CN104318231A - Quick locating method for ballot image - Google Patents
Quick locating method for ballot image Download PDFInfo
- Publication number
- CN104318231A CN104318231A CN201410544808.6A CN201410544808A CN104318231A CN 104318231 A CN104318231 A CN 104318231A CN 201410544808 A CN201410544808 A CN 201410544808A CN 104318231 A CN104318231 A CN 104318231A
- Authority
- CN
- China
- Prior art keywords
- ballot paper
- ballot
- image
- rectangular code
- page
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/243—Aligning, centring, orientation detection or correction of the image by compensating for image skew or non-uniform image deformations
Abstract
The invention discloses a quick locating method for a ballot image. The quick locating method for the ballot image includes that designing ballot format, storing ballot format data, scanning a ballot, pre-processing the scanned image, shooting the page bottom of the scanned image, wherein the screenshot comprises a rectangular code of the ballot sequence number, a rectangular code of the ballot page and page number value information; calculating the slope gradient of the screenshot and using the slope gradient to correct the incline of the screenshot, horizontally and vertically projecting the screenshot image, confirming the positions of the left upper peak of the rectangular code of the ballot sequence number and the right upper peak of the rectangular code of the ballot page, identifying the ballot type and the page value thereof, correcting the incline of the whole ballot image according to the ballot format data, converting the position of the left upper vertex of the rectangular code of the ballot sequence number into the position in the whole ballot image, and calculating and searching the precise position to be identified in the ballot image or the precise position of the screenshot region. The quick locating method for the ballot image greatly improves the locating speed and precision, lowers the requirements for ballot paper quality, ballot design and manufacturing, and improves the application agility of the ballot.
Description
Technical field
The present invention relates to framing technology, particularly relate to a kind of system and method for ballot paper Image Quick Orientation.
Background technology
Traditional poll mode fills in the symbol such as " √ ", "○", "×" for elector on papery ballot paper, and by manually carrying out calling out the names of those voted for while counting ballot-slips and count of votes, such operation is not only time-consuming, the more important thing is easily to make mistakes, and is subject to the interference of human factor; Based on OMR (Optical Mark Recognition, optical markings identification) the poll system of technology requires higher, too high and restriction is too many, use and do not meet the subject matters such as ordinary practice to user's fill request to ballot paper paper and printing quality, greatly limit using and promoting of this system; Although adopt, electronic voting ballot mode count of votes speed is fast, accuracy is high, and cannot disclose ticket checking owing to lacking stub, its confidence level is under suspicion, and its safety and reliability problem fails to solve well always.Therefore, in a hurry a kind of the confidence level, the poll system that meets user's use habit again, also will increase work efficiency that had both retained traditional ballot mode is needed.
Along with the fast development of OCR (Optical Character Recognition, optical character identification) technology, increasing people applies it to poll system.But also there are some problems, as: existing Table recognition algorithm is only applicable to simple form, and it is not high that Table Layout Structure understands efficiency of algorithm.Although understand the layout structure of ballot system without predefined ballot paper of algorithm based on ballot paper layout structure, more complicated at the ballot paper space of a whole page, when form fields quantity is more, form thread breakage is more serious, rapidity is also a greater impact.In a word, due to the restriction of ballot paper image position method, the requirement of system in ballot box hardware, ballot paper paper quality, ballot paper space of a whole page complicacy, ballot paper making etc. is not quite similar, limits dirigibility and the usable range of system to a certain extent.
Summary of the invention
In order to solve the problem, meet actual demand widely, the present invention, on the basis taking into full account ballot paper design and image processing techniques, provides a kind of method of ballot paper Image Quick Orientation.The relative position data of record during the method utilizes ballot paper to design, after ballot paper Image semantic classification, find a reference point determined, extract the position data in ballot paper design again, it is converted into the picture position relative to this reference point, utilizes this location finding form line, thus determine the accurate location that will identify or want sectional drawing image, substantially increase speed and the degree of accuracy of location, reduce the requirement to ballot paper paper quality, ballot paper designing and making etc., improve its application flexibility.
The present invention adopts following technical scheme:
A method for ballot paper Image Quick Orientation, comprises the steps:
S1: utilize host side to design ballot paper form preserve ballot paper formatted data, described ballot paper formatted data comprises: paper size, margin, table position, boxhead are high, gauge outfit columns, fill in hurdle column number, fill in that hurdle is wide, candidate hurdle is wide, the columns of each row in capable high, the table body of table body line number, table body; Described ballot paper form is provided with symmetrical ballot paper sequence number rectangular code and ballot paper page number rectangular code in the fixed position, base of ballot paper page, the frame line of two rectangular codes is thick lines, and each rectangular code is made up of the little square of 6 same sizes;
S2: ballot paper formatted data is sent to ballot box end by host side;
S3: the high speed scanner of ballot box end scans ballot paper to be positioned, obtains the scan image of ballot paper;
S4: ballot box end carries out pre-service to the scan image of ballot paper; Described pre-service comprises image and turns gray-scale map, binaryzation, goes discrete noise;
S5: ballot box end carries out sectional drawing at the bottom of ballot paper page to ballot paper image, described sectional drawing comprises ballot paper sequence number rectangular code and ballot paper page number rectangular code, and calculates the slope of sectional drawing, utilizes slope to carry out slant correction to sectional drawing image;
S6: carry out horizontal projection and vertical projection to sectional drawing image at the bottom of corrected ballot paper page, determines the position of ballot paper sequence number rectangular code left upper apex and ballot paper page number rectangular code right vertices; Utilize two vertex positions obtained to navigate to each little square, and judge there is nil in each little square, utilize the weights distribution principle of rectangular code, determine the sequence number of ballot paper kind and the page number;
S7: the sequence number utilizing ballot paper kind and the page number thereof obtained in S6, carries out slant correction according to ballot paper formatted data and slope by whole ballot paper image;
S8: the position of ballot paper sequence number rectangular code left upper apex is converted into its position at whole ballot paper image, namely determines the position of reference point;
S9: utilize the ballot paper formatted data that the position of reference point in ballot paper image, ballot paper kind and page number sequence number are corresponding, calculate approximate location that is to be identified or screenshot area, utilize this location finding form line thus determine accurate location that is to be identified or screenshot area.
Preferably, in described step S1, the position of the page number rectangular code centered beneath of ballot paper sequence number rectangular code and ballot paper is also provided with page number value.
Preferably, the ballot paper sequence number rectangular code in described step S1 is used for identifying the kind of ballot paper; Ballot paper page number rectangular code is used for identifying the page number of ballot paper, and ballot paper sequence number rectangular code is positioned at the ballot paper page number rectangular code left side.
Preferably, the slope in described step S5 is the ratio of the true altitude of rectangular code in average height half of about rectangular code in sectional drawing image and ballot paper page formatted data.
Preferably, horizontal projection in described step S6 is by down searching for from the first row of sectional drawing image, record the number of the black pixel point of every a line, thick lines are used due to rectangular code, make in horizontal projection, necessarily have a number to be greater than the threshold value of setting, the picturedeeps that first such number is corresponding are exactly the position of the vertical direction at place, rectangular code top; Vertical projection is by searching for from left to right sectional drawing image, record the number of the black pixel point of each row, if there is a number to be greater than the threshold value of setting, picturewide corresponding to this number be exactly the little square left side of ballot paper sequence number rectangular code first position in the horizontal direction; Turn left from the right side search, the first number is greater than the threshold value of this setting again, the picturewide that this number is corresponding be exactly the little square the right of ballot paper page number rectangular code the 6th position in the horizontal direction.
Preferably, utilize this location finding form line in described step S9 thus determine accurate location that is to be identified or screenshot area, refer in the horizontal direction, relatively calculated value searches the step number of nearest straight line and the straight line step number to nearest straight line backward, thus determine that form alignment is on the left side of calculated value or the right, in like manner, in vertical direction, determine that form line in the top of calculated value or below.
Preferably, described step S9, before search, first by this position correspondingly mobile pixel; During straight line, just first move a pixel backward; When searching for backward, just first move forward a pixel; Search for straight line again.
Beneficial effect of the present invention:
The present invention utilize rectangular code in ballot paper the design feature of known position data and form in position in the picture, ballot paper design data, after carrying out some basic Image semantic classification, by first calculating the approximate location obtaining area to be targeted, search list ruling obtains its accurate location again, thus achieves the quick position of form image recognition.This is not only conducive to improving ballot paper image recognition rate, and the ballot paper space of a whole page can be more complicated, and reduce the requirement to ballot paper paper quality, ballot paper designing and making etc., improve its application flexibility, the scope of application can be wider.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of an embodiment of the present invention;
Fig. 2 is ballot paper sequence number rectangular code and the ballot paper page number rectangular code sectional drawing schematic diagram of an embodiment of the present invention;
Fig. 3 is the calculated value of left upper apex position, area to be targeted and the relation schematic diagram of its exact value of an embodiment of the present invention;
Fig. 4 be an embodiment of the present invention by the schematic diagram of calculated value search list ruling;
Fig. 5 is the schematic diagram of calculated value in-scope.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention is described in detail.
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art, not making the every other embodiment obtained under creative work prerequisite, belong to the scope of protection of the invention.
What rectangular code in the present invention adopted is the patent No. is: CN1437157, patent name for a kind of rectangular code coding method and based on the method rectangular code described in rectangular code.
As shown in Figure 1, the method for a kind of ballot paper Image Quick Orientation of a kind of embodiment of the present invention, comprises the steps:
S1: utilize host side to design ballot paper form preserve ballot paper formatted data, described ballot paper formatted data comprises: paper size, margin, table position, boxhead are high, gauge outfit columns, fill in hurdle column number, fill in that hurdle is wide, candidate hurdle is wide, the columns of each row in capable high, the table body of table body line number, table body; Described ballot paper form is provided with symmetrical ballot paper sequence number rectangular code and ballot paper page number rectangular code in the fixed position, base of ballot paper page, the frame line of two rectangular codes is thick lines, and each rectangular code is made up of the little square of 6 same sizes;
S2: ballot paper formatted data is sent to ballot box end by host side;
S3: the high speed scanner of ballot box end scans ballot paper to be positioned, obtains the scan image of ballot paper;
S4: ballot box end carries out pre-service to the scan image of ballot paper; Described pre-service comprises image and turns gray-scale map, binaryzation, goes discrete noise;
S5: ballot box end carries out sectional drawing at the bottom of ballot paper page to ballot paper image, described sectional drawing comprises ballot paper sequence number rectangular code and ballot paper page number rectangular code, and calculates the slope of sectional drawing, utilizes slope to carry out slant correction to sectional drawing image;
S6: carry out horizontal projection and vertical projection to sectional drawing image at the bottom of corrected ballot paper page, determines the position of ballot paper sequence number rectangular code left upper apex and ballot paper page number rectangular code right vertices; Utilize two vertex positions obtained to navigate to each little square, and judge there is nil in each little square, utilize the weights distribution principle of rectangular code, determine the sequence number of ballot paper kind and the page number;
S7: the sequence number utilizing ballot paper kind and the page number thereof obtained in S6, carries out slant correction according to ballot paper formatted data and slope by whole ballot paper image;
S8: the position of ballot paper sequence number rectangular code left upper apex is converted into its position at whole ballot paper image, namely determines the position of reference point;
S9: utilize the ballot paper formatted data that the position of reference point in ballot paper image, ballot paper kind and page number sequence number are corresponding, calculate approximate location that is to be identified or screenshot area, utilize this location finding form line thus determine accurate location that is to be identified or screenshot area.
In the present embodiment in step S1 rectangular code frame line adopt be thick lines, live width is 8, two rectangular codes are distributed in the both sides on paper base symmetrically, the left upper apex of left side ballot paper sequence number rectangular code is apart from paper left side 15mm, apart from paper base 10mm, 15mm on the right of the right vertices distance paper of the ballot paper page number rectangular code on the right, apart from paper base 10mm, there is the page number value (horizontal center for which page checked for user the centre of two rectangular codes.During single page, do not need).In addition, the margin of ballot paper is at least 15mm.
What the image in the present embodiment in step S4 turned gray-scale map employing is change into 256 color shade figure.
Ballot box end in the present embodiment in step S5 carries out sectional drawing at the bottom of ballot paper page to ballot paper image, refer to the pixel value (15* scan image resolution/25.4) 15mm being converted into scan image, the parts of images that intercepting is highly this value, width is ballot paper picture traverse, the information of two rectangular codes and page number value is just contained (during single page ballot paper in this image, without page number value), as shown in Figure 2, the slope of this scan image is very little.For the image that this kind of slope is very little, by the statistics to average height half of about it, compared with the true altitude of rectangular code in ballot paper page formatted data, slope more accurately can be obtained.According to this slope, realize sectional drawing image rectification.
Sectional drawing image after correction is carried out horizontal projection, vertical projection operation by the S6 in the present embodiment, determines the position of ballot paper sequence number rectangular code left upper apex, ballot paper page number rectangular code right vertices.During horizontal projection operation, down search for from the first row of image, record the number of the black pixel point of every a line, due to rectangular code employing is thick lines, make in horizontal projection, necessarily have a number to be greater than the threshold value of setting, the picturedeeps that first such number is corresponding are exactly the position of the vertical direction at place, rectangular code top.During vertical projection operation, search for from left to right, record the number of black pixel point of each row, if there is a number to be greater than the threshold value of setting, picturewide corresponding to this number be exactly the little square left side of ballot paper sequence number rectangular code first position in the horizontal direction; Turn left from the right side search, the first number is greater than the threshold value of this setting again, the picturewide that this number is corresponding be exactly the little square the right of ballot paper page number rectangular code the 6th position in the horizontal direction.Thus obtain the position of ballot paper sequence number left upper apex, ballot paper page number rectangular code right vertices.Utilize the position on these two summits, navigate to each little square successively, due to apart from short, the error of calculation is very little, and this makes the position data calculated be more accurately.Utilize this position, intercept little square-shaped image, judge there is nil in this image, the weights of recycling rectangular code distribute, and just can determine the sequence number of ballot paper kind and the page number thereof.
Utilize the slope that sectional drawing obtains in the present embodiment in step S7, the point of current whole ballot paper new images is mapped to the point of source images, just achieves the slant correction of whole ballot paper image.
In the present embodiment, the position of ballot paper sequence number rectangular code left upper apex is converted into its position at whole ballot paper image by step S8.This summit is referred to as reference point.
In the present embodiment, step S9 utilizes the position of reference point in ballot paper image, be aware of again ballot paper kind sequence number and the page number thereof, just can search the position data that this ballot paper is known in ballot paper design, they are changed into the position data of relatively this reference point, thus their position datas in the picture can be determined.The calculating of these position datas, certainly can also utilize the existing design feature of form, calculate regularly, so just obtain the approximate location of area to be targeted.
Due to the impact of the factors such as error of calculation during slant correction, make picture position its physical location relatively calculated, there is a small amount of error.If determine the accurate location of rectangular area to be positioned left upper apex, just there are following 8 kinds of situations, as shown in Figure 3.Therefore need further to extract accurate location to image, need to utilize the approximate location of the area to be targeted of calculating to carry out search list ruling, thus determine accurate location that is to be identified or screenshot area, as shown in Figure 4, namely in the horizontal direction, relatively calculated value searches the step number of nearest straight line and the straight line step number to nearest straight line backward, thus determine that form alignment is on the left side of calculated value or the right, in like manner, in vertical direction, determine that form line in the top of calculated value or below.Be that calculated value has just in time dropped on form line owing to there being a kind of situation, search straight line mistake can be there is, therefore before search, first by this position correspondingly mobile pixel; During straight line, just first move a pixel backward; When searching for backward, just first move forward a pixel; Search for straight line again.As shown in Figure 5, calculated value C must drop on (dotted rectangle is made up of the line of accurate location P tetra-rectangular centre Thursday) within the scope of dotted rectangle.This is 300DPI for resolution of scanner and the grid length of side is not less than the scan image of 5mm, generally all can meet.
To those skilled in the art, obviously the invention is not restricted to the details of above-mentioned one exemplary embodiment, and when not deviating from spirit of the present invention or essential characteristic, the present invention can be realized in other specific forms.Therefore, no matter from which point, all should embodiment be regarded as exemplary, and be nonrestrictive, scope of the present invention is limited by claims instead of above-mentioned explanation, and all changes be therefore intended in the implication of the equivalency by dropping on claim and scope are included in the present invention.Any Reference numeral in claim should be considered as the claim involved by limiting.
In addition, be to be understood that, although this instructions is described according to embodiment, but not each embodiment only comprises an independently technical scheme, this narrating mode of instructions is only for clarity sake, those skilled in the art should by instructions integrally, and the technical scheme in each embodiment also through appropriately combined, can form other embodiments that it will be appreciated by those skilled in the art that.
Claims (7)
1. a method for ballot paper Image Quick Orientation, is characterized in that comprising the steps:
S1: utilize host side to design ballot paper form preserve ballot paper formatted data, described ballot paper formatted data comprises: paper size, margin, table position, boxhead are high, gauge outfit columns, fill in hurdle column number, fill in that hurdle is wide, candidate hurdle is wide, the columns of each row in capable high, the table body of table body line number, table body; Described ballot paper form is provided with symmetrical ballot paper sequence number rectangular code and ballot paper page number rectangular code in the fixed position, base of ballot paper page, the frame line of two rectangular codes is thick lines, and each rectangular code is made up of the little square of 6 same sizes;
S2: ballot paper formatted data is sent to ballot box end by host side;
S3: the high speed scanner of ballot box end scans ballot paper to be positioned, obtains the scan image Pic0 of ballot paper;
S4: the scan image Pic0 of ballot box end to ballot paper carries out pre-service; Described pre-service comprises and scan image is converted into 24 colored DIB and schemes Pic1, then carries out image to Pic1 and turn gray-scale map, binaryzation, go discrete noise;
S5: ballot box end carries out sectional drawing at the bottom of ballot paper page to ballot paper image, described sectional drawing comprises ballot paper sequence number rectangular code and ballot paper page number rectangular code, and calculates the slope of sectional drawing, utilizes slope to carry out slant correction to sectional drawing image;
S6: carry out horizontal projection and vertical projection to sectional drawing image at the bottom of corrected ballot paper page, determines the position of ballot paper sequence number rectangular code left upper apex and ballot paper page number rectangular code right vertices; Utilize two vertex positions obtained to navigate to each little square, and judge there is nil in each little square, utilize the weights distribution principle of rectangular code, determine the sequence number of ballot paper kind and the page number;
S7: the sequence number utilizing ballot paper kind and the page number thereof obtained in S6, carries out slant correction according to ballot paper formatted data and slope by whole ballot paper image;
S8: the position of ballot paper sequence number rectangular code left upper apex is converted into its position at whole ballot paper image, namely determines the position of reference point;
S9: utilize the ballot paper formatted data that the position of reference point in ballot paper image, ballot paper kind and page number sequence number are corresponding, calculate approximate location that is to be identified or screenshot area, utilize this location finding form line thus determine accurate location that is to be identified or screenshot area.
2. the method for a kind of ballot paper Image Quick Orientation according to claim 1, is characterized in that: in described step S1, the position of the page number rectangular code centered beneath of ballot paper sequence number rectangular code and ballot paper is also provided with page number value.
3. the method for a kind of ballot paper Image Quick Orientation according to claim 1, is characterized in that: the ballot paper sequence number rectangular code in described step S1 is used for identifying the kind of ballot paper; Ballot paper page number rectangular code is used for identifying the page number of ballot paper, and ballot paper sequence number rectangular code is positioned at the ballot paper page number rectangular code left side.
4. the method for a kind of ballot paper Image Quick Orientation according to claim 1, is characterized in that: the slope in described step S5 is the ratio of the true altitude of rectangular code in average height half of about rectangular code in sectional drawing image and ballot paper page formatted data.
5. the method for a kind of ballot paper Image Quick Orientation according to claim 1, it is characterized in that: the horizontal projection in described step S6 is by down searching for from the first row of sectional drawing image, record the number of the black pixel point of every a line, thick lines are used due to rectangular code, make in horizontal projection, necessarily have a number to be greater than the threshold value of setting, the picturedeeps that first such number is corresponding are exactly the position of the vertical direction at place, rectangular code top; Vertical projection is by searching for from left to right sectional drawing image, record the number of the black pixel point of each row, if there is a number to be greater than the threshold value of setting, picturewide corresponding to this number be exactly the little square left side of ballot paper sequence number rectangular code first position in the horizontal direction; Turn left from the right side search, the first number is greater than the threshold value of this setting again, the picturewide that this number is corresponding be exactly the little square the right of ballot paper page number rectangular code the 6th position in the horizontal direction.
6. the method for a kind of ballot paper Image Quick Orientation according to claim 1, it is characterized in that: utilize this location finding form line in described step S9 thus determine accurate location that is to be identified or screenshot area, refer in the horizontal direction, relatively calculated value searches the step number of nearest straight line and the straight line step number to nearest straight line backward, thus determine that form alignment is on the left side of calculated value or the right, in like manner, in vertical direction, determine that form line in the top of calculated value or below.
7. the method for a kind of ballot paper Image Quick Orientation according to claim 6, is characterized in that: described step S9, before search, first by this position correspondingly mobile pixel; During straight line, just first move a pixel backward; When searching for backward, just first move forward a pixel; Search for straight line again.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410544808.6A CN104318231A (en) | 2014-10-15 | 2014-10-15 | Quick locating method for ballot image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410544808.6A CN104318231A (en) | 2014-10-15 | 2014-10-15 | Quick locating method for ballot image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104318231A true CN104318231A (en) | 2015-01-28 |
Family
ID=52373460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410544808.6A Pending CN104318231A (en) | 2014-10-15 | 2014-10-15 | Quick locating method for ballot image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104318231A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107194391A (en) * | 2017-04-21 | 2017-09-22 | 广东清华文通科技有限公司 | A kind of method for the intellectual analysis positioning electronic ballot paper for resisting image stretch skew |
| CN110163198A (en) * | 2018-09-27 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of Table recognition method for reconstructing, device and storage medium |
| CN110308346A (en) * | 2019-06-24 | 2019-10-08 | 中国航空无线电电子研究所 | Cockpit display system automatic test approach and system based on image recognition |
| CN110348360A (en) * | 2019-07-04 | 2019-10-18 | 上海眼控科技股份有限公司 | A kind of examining report recognition methods and equipment |
| CN113066222A (en) * | 2021-03-26 | 2021-07-02 | 杭州目光科技有限公司 | Voting system for realizing fair and public justice of major conferences through voting code publicity |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030001015A1 (en) * | 2001-07-02 | 2003-01-02 | Rouverol William Spence | Voting device with immediate feedback |
| CN1437157A (en) * | 2002-02-05 | 2003-08-20 | 安徽大学 | Rectangular code encoding method and rectangular code based on themethod |
| CN1815510A (en) * | 2006-02-28 | 2006-08-09 | 吴建国 | Electronic ballot box based on image-symbol identification |
-
2014
- 2014-10-15 CN CN201410544808.6A patent/CN104318231A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030001015A1 (en) * | 2001-07-02 | 2003-01-02 | Rouverol William Spence | Voting device with immediate feedback |
| CN1437157A (en) * | 2002-02-05 | 2003-08-20 | 安徽大学 | Rectangular code encoding method and rectangular code based on themethod |
| CN1815510A (en) * | 2006-02-28 | 2006-08-09 | 吴建国 | Electronic ballot box based on image-symbol identification |
Non-Patent Citations (2)
| Title |
|---|
| 胡俐蕊等: "选票图像识别的快速方法", 《计算机工程与设计》 * |
| 胡俐蕊等: "选票扫描图像识别中的快速定位方法", 《计算机应用与软件》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107194391A (en) * | 2017-04-21 | 2017-09-22 | 广东清华文通科技有限公司 | A kind of method for the intellectual analysis positioning electronic ballot paper for resisting image stretch skew |
| CN107194391B (en) * | 2017-04-21 | 2022-11-08 | 广东清华文通科技有限公司 | Method for intelligently analyzing and positioning electronic ballot capable of resisting image stretching deviation |
| CN110163198A (en) * | 2018-09-27 | 2019-08-23 | 腾讯科技（深圳）有限公司 | A kind of Table recognition method for reconstructing, device and storage medium |
| CN110163198B (en) * | 2018-09-27 | 2022-03-08 | 腾讯科技（深圳）有限公司 | Table identification reconstruction method and device and storage medium |
| CN110308346A (en) * | 2019-06-24 | 2019-10-08 | 中国航空无线电电子研究所 | Cockpit display system automatic test approach and system based on image recognition |
| CN110308346B (en) * | 2019-06-24 | 2021-10-26 | 中国航空无线电电子研究所 | Automatic testing method and system for cockpit display system based on image recognition |
| CN110348360A (en) * | 2019-07-04 | 2019-10-18 | 上海眼控科技股份有限公司 | A kind of examining report recognition methods and equipment |
| CN110348360B (en) * | 2019-07-04 | 2020-11-24 | 上海眼控科技股份有限公司 | Detection report identification method and equipment |
| CN113066222A (en) * | 2021-03-26 | 2021-07-02 | 杭州目光科技有限公司 | Voting system for realizing fair and public justice of major conferences through voting code publicity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107862303B (en) | Information identifying method, electronic device and the readable storage medium storing program for executing of form class diagram picture | |
| CN104318231A (en) | Quick locating method for ballot image | |
| CN110766014B (en) | Bill information positioning method, system and computer readable storage medium | |
| CN106156761B (en) | Image table detection and identification method for mobile terminal shooting | |
| CN100470590C (en) | Camera calibration method and calibration apparatus thereof | |
| RU2678485C1 (en) | Method of character segmentation and recognition | |
| CN103631928B (en) | LSH (Locality Sensitive Hashing)-based clustering and indexing method and LSH-based clustering and indexing system | |
| US9934444B2 (en) | Image processing apparatus, image processing method and computer-readable storage medium | |
| CN101303768B (en) | Method for correcting circle center error of circular index point when translating camera perspective projection | |
| CN102855232B (en) | A kind of tabular analysis adapts job operation | |
| US20020001029A1 (en) | Image processing apparatus, image processing method, and storage medium | |
| CN102184383B (en) | Automatic generation method of image sample of printed character | |
| US20150129658A1 (en) | Method for decoding matrix-type two-dimensional code | |
| CN102773862A (en) | Quick and accurate locating system used for indoor mobile robot and working method thereof | |
| CN111872544B (en) | Calibration method and device for laser light-emitting indication point and galvanometer coaxial vision system | |
| CN102360419A (en) | Method and system for computer scanning reading management | |
| CN103488965B (en) | Waybill typing and colored color lump coding/decoding system | |
| CN101794404A (en) | Method for coding and reading invisible two-dimensional codes | |
| CN113723347B (en) | Information extraction method and device, electronic equipment and storage medium | |
| CN102750530B (en) | Character recognition method and device | |
| CN106228103B (en) | A kind of recognition methods of bilayer code | |
| CN108958455A (en) | Handwriting trace projecting method and device | |
| US20190294936A1 (en) | Method for detecting and recognizing long-range high-density visual markers | |
| CN106909869A (en) | A kind of sampling grid partitioning method and device of matrix two-dimensional code | |
| CN114399677A (en) | Pointer instrument identification method based on text region reading |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150128 |
|
| RJ01 | Rejection of invention patent application after publication |