special calculator and application method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109753476A true CN109753476A (en) | 2019-05-14 |
Family
ID=66405475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910027243.7A Pending CN109753476A (en) | 2019-01-11 | 2019-01-11 | A kind of bill scans financial special calculator and application method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109753476A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110400281A (en) * | 2019-08-05 | 2019-11-01 | 山东志盈医学科技有限公司 | Image enchancing method in a kind of digital slices scanner |
| CN112699860A (en) * | 2021-03-24 | 2021-04-23 | 成都新希望金融信息有限公司 | Method for automatically extracting and sorting effective information in personal tax APP operation video |
| CN114926841A (en) * | 2022-07-22 | 2022-08-19 | 广州能源检测研究院 | Electronic water meter reading image identification method and device based on improved threading method |
| CN115308978A (en) * | 2022-08-05 | 2022-11-08 | 郑州森鹏电子技术股份有限公司 | Design method for heating and defrosting function of vehicle-mounted camera |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202275404U (en) * | 2011-10-26 | 2012-06-13 | 上海理工大学 | Calculator with character recognizing function |
| CN205091737U (en) * | 2015-11-11 | 2016-03-16 | 王倩 | Financial calculator |
-
2019
- 2019-01-11 CN CN201910027243.7A patent/CN109753476A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202275404U (en) * | 2011-10-26 | 2012-06-13 | 上海理工大学 | Calculator with character recognizing function |
| CN205091737U (en) * | 2015-11-11 | 2016-03-16 | 王倩 | Financial calculator |
Non-Patent Citations (2)
| Title |
|---|
| 卓磊 等: "基于穿线法的计算器数字识别", 《软件工程》 * |
| 蒋先刚: "《数字图像模式识别工程项目研究》", 31 March 2014, 成都：西南交通大学出版社 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110400281A (en) * | 2019-08-05 | 2019-11-01 | 山东志盈医学科技有限公司 | Image enchancing method in a kind of digital slices scanner |
| CN112699860A (en) * | 2021-03-24 | 2021-04-23 | 成都新希望金融信息有限公司 | Method for automatically extracting and sorting effective information in personal tax APP operation video |
| CN112699860B (en) * | 2021-03-24 | 2021-06-22 | 成都新希望金融信息有限公司 | Method for automatically extracting and sorting effective information in personal tax APP operation video |
| CN114926841A (en) * | 2022-07-22 | 2022-08-19 | 广州能源检测研究院 | Electronic water meter reading image identification method and device based on improved threading method |
| CN115308978A (en) * | 2022-08-05 | 2022-11-08 | 郑州森鹏电子技术股份有限公司 | Design method for heating and defrosting function of vehicle-mounted camera |
| CN115308978B (en) * | 2022-08-05 | 2024-05-28 | 郑州森鹏电子技术股份有限公司 | Design method for heating and defrosting functions of vehicle-mounted camera |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109753476A (en) | A kind of bill scans financial special calculator and application method | |
| CN109752394B (en) | High-precision detection method and system for defects of display screen | |
| CN103984930B (en) | The digital instrument identifying system of view-based access control model and its recognition methods | |
| CN110599548A (en) | Camera calibration method and device, camera and computer readable storage medium | |
| CN106778676B (en) | Attention assessment method based on face recognition and image processing | |
| CN109409355B (en) | Novel transformer nameplate identification method and device | |
| CN103699532B (en) | Image color retrieval method and system | |
| CN109785316A (en) | A kind of apparent defect inspection method of chip | |
| CN110287787B (en) | Image recognition method, image recognition device and computer-readable storage medium | |
| CN104598907B (en) | Lteral data extracting method in a kind of image based on stroke width figure | |
| CN106971393B (en) | A kind of the phenotype measurement method and system of corn kernel | |
| CN101983507A (en) | Automatic redeye detection | |
| CN104463134B (en) | A kind of detection method of license plate and system | |
| CN106097354B (en) | A kind of hand images dividing method of combining adaptive Gauss Face Detection and region growing | |
| CN106384117A (en) | Vehicle color recognition method and device | |
| CN108921804A (en) | Distort the bearing calibration of file and picture | |
| CN104517101A (en) | Game poker card recognition method based on pixel square difference matching | |
| CN111259891A (en) | Method, device, equipment and medium for identifying identity card in natural scene | |
| CN112164055A (en) | Photovoltaic cell color difference classification method based on color segmentation | |
| KR20220088832A (en) | Seal certification assisting method using seal scanner | |
| CN114187253A (en) | Circuit board part installation detection method | |
| CN1492379A (en) | Method for covering face of news interviewee using quick face detection | |
| US20070019248A1 (en) | Method for collecting information of business cards in a mobile communication device | |
| CN113554022A (en) | Automatic acquisition method and device for detection test data of power instrument | |
| CN109978889A (en) | Image processing method, system, device, storage medium and blackboard device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190514 |
|
| RJ01 | Rejection of invention patent application after publication |