CN107688813A - A kind of character identifying method - Google Patents
A kind of character identifying method Download PDFInfo
- Publication number
- CN107688813A CN107688813A CN201710871108.1A CN201710871108A CN107688813A CN 107688813 A CN107688813 A CN 107688813A CN 201710871108 A CN201710871108 A CN 201710871108A CN 107688813 A CN107688813 A CN 107688813A
- Authority
- CN
- China
- Prior art keywords
- character
- identified
- region
- pixel
- single character
- 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
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Character Discrimination (AREA)
Abstract
The present invention proposes a kind of character identifying method, solves the problems, such as the character recognition containing only the display software for determining character, this method is simply, efficiently.Identification process:Determine the independent identification region of picture;Character string in region to be identified is divided into single character;Normalizing is carried out to the rgb value of single character;The characteristic value summation in a certain sampling interval is carried out to the rgb value of character normalizing to be identified;Summed result is matched with character in character repertoire;If character to be identified only matches a character in character repertoire, identify successfully;Otherwise the sampling interval is changed, continues to identify;Until identify in frame out identification in need character.
Description
Technical field
The present invention relates to a kind of character identifying method, the more particularly to character recognition containing only the display software for determining character.
Background technology
In the software for having high security requirement, it is necessary to monitor key character display whether correctly, as HUD show software,
Flight key character (e.g., current air speed, present level) is needed to monitor.
Existing character recognition technologies need, using complicated algorithm, to match huge character sample storehouse, compare and expend the time;
And, it is necessary to which algorithm is as far as possible simple for showing software to high security, reduction proving time cost, operation efficiency improves as far as possible,
So as to improve Consumer's Experience effect.
The content of the invention
For proposing a kind of character identifying method containing only the display software for determining character, the present invention, for needing what is identified
Character picture, the independent identification region of picture is determined, the character string in region to be identified is divided into single character, obtains character
Rgb value, normalizing is carried out to rgb value, carries out the characteristic value summation at particular sample interval, summed result is entered with character in character repertoire
Row matching, so as to reach the purpose of character recognition, the algorithm is simple, and reliability is high, disclosure satisfy that high security shows that software will
Ask.
The technical scheme is that:
A kind of character identifying method, it is characterised in that:Comprise the following steps:
Step 1:The data of image to be displayed are scanned, according to pre-determined identification region, in scan data
It is determined that each independent identification region to be identified, and the character string in region to be identified is divided into single character, determine single
The identification region of character;
Step 2:The identification region of single character is handled as follows:
Step 2.1:Binaryzation is carried out to each pixel in single character recognition region:If rgb value be present in pixel,
The pixel characteristic value is arranged to 1, is otherwise 0;
Step 2.2:Sampling between-line spacing to single character recognition region according to setting, to the pixel point feature of all samplings
Value summation, is matched character to be identified with character in character repertoire according to summed result;If there is multiple matching results, then
Between-line spacing+1 will be sampled, then the pixel characteristic values of all samplings will be summed, according to summed result by character to be identified and upper one
The multiple matching results obtained in circulation matching process are matched, until existence anduniquess matching result;
Step 3:Repeat step 2, complete the character recognition in all single character recognition regions.
Beneficial effect
It is an advantage of the invention that:The method of character recognition provided by the present invention, independent of complicated algorithm and huge word
Sample Storehouse is accorded with, but normalizing, characteristic value summation are carried out to the rgb value of character to be identified, as a result matches, reaches the mesh of character recognition
's.This method has the advantages that simple, efficient, improves the efficiency of high security software character monitoring.
The additional aspect and advantage of the present invention will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
The above-mentioned and/or additional aspect and advantage of the present invention will become in the description from combination accompanying drawings below to embodiment
Substantially and it is readily appreciated that, wherein:
Fig. 1:Character recognizing process figure;
Fig. 2:Character repertoire;
Fig. 3:The key character for needing to identify is illustrated;
Fig. 4:RGB arrays corresponding to character string " 200 " in Fig. 3 regions 1;
Fig. 5:RGB arrays corresponding to character " 2 " in Fig. 4.
Embodiment
Embodiments of the invention are described below in detail, the embodiment is exemplary, it is intended to for explaining the present invention, and
It is not considered as limiting the invention.
The main thinking principle of character identifying method in the present embodiment is the character picture for needing to identify, determines picture
The independent identification region in face, the character string in region to be identified is divided into single character, the rgb value of character is obtained, to rgb value
Normalizing is carried out, carries out the characteristic value summation at particular sample interval, summed result is matched with character in character repertoire, so as to reach
The purpose of character recognition.
Specifically include following steps:
Step 1:The data of image to be displayed are scanned, according to pre-determined identification region, in scan data
It is determined that each independent identification region to be identified, and the character string in region to be identified is divided into single character, determine single
The identification region of character;
Step 2:The identification region of single character is handled as follows:
Step 2.1:Binaryzation is carried out to each pixel in single character recognition region:If rgb value be present in pixel,
The pixel characteristic value is arranged to 1, is otherwise 0;
Step 2.2:Sampling between-line spacing to single character recognition region according to setting, to the pixel point feature of all samplings
Value summation, is matched character to be identified with character in character repertoire according to summed result;If there is multiple matching results, then
Between-line spacing+1 will be sampled, then the pixel characteristic values of all samplings will be summed, according to summed result by character to be identified and upper one
The multiple matching results obtained in circulation matching process are matched, until existence anduniquess matching result;
Step 3:Repeat step 2, complete the character recognition in all single character recognition regions.
It should be noted that the matching refers under a certain sampling between-line spacing, the characteristic value summed result of character to be identified
And the difference of the characteristic value of character is in the range of tolerable variance of setting in character repertoire.
The present invention is described with reference to embodiment:
The character repertoire for determining character is established in advance:
1st, the character needed to display software, obtains rgb value;
2nd, binaryzation is carried out to each pixel of character:If pixel has rgb value, the pixel characteristic value is set
1 is set to, is otherwise 0;
3rd, set it is some sampling between-line spacings (sampling between-line spacing determination principle be:By Fig. 1 flow, can recognize that
Carry out character all in character repertoire, and sampling interval number is minimum)
4th, calculate under each sampling between-line spacing, in character repertoire the characteristic value of each character with and store.
After establishing character repertoire, character recognition is carried out using following steps:
Step 1:The data of image to be displayed are scanned, according to pre-determined identification region, in scan data
It is determined that each independent identification region to be identified, and the character string in region to be identified is divided into single character, determine single
The identification region of character.
The pre-determined identification region is that continuous a line character is an identification region, region as shown in Figure 3
1-region 6.Rgb value corresponding to scanning character string, run into the several columns of RGB full 0s, then it is assumed that be the end of single character, if entirely
0 row exceed certain limit, then it is assumed that are the end of character string.So as to which character string is divided into single character.To region in Fig. 4
1 character string " 200 " obtains single character " 2 " after being separated.
Step 2:The identification region of single character is handled as follows:
Step 2.1:Binaryzation is carried out to each pixel in single character recognition region:If rgb value be present in pixel,
The pixel characteristic value is arranged to 1, is otherwise 0;
Step 2.2:Sampling between-line spacing to single character recognition region according to setting, to the pixel point feature of all samplings
Value summation, is matched character to be identified with character in character repertoire according to summed result;If there is multiple matching results, then
Between-line spacing+1 will be sampled, then the pixel characteristic values of all samplings will be summed, according to summed result by character to be identified and upper one
The multiple matching results obtained in circulation matching process are matched, until existence anduniquess matching result;
For single character " 2 ", the characteristic value that 1 is in the ranks divided into using sampling is summed, and 1 is in the ranks divided into being sampled in character library
Character is matched, unique match to " 2 ", so as to identify 2;Next single character " 0 " is identified, discovery is matched in character library
" 0 " and " C ";Now the sampling interval is changed to 4, and by matching, unique match identifies 0 to " 0 ".
Step 3:Repeat step 2, complete the character recognition in all single character recognition regions.
Although embodiments of the invention have been shown and described above, it is to be understood that above-described embodiment is example
Property, it is impossible to limitation of the present invention is interpreted as, one of ordinary skill in the art is not departing from the principle and objective of the present invention
In the case of above-described embodiment can be changed within the scope of the invention, change, replace and modification.
Claims (1)
- A kind of 1. character identifying method, it is characterised in that:Comprise the following steps:Step 1:The data of image to be displayed are scanned, according to pre-determined identification region, determined in scan data Each independent identification region to be identified, and the character string in region to be identified is divided into single character, determine single character Identification region;Step 2:The identification region of single character is handled as follows:Step 2.1:Binaryzation is carried out to each pixel in single character recognition region:, should if pixel has rgb value Pixel characteristic value is arranged to 1, is otherwise 0;Step 2.2:Sampling between-line spacing to single character recognition region according to setting, is asked the pixel characteristic value of all samplings With character to be identified is matched with character in character repertoire according to summed result;If there is multiple matching results, then will adopt Sample between-line spacing+1, then the pixel characteristic value of all samplings is summed, character to be identified and upper one are circulated according to summed result The multiple matching results obtained in matching process are matched, until existence anduniquess matching result;Step 3:Repeat step 2, complete the character recognition in all single character recognition regions.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710871108.1A CN107688813A (en) | 2017-09-24 | 2017-09-24 | A kind of character identifying method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710871108.1A CN107688813A (en) | 2017-09-24 | 2017-09-24 | A kind of character identifying method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107688813A true CN107688813A (en) | 2018-02-13 |
Family
ID=61155390
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710871108.1A Pending CN107688813A (en) | 2017-09-24 | 2017-09-24 | A kind of character identifying method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107688813A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110660267A (en) * | 2019-09-18 | 2020-01-07 | 恒大智慧科技有限公司 | Parking management method, parking management system, and storage medium |
CN110740294A (en) * | 2019-09-18 | 2020-01-31 | 恒大智慧科技有限公司 | Intelligent vehicle warehousing method, vehicle and storage medium |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000040153A (en) * | 1998-07-22 | 2000-02-08 | Ricoh Co Ltd | Image processing method, medium recording image processing program and image processor |
CN101923741A (en) * | 2010-08-11 | 2010-12-22 | 西安理工大学 | Paper currency number identification method based on currency detector |
CN102663360A (en) * | 2012-03-30 | 2012-09-12 | 中南大学 | Method for automatic identifying steel slab coding and steel slab tracking system |
CN102663380A (en) * | 2012-03-30 | 2012-09-12 | 中南大学 | Method for identifying character in steel slab coding image |
CN104899965A (en) * | 2015-05-15 | 2015-09-09 | 浙江大学 | Multi-national paper money serial number identification method based on sorting machine |
CN105989659A (en) * | 2016-04-15 | 2016-10-05 | 新达通科技股份有限公司 | Similar character recognition method and paper currency crown code recognition method |
CN106780960A (en) * | 2015-11-18 | 2017-05-31 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of Iranian bank note currency type and system |
CN107067008A (en) * | 2017-01-17 | 2017-08-18 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of similar character and system |
-
2017
- 2017-09-24 CN CN201710871108.1A patent/CN107688813A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2000040153A (en) * | 1998-07-22 | 2000-02-08 | Ricoh Co Ltd | Image processing method, medium recording image processing program and image processor |
CN101923741A (en) * | 2010-08-11 | 2010-12-22 | 西安理工大学 | Paper currency number identification method based on currency detector |
CN102663360A (en) * | 2012-03-30 | 2012-09-12 | 中南大学 | Method for automatic identifying steel slab coding and steel slab tracking system |
CN102663380A (en) * | 2012-03-30 | 2012-09-12 | 中南大学 | Method for identifying character in steel slab coding image |
CN104899965A (en) * | 2015-05-15 | 2015-09-09 | 浙江大学 | Multi-national paper money serial number identification method based on sorting machine |
CN106780960A (en) * | 2015-11-18 | 2017-05-31 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of Iranian bank note currency type and system |
CN105989659A (en) * | 2016-04-15 | 2016-10-05 | 新达通科技股份有限公司 | Similar character recognition method and paper currency crown code recognition method |
CN107067008A (en) * | 2017-01-17 | 2017-08-18 | 深圳怡化电脑股份有限公司 | A kind of recognition methods of similar character and system |
Non-Patent Citations (3)
Title |
---|
CHANG Y C 等: "License Plate Character Recognition Using Block-Binary-Pixel-Sum Features", 《INTERNATIONAL CONFERENCE ON COMPUTER, NETWORKS AND COMMUNICATION ENGINEERING (ICCNCE 2013)》 * |
叶晨洲 等: "车辆牌照字符识别系统", 《计算机系统应用》 * |
巩玉滨 等: "一种数显仪表数字字符识别方法研究", 《山东建筑大学学报》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110660267A (en) * | 2019-09-18 | 2020-01-07 | 恒大智慧科技有限公司 | Parking management method, parking management system, and storage medium |
CN110740294A (en) * | 2019-09-18 | 2020-01-31 | 恒大智慧科技有限公司 | Intelligent vehicle warehousing method, vehicle and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9189694B2 (en) | Image processing device and image processing method | |
EP3552067B1 (en) | Methods and systems for discovery of prognostic subsequences in time series | |
EP3309705B1 (en) | Qr code feature detection method and system | |
EP3001352B1 (en) | Image processing apparatus and image processing method | |
CN103955660B (en) | Method for recognizing batch two-dimension code images | |
CN109766883B (en) | Method for rapidly extracting network video subtitles based on deep neural network | |
CN107688813A (en) | A kind of character identifying method | |
US9934429B2 (en) | Storage medium, recognition method, and recognition apparatus | |
US9715729B2 (en) | Method and apparatus for processing block to be processed of urine sediment image | |
CN103077401A (en) | Method and system for detecting context histogram abnormal behaviors based on light streams | |
CN108171229B (en) | Method and system for identifying hollow adhesion verification code | |
JP2015135576A (en) | Document item recognition method, device and program | |
US20210256302A1 (en) | Image determination device, image determination method, and non-transitory computer readable medium storing program | |
JP6356015B2 (en) | Gene expression information analyzing apparatus, gene expression information analyzing method, and program | |
JP5857634B2 (en) | Word space detection device, word space detection method, and computer program for word space detection | |
US8682078B2 (en) | Moving image processing apparatus, moving image processing method, and program | |
JP5387378B2 (en) | Character identification device and character identification method | |
US20170128843A1 (en) | Systems, methods, and apparatuses for extracting and analyzing live video content | |
US20150063698A1 (en) | Assisted OCR | |
CN106803053B (en) | Fingerprint image processing method and device | |
CN111783780B (en) | Image processing method, device and computer readable storage medium | |
CN113850157A (en) | Character recognition method based on neural network | |
US20160300098A1 (en) | Data processing method and system | |
JP2021005234A (en) | Form recognition device, form recognition method, and form recognition system | |
CN112541505A (en) | Text recognition method, text recognition device and computer-readable storage medium |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180213 |
|
WD01 | Invention patent application deemed withdrawn after publication |