CN105046254A - Character recognition method and apparatus - Google Patents
Character recognition method and apparatus Download PDFInfo
- Publication number
- CN105046254A CN105046254A CN201510422663.7A CN201510422663A CN105046254A CN 105046254 A CN105046254 A CN 105046254A CN 201510422663 A CN201510422663 A CN 201510422663A CN 105046254 A CN105046254 A CN 105046254A
- Authority
- CN
- China
- Prior art keywords
- character
- line
- segmentation
- text
- image
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Character Input (AREA)
Abstract
The invention relates to a character recognition method and apparatus. The method comprises: obtaining an input text image; performing text line segmentation on the text image to obtain a text line region of the text image; performing character region segmentation on the text line region according to text character attributes to obtain character region information; and according to the character region information, performing single character segmentation in combination with the text image to obtain a character segmentation result. According to the character recognition method and apparatus, the text segmentation can be accurately performed, so that the recognition performance of OCR (Optical Character Recognition) is greatly improved; and the scheme has relatively high practical values in various text recognition applications.
Description
Technical field
The present invention relates to character recognition technologies field, particularly relate to a kind of character identifying method and device.
Background technology
OCR (OpticalCharacterRecognition, optical character identification) refer to that electronic equipment (such as scanner or digital camera) checks the character that paper prints, determining its shape by detecting dark, bright pattern, then with character identifying method, shape being translated into the process of computword; That is, text information is scanned, then analyzing and processing is carried out to image file, obtain the process of word and layout information.
Wherein, when carrying out character recognition, usually can need to carry out image and Character segmentation.Wherein, Iamge Segmentation refers to the region according to features such as gray scale, color, texture and shapes, image being divided into some mutual not crossovers, and makes these features in the same area, present similarity, and between zones of different, present obvious otherness.Character segmentation refers to does dividing processing to image, is split in the region and its background area that wherein comprise word, is to improve the important step of OCR recognition performance.
At present, conventional image partition method has multiple, such as: based on the partitioning algorithm of threshold value, based on the dividing method at edge, based on the dividing method etc. in region.And for the segmentation of character image, be also all continue to use above general image partitioning algorithm substantially.
But there is following defect in existing character image partitioning algorithm:
1, for the image of uneven illumination, the non-constant of effect that existing algorithm is usually split;
2, character area segmentation is imperfect, usually show as and single character is divided into polylith, or multiple character can not be separated, cause identification difficulty to OCR;
3, there is too much noise region, in the character zone be namely partitioned into, much in fact do not comprise character.
Summary of the invention
The embodiment of the present invention provides a kind of character identifying method and device, is intended to the accuracy improving character recognition.
The embodiment of the present invention proposes a kind of character identifying method, comprising:
Obtain the character image of input;
Line of text segmentation is carried out to described character image, obtains the line of text region of described character image;
Character zone segmentation is carried out according to alphabetic character attribute in described line of text region, obtains character zone information;
According to described character zone information, carry out single character cutting in conjunction with described character image, obtain Character segmentation result.
The embodiment of the present invention also proposes a kind of character recognition device, comprising:
Acquisition module, for obtaining the character image of input;
Line of text segmentation module, for carrying out line of text segmentation to described character image, obtains the line of text region of described character image;
Character segmentation module, for character zone segmentation is carried out according to alphabetic character attribute in described line of text region, obtains character zone information;
Cutting processing module, for according to described character zone information, carries out single character cutting in conjunction with described character image, obtains Character segmentation result.
A kind of character identifying method that the embodiment of the present invention proposes and device, by obtaining the character image of input; Line of text segmentation is carried out to character image, obtains the line of text region of character image; Character zone segmentation is carried out according to alphabetic character attribute in line of text region, obtains character zone information; According to character zone information, carry out single character cutting in conjunction with character image, obtain Character segmentation result, by this programme, can accurately Text segmentation be carried out, thus improve OCR recognition performance greatly, in various Text region application, this programme has larger practical value.
Accompanying drawing explanation
Fig. 1 is the terminal structure schematic diagram of the hardware running environment that embodiment of the present invention scheme relates to;
Fig. 2 is the schematic flow sheet of character identifying method first embodiment of the present invention;
Fig. 3 is the schematic flow sheet of character identifying method second embodiment of the present invention;
Fig. 4 a is a kind of example picture schematic diagram in the embodiment of the present invention;
Fig. 4 b is the edge detection results schematic diagram of a kind of example picture in the embodiment of the present invention;
Fig. 4 c is the edge horizontal direction connection result schematic diagram of a kind of example picture in the embodiment of the present invention;
Fig. 4 d is the convex closure segmentation result schematic diagram of a kind of example picture in the embodiment of the present invention;
Fig. 4 e is the monocase segmentation result schematic diagram of a kind of example picture in the embodiment of the present invention;
Fig. 5 is the high-level schematic functional block diagram of character recognition device first embodiment of the present invention;
Fig. 6 is the high-level schematic functional block diagram of character recognition device second embodiment of the present invention.
In order to make technical scheme of the present invention clearly, understand, be described in further detail below in conjunction with accompanying drawing.
Embodiment
Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
The primary solutions of the embodiment of the present invention is: by obtaining the character image of input; Line of text segmentation is carried out to character image, obtains the line of text region of character image; Character zone segmentation is carried out according to alphabetic character attribute in line of text region, obtains character zone information; According to character zone information, carry out single character cutting in conjunction with character image, obtain Character segmentation result, compared to existing technology, the accuracy of character recognition can be improved.
The terminal that the hardware running environment that embodiment of the present invention scheme relates to relates to, can be PC, also can be smart mobile phone, panel computer, E-book reader, MP3 (MovingPictureExpertsGroupAudioLayerIII, dynamic image expert compression standard audio frequency aspect 3) player, MP4 (MovingPictureExpertsGroupAudioLayerIV, dynamic image expert compression standard audio frequency aspect 3) player, pocket computer etc. have the packaged type terminal device of Presentation Function.Or, for being carried on the character recognition device in mobile terminal, PC terminal.
With reference to the terminal structure schematic diagram that Fig. 1, Fig. 1 are the hardware running environment that embodiment of the present invention scheme relates to.
As shown in Figure 1, this terminal can comprise: processor 1001, such as CPU, network interface 1004, user interface 1003, storer 1005, communication bus 1002.Wherein, communication bus 1002 is for realizing the connection communication between these assemblies.User interface 1003 can comprise display screen (Display), input block such as keyboard (Keyboard), and optional user interface 1003 can also comprise wireline interface, the wave point of standard.Network interface 1004 optionally can comprise wireline interface, the wave point (as WI-FI interface) of standard.Storer 1005 can be high-speed RAM storer, also can be stable storer (non-volatilememory), such as magnetic disk memory.Storer 1005 can also be optionally the memory storage independent of aforementioned processor 1001.
Alternatively, mobile terminal can also comprise camera, RF (RadioFrequency, radio frequency) circuit, sensor, voicefrequency circuit, WiFi module etc.Wherein, sensor such as optical sensor, motion sensor and other sensors.Particularly, optical sensor can comprise ambient light sensor and proximity transducer, and wherein, ambient light sensor the light and shade of environmentally light can regulate the brightness of display screen, and proximity transducer when mobile terminal moves in one's ear, can cut out display screen and/or backlight.As the one of motion sensor, Gravity accelerometer can detect the size of all directions (are generally three axles) acceleration, size and the direction of gravity can be detected time static, can be used for identifying the application (such as horizontal/vertical screen switching, dependent game, magnetometer pose calibrating) of mobile terminal attitude, Vibration identification correlation function (such as passometer, knock) etc.; Certainly, mobile terminal is other sensors such as configurable gyroscope, barometer, hygrometer, thermometer, infrared ray sensor also, do not repeat them here.
It will be understood by those skilled in the art that the restriction of the not structure paired terminal of the terminal structure shown in Fig. 1, the parts more more or less than diagram can be comprised, or combine some parts, or different parts are arranged.
As shown in Figure 1, operating system, network communication module, Subscriber Interface Module SIM and character recognition application program can be comprised as in a kind of storer 1005 of computer-readable storage medium.
In the terminal shown in Fig. 1, network interface 1004 is mainly used in connecting background server, carries out data communication with background server; User interface 1003 is mainly used in connecting client (user side), carries out data communication with client; And processor 1001 may be used for calling the character recognition application program stored in storer 1005, and perform following operation:
Obtain the character image of input;
Line of text segmentation is carried out to described character image, obtains the line of text region of described character image;
Character zone segmentation is carried out according to alphabetic character attribute in described line of text region, obtains character zone information;
According to described character zone information, carry out single character cutting in conjunction with described character image, obtain Character segmentation result.
Further, processor 1001 can call the character recognition application program stored in storer 1005, also performs following operation:
Also comprised before line of text segmentation is carried out to described character image:
Photo-irradiation treatment is gone to described character image.
Further, processor 1001 can call the character recognition application program stored in storer 1005, also performs following operation:
Line of text rim detection is carried out to described character image;
According to edge detection results, connect line of text horizontal direction edge, obtain the line of text region of described character image.
Further, processor 1001 can call the character recognition application program stored in storer 1005, also performs following operation:
According to alphabetic character attribute, obtain the convex closure in described line of text region, as character zone;
In described line of text region, described convex closure is split, remove the false areas not comprising word, obtain character zone information.
Further, processor 1001 can call the character recognition application program stored in storer 1005, also performs following operation:
Local segmentation threshold value is calculated in single convex closure;
According to the described local segmentation threshold value calculated, in described character image, according to described character zone information, local binarization process is carried out to single character, obtain final Character segmentation result.
The present embodiment passes through such scheme, especially by the character image obtaining user's input; Line of text segmentation is carried out to character image, obtains the line of text region of character image; Character zone segmentation is carried out according to alphabetic character attribute in line of text region, obtains character zone information; According to character zone information, carry out single character cutting in conjunction with character image, obtain Character segmentation result, by this programme, can accurately Text segmentation be carried out, thus improve OCR recognition performance greatly, in various Text region application, this programme has larger practical value.
Based on above-mentioned hardware configuration, character identifying method embodiment of the present invention is proposed.
As shown in Figure 2, first embodiment of the invention proposes a kind of character identifying method, comprising:
Step S101, obtains the character image of input;
The present embodiment scheme can be applied in OCR recognition technology, and performs the software flow of the program by a character recognition device.User can select the character image needing to carry out Text region.
The present embodiment scheme acquiescence for be the situation that character image does not need to carry out photo-irradiation treatment.
Step S102, carries out line of text segmentation to described character image, obtains the line of text region of described character image;
Character area (i.e. line of text region) adjacent in character image is split by the texture information that enriches according to word.
Particularly, first, line of text rim detection can be carried out to character image; Wherein, line of text edge detection algorithm can adopt the operators such as Sobel, Canny.
Then, according to edge detection results, connect line of text horizontal direction edge, specifically can be realized by technology such as horizontal direction projections, obtain the line of text region of character image.
Wherein, in the process in line of text region obtaining character image, the binarization segmentation treatment technology of image can be adopted.
The ultimate principle of the binaryzation of image is as follows:
The binary conversion treatment of image is exactly that the gray scale of the point on image is set to 0 or 255, namely whole image is presented obvious black and white effect.Gray level image by 256 brightness degrees is chosen by suitable threshold values and obtains the binary image that still can reflect integral image and local feature.
In Digital Image Processing, bianry image occupies very important status, particularly in the image procossing of practicality, the system formed with binary Images Processing realization is a lot, carry out the treatment and analyses of bianry image, first will Binary Sketch of Grey Scale Image, obtain binary image, so be conducive to again to image do process further time, the set character of image is only that the position of the point of 0 or 255 is relevant with pixel value, no longer relate to the multilevel values of pixel, make process become simple, and the process of data and decrement little.
In order to obtain desirable bianry image, the general region adopting boundary definition that is closed, that be communicated with not overlapping.The pixel that all gray scales are more than or equal to threshold values is judged as and belongs to certain objects, and its gray-scale value is 255 expressions, otherwise these pixels are excluded beyond object area, and gray-scale value is 0, represents the object area of background or exception.If certain certain objects has the gray-scale value of uniformity in inside, and it is in the homogeneous background that has other level gray values, uses threshold method just can obtain the segmentation effect compared.If this distinction, with the difference performance (such as texture is different) not on gray-scale value of background, can be converted to the difference of gray scale, then utilize threshold values selecting technology to split this image by object.Dynamic adjustments threshold values realizes the concrete outcome of its segmentation image of binaryzation dynamic observation of image.
Step S103, carries out character zone segmentation by described line of text region according to alphabetic character attribute, obtains character zone information;
Afterwards, according to the attribute of single alphabetic character by independent Text segmentation out.
Particularly, according to alphabetic character attribute, obtain the convex closure in line of text region, as character zone;
In described line of text region, described convex closure is split, remove the false areas not comprising word, obtain character zone information.
Step S104, according to described character zone information, carries out single character cutting in conjunction with described character image, obtains Character segmentation result.
After obtaining character zone information, carry out the segmentation of secondary local binarization in conjunction with original character image, finally obtain complete Text segmentation result.
Particularly, first, in single convex closure, local segmentation threshold value is calculated; Wherein, segmentation threshold computing method, can adopt otsu, watershed method, region-growing method etc.
Then, according to the described local segmentation threshold value calculated, in described character image, according to described character zone information, local binarization process is carried out to single character, obtain final Character segmentation result.
The present embodiment passes through such scheme, especially by the character image obtaining user's input; Line of text segmentation is carried out to character image, obtains the line of text region of character image; Character zone segmentation is carried out according to alphabetic character attribute in line of text region, obtains character zone information; According to character zone information, carry out single character cutting in conjunction with character image, obtain Character segmentation result, by this programme, can accurately Text segmentation be carried out, thus improve OCR recognition performance greatly, in various Text region application, this programme has larger practical value.
As shown in Figure 3, second embodiment of the invention proposes a kind of character identifying method, based on the embodiment shown in above-mentioned Fig. 2, at above-mentioned steps S102: can also comprise before carrying out line of text segmentation to described character image:
Step S105, goes photo-irradiation treatment to described character image.
Compare above-described embodiment, the present embodiment, for the character image of uneven illumination, carries out photo-irradiation treatment, to improve the effect of Text segmentation process.
Below by instantiation, the present embodiment Character segmentation scheme is described in detail:
First, input picture, as shown in fig. 4 a.
Then, go photo-irradiation treatment to the picture of input, and carry out rim detection to the picture of input, edge detection results as shown in Figure 4 b.
Afterwards, according to edge detection results, connect line of text horizontal direction edge, edge horizontal direction connection result as illustrated in fig. 4 c, obtains the line of text region of character image.
Afterwards, calculate local segmentation threshold value in single convex closure, convex closure segmentation as shown in figure 4d.
Finally, carry out Local threshold segmentation, and do monocase segmentation result, as shown in fig 4e.
Can be clearly seen that from Fig. 4 e, split the character edge complete display obtained according to this algorithm, the phenomenons such as uneven illumination all solve preferably.
Accordingly, character recognition device embodiment of the present invention is proposed.
As shown in Figure 5, first embodiment of the invention proposes a kind of character recognition device, comprising: the segmentation of acquisition module 201, line of text module 202, Character segmentation module 203 and cutting processing module 204, wherein:
Acquisition module 201, for obtaining the character image of input;
Line of text segmentation module 202, for carrying out line of text segmentation to described character image, obtains the line of text region of described character image;
Character segmentation module 203, for character zone segmentation is carried out according to alphabetic character attribute in described line of text region, obtains character zone information;
Cutting processing module 204, for according to described character zone information, carries out single character cutting in conjunction with described character image, obtains Character segmentation result.
Particularly, the present embodiment scheme can be applied in OCR recognition technology, and performs the software flow of the program by a character recognition device.User can select the character image needing to carry out Text region.
The present embodiment scheme acquiescence for be the situation that character image does not need to carry out photo-irradiation treatment.
After the character image obtaining input, character area (i.e. line of text region) adjacent in character image is split by the texture information that enriches according to word.
Particularly, first, line of text rim detection can be carried out to character image; Wherein, line of text edge detection algorithm can adopt the operators such as Sobel, Canny.
Then, according to edge detection results, connect line of text horizontal direction edge, specifically can be realized by technology such as horizontal direction projections, obtain the line of text region of character image.
Wherein, in the process in line of text region obtaining character image, the binarization segmentation treatment technology of image can be adopted.
The ultimate principle of the binaryzation of image is as follows:
The binary conversion treatment of image is exactly that the gray scale of the point on image is set to 0 or 255, namely whole image is presented obvious black and white effect.Gray level image by 256 brightness degrees is chosen by suitable threshold values and obtains the binary image that still can reflect integral image and local feature.
In Digital Image Processing, bianry image occupies very important status, particularly in the image procossing of practicality, the system formed with binary Images Processing realization is a lot, carry out the treatment and analyses of bianry image, first will Binary Sketch of Grey Scale Image, obtain binary image, so be conducive to again to image do process further time, the set character of image is only that the position of the point of 0 or 255 is relevant with pixel value, no longer relate to the multilevel values of pixel, make process become simple, and the process of data and decrement little.
In order to obtain desirable bianry image, the general region adopting boundary definition that is closed, that be communicated with not overlapping.The pixel that all gray scales are more than or equal to threshold values is judged as and belongs to certain objects, and its gray-scale value is 255 expressions, otherwise these pixels are excluded beyond object area, and gray-scale value is 0, represents the object area of background or exception.If certain certain objects has the gray-scale value of uniformity in inside, and it is in the homogeneous background that has other level gray values, uses threshold method just can obtain the segmentation effect compared.If this distinction, with the difference performance (such as texture is different) not on gray-scale value of background, can be converted to the difference of gray scale, then utilize threshold values selecting technology to split this image by object.Dynamic adjustments threshold values realizes the concrete outcome of its segmentation image of binaryzation dynamic observation of image.
Afterwards, according to the attribute of single alphabetic character by independent Text segmentation out.
Particularly, according to alphabetic character attribute, obtain the convex closure in line of text region, as character zone;
In described line of text region, described convex closure is split, remove the false areas not comprising word, obtain character zone information.
After obtaining character zone information, carry out the segmentation of secondary local binarization in conjunction with original character image, finally obtain complete Text segmentation result.
Particularly, first, in single convex closure, local segmentation threshold value is calculated; Wherein, segmentation threshold computing method, can adopt otsu, watershed method, region-growing method etc.
Then, according to the described local segmentation threshold value calculated, in described character image, according to described character zone information, local binarization process is carried out to single character, obtain final Character segmentation result.
The present embodiment passes through such scheme, especially by the character image obtaining user's input; Line of text segmentation is carried out to character image, obtains the line of text region of character image; Character zone segmentation is carried out according to alphabetic character attribute in line of text region, obtains character zone information; According to character zone information, carry out single character cutting in conjunction with character image, obtain Character segmentation result, by this programme, can accurately Text segmentation be carried out, thus improve OCR recognition performance greatly, in various Text region application, this programme has larger practical value.
As shown in Figure 6, second embodiment of the invention proposes a kind of character recognition device, and based on the embodiment shown in above-mentioned Fig. 5, this device also comprises:
Photo-irradiation treatment module 205, for going photo-irradiation treatment to described character image.
Compare above-described embodiment, the present embodiment, for the character image of uneven illumination, carries out photo-irradiation treatment, to improve the effect of Text segmentation process.
Below by instantiation, the present embodiment Character segmentation scheme is described in detail:
First, input picture, as shown in fig. 4 a.
Then, go photo-irradiation treatment to the picture of input, and carry out rim detection to the picture of input, edge detection results as shown in Figure 4 b.
Afterwards, according to edge detection results, connect line of text horizontal direction edge, edge horizontal direction connection result as illustrated in fig. 4 c, obtains the line of text region of character image.
Afterwards, calculate local segmentation threshold value in single convex closure, convex closure segmentation as shown in figure 4d.
Finally, carry out Local threshold segmentation, and do monocase segmentation result, as shown in fig 4e.
Can be clearly seen that from Fig. 4 e, split the character edge complete display obtained according to this algorithm, the phenomenons such as uneven illumination all solve preferably.
Also it should be noted that, in this article, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, article or device and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, article or device.When not more restrictions, the key element limited by statement " comprising ... ", and be not precluded within process, method, article or the device comprising this key element and also there is other identical element.
The invention described above embodiment sequence number, just to describing, does not represent the quality of embodiment.
Through the above description of the embodiments, those skilled in the art can be well understood to the mode that above-described embodiment method can add required general hardware platform by software and realize, hardware can certainly be passed through, but in a lot of situation, the former is better embodiment.Based on such understanding, technical scheme of the present invention can embody with the form of software product the part that prior art contributes in essence in other words, this computer software product is stored in a storage medium (as ROM/RAM, magnetic disc, CD), comprising some instructions in order to make a station terminal equipment (can be mobile phone, computing machine, server, or the network equipment etc.) perform method described in each embodiment of the present invention.
The foregoing is only the preferred embodiments of the present invention; not thereby the scope of the claims of the present invention is limited; every utilize instructions of the present invention and accompanying drawing content to do equivalent structure or flow process conversion; or be directly or indirectly used in other relevant technical field, be all in like manner included in scope of patent protection of the present invention.
Claims (10)
1. a character identifying method, is characterized in that, comprising:
Obtain the character image of input;
Line of text segmentation is carried out to described character image, obtains the line of text region of described character image;
Character zone segmentation is carried out according to alphabetic character attribute in described line of text region, obtains character zone information;
According to described character zone information, carry out single character cutting in conjunction with described character image, obtain Character segmentation result.
2. method according to claim 1, is characterized in that, described described character image is carried out to the step of line of text segmentation before also comprise:
Photo-irradiation treatment is gone to described character image.
3. method according to claim 1, is characterized in that, describedly carries out line of text segmentation to described character image, and the step obtaining the line of text region of described character image comprises:
Line of text rim detection is carried out to described character image;
According to edge detection results, connect line of text horizontal direction edge, obtain the line of text region of described character image.
4. method according to claim 1, is characterized in that, described character zone segmentation is carried out according to alphabetic character attribute in described line of text region, and the step obtaining character zone information comprises:
According to alphabetic character attribute, obtain the convex closure in described line of text region, as character zone;
In described line of text region, described convex closure is split, remove the false areas not comprising word, obtain character zone information.
5. the method according to any one of claim 1-4, is characterized in that, describedly carries out single character cutting according to described character zone information in conjunction with described character image, and the step obtaining Character segmentation result comprises:
Local segmentation threshold value is calculated in single convex closure;
According to the described local segmentation threshold value calculated, in described character image, according to described character zone information, local binarization process is carried out to single character, obtain final Character segmentation result.
6. a character recognition device, is characterized in that, comprising:
Acquisition module, for obtaining the character image of input;
Line of text segmentation module, for carrying out line of text segmentation to described character image, obtains the line of text region of described character image;
Character segmentation module, for character zone segmentation is carried out according to alphabetic character attribute in described line of text region, obtains character zone information;
Cutting processing module, for according to described character zone information, carries out single character cutting in conjunction with described character image, obtains Character segmentation result.
7. device according to claim 6, is characterized in that, described device also comprises:
Photo-irradiation treatment module, for going photo-irradiation treatment to described character image.
8. device according to claim 6, is characterized in that,
Described line of text segmentation module, also for carrying out line of text rim detection to described character image; According to edge detection results, connect line of text horizontal direction edge, obtain the line of text region of described character image.
9. device according to claim 6, is characterized in that,
Described Character segmentation module, also for according to alphabetic character attribute, obtains the convex closure in described line of text region, as character zone; In described line of text region, described convex closure is split, remove the false areas not comprising word, obtain character zone information.
10. the device according to any one of claim 6-9, is characterized in that,
Described cutting processing module, also for calculating local segmentation threshold value in single convex closure; According to the described local segmentation threshold value calculated, in described character image, according to described character zone information, local binarization process is carried out to single character, obtain final Character segmentation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510422663.7A CN105046254A (en) | 2015-07-17 | 2015-07-17 | Character recognition method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510422663.7A CN105046254A (en) | 2015-07-17 | 2015-07-17 | Character recognition method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105046254A true CN105046254A (en) | 2015-11-11 |
Family
ID=54452783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510422663.7A Pending CN105046254A (en) | 2015-07-17 | 2015-07-17 | Character recognition method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105046254A (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105930844A (en) * | 2016-04-20 | 2016-09-07 | 西北工业大学 | Method for improving paper medical test sheet mobile phone scanning identification rate |
| CN106940799A (en) * | 2016-01-05 | 2017-07-11 | 腾讯科技（深圳）有限公司 | Method for processing text images and device |
| CN107403130A (en) * | 2017-04-19 | 2017-11-28 | 北京粉笔未来科技有限公司 | A kind of character identifying method and character recognition device |
| CN108399405A (en) * | 2017-02-07 | 2018-08-14 | 腾讯科技（上海）有限公司 | Business license recognition methods and device |
| CN108460385A (en) * | 2018-03-02 | 2018-08-28 | 山东超越数控电子股份有限公司 | A kind of Document Segmentation method and apparatus |
| CN109558875A (en) * | 2018-11-14 | 2019-04-02 | 广州同略信息科技有限公司 | Method, apparatus, terminal and storage medium based on image automatic identification |
| CN109919146A (en) * | 2019-02-02 | 2019-06-21 | 上海兑观信息科技技术有限公司 | Picture character recognition methods, device and platform |
| CN110135411A (en) * | 2019-04-30 | 2019-08-16 | 北京邮电大学 | Business card identification method and device |
| CN110728687A (en) * | 2019-10-15 | 2020-01-24 | 卓尔智联(武汉)研究院有限公司 | File image segmentation method and device, computer equipment and storage medium |
| CN110766017A (en) * | 2019-10-22 | 2020-02-07 | 国网新疆电力有限公司信息通信公司 | Mobile terminal character recognition method and system based on deep learning |
| CN110956022A (en) * | 2019-12-04 | 2020-04-03 | 青岛盈智科技有限公司 | Document processing method and system |
| CN111898605A (en) * | 2020-08-28 | 2020-11-06 | 四川长虹网络科技有限责任公司 | Set top box information detection method and system based on image OCR recognition |
| CN112132003A (en) * | 2020-09-18 | 2020-12-25 | 北京搜狗科技发展有限公司 | Data processing method and device and recording equipment |
| CN112381089A (en) * | 2020-11-20 | 2021-02-19 | 山西同方知网数字出版技术有限公司 | Self-feedback text separation method and system in complex environment |
| CN113033563A (en) * | 2019-12-25 | 2021-06-25 | 北京世纪好未来教育科技有限公司 | Text segmentation method and device, electronic equipment and storage medium |
| CN113642619A (en) * | 2021-07-29 | 2021-11-12 | 华侨大学 | Method, device and equipment for training character recognition model and readable storage medium |
| CN113657369A (en) * | 2021-08-26 | 2021-11-16 | 北京有竹居网络技术有限公司 | Character recognition method and related equipment thereof |
| CN112381089B (en) * | 2020-11-20 | 2024-06-07 | 山西同方知网数字出版技术有限公司 | Self-feedback text separation method and system in complex environment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251892A (en) * | 2008-03-07 | 2008-08-27 | 北大方正集团有限公司 | Method and apparatus for cutting character |
| CN103106406A (en) * | 2011-11-09 | 2013-05-15 | 佳能株式会社 | Method and system for segmenting characters in text line with different character widths |
| CN104408449A (en) * | 2014-10-27 | 2015-03-11 | 西安电子科技大学宁波信息技术研究院 | Intelligent mobile terminal scene character processing method |
-
2015
- 2015-07-17 CN CN201510422663.7A patent/CN105046254A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101251892A (en) * | 2008-03-07 | 2008-08-27 | 北大方正集团有限公司 | Method and apparatus for cutting character |
| CN103106406A (en) * | 2011-11-09 | 2013-05-15 | 佳能株式会社 | Method and system for segmenting characters in text line with different character widths |
| CN104408449A (en) * | 2014-10-27 | 2015-03-11 | 西安电子科技大学宁波信息技术研究院 | Intelligent mobile terminal scene character processing method |
Non-Patent Citations (1)
| Title |
|---|
| 文颖: "数字、字符识别及其应用研究", 《中国博士学位论文全文数据库（信息科技辑）》 * |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102012819B1 (en) * | 2016-01-05 | 2019-08-21 | 텐센트 테크놀로지(센젠) 컴퍼니 리미티드 | Text image processing method and device |
| CN106940799A (en) * | 2016-01-05 | 2017-07-11 | 腾讯科技（深圳）有限公司 | Method for processing text images and device |
| WO2017118356A1 (en) * | 2016-01-05 | 2017-07-13 | 腾讯科技（深圳）有限公司 | Text image processing method and apparatus |
| KR20170137170A (en) * | 2016-01-05 | 2017-12-12 | 텐센트 테크놀로지(센젠) 컴퍼니 리미티드 | Method and apparatus for text image processing |
| US20180053048A1 (en) * | 2016-01-05 | 2018-02-22 | Tencent Technology (Shenzhen) Company Limited | Text image processing method and apparatus |
| CN106940799B (en) * | 2016-01-05 | 2020-07-24 | 腾讯科技（深圳）有限公司 | Text image processing method and device |
| US10572728B2 (en) * | 2016-01-05 | 2020-02-25 | Tencent Technology (Shenzhen) Company Limited | Text image processing method and apparatus |
| CN105930844A (en) * | 2016-04-20 | 2016-09-07 | 西北工业大学 | Method for improving paper medical test sheet mobile phone scanning identification rate |
| CN108399405A (en) * | 2017-02-07 | 2018-08-14 | 腾讯科技（上海）有限公司 | Business license recognition methods and device |
| CN108399405B (en) * | 2017-02-07 | 2023-06-27 | 腾讯科技（上海）有限公司 | Business license identification method and device |
| CN107403130A (en) * | 2017-04-19 | 2017-11-28 | 北京粉笔未来科技有限公司 | A kind of character identifying method and character recognition device |
| CN108460385A (en) * | 2018-03-02 | 2018-08-28 | 山东超越数控电子股份有限公司 | A kind of Document Segmentation method and apparatus |
| CN109558875A (en) * | 2018-11-14 | 2019-04-02 | 广州同略信息科技有限公司 | Method, apparatus, terminal and storage medium based on image automatic identification |
| CN109919146A (en) * | 2019-02-02 | 2019-06-21 | 上海兑观信息科技技术有限公司 | Picture character recognition methods, device and platform |
| CN110135411A (en) * | 2019-04-30 | 2019-08-16 | 北京邮电大学 | Business card identification method and device |
| CN110728687B (en) * | 2019-10-15 | 2022-08-02 | 卓尔智联(武汉)研究院有限公司 | File image segmentation method and device, computer equipment and storage medium |
| CN110728687A (en) * | 2019-10-15 | 2020-01-24 | 卓尔智联(武汉)研究院有限公司 | File image segmentation method and device, computer equipment and storage medium |
| CN110766017A (en) * | 2019-10-22 | 2020-02-07 | 国网新疆电力有限公司信息通信公司 | Mobile terminal character recognition method and system based on deep learning |
| CN110956022A (en) * | 2019-12-04 | 2020-04-03 | 青岛盈智科技有限公司 | Document processing method and system |
| CN113033563A (en) * | 2019-12-25 | 2021-06-25 | 北京世纪好未来教育科技有限公司 | Text segmentation method and device, electronic equipment and storage medium |
| CN111898605A (en) * | 2020-08-28 | 2020-11-06 | 四川长虹网络科技有限责任公司 | Set top box information detection method and system based on image OCR recognition |
| CN112132003A (en) * | 2020-09-18 | 2020-12-25 | 北京搜狗科技发展有限公司 | Data processing method and device and recording equipment |
| CN112381089A (en) * | 2020-11-20 | 2021-02-19 | 山西同方知网数字出版技术有限公司 | Self-feedback text separation method and system in complex environment |
| CN112381089B (en) * | 2020-11-20 | 2024-06-07 | 山西同方知网数字出版技术有限公司 | Self-feedback text separation method and system in complex environment |
| CN113642619A (en) * | 2021-07-29 | 2021-11-12 | 华侨大学 | Method, device and equipment for training character recognition model and readable storage medium |
| CN113642619B (en) * | 2021-07-29 | 2023-12-26 | 华侨大学 | Training method, training device, training equipment and training readable storage medium for character recognition model |
| CN113657369A (en) * | 2021-08-26 | 2021-11-16 | 北京有竹居网络技术有限公司 | Character recognition method and related equipment thereof |
| CN113657369B (en) * | 2021-08-26 | 2024-05-24 | 北京有竹居网络技术有限公司 | Character recognition method and related equipment thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105046254A (en) | Character recognition method and apparatus | |
| US10896349B2 (en) | Text detection method and apparatus, and storage medium | |
| US9646202B2 (en) | Image processing system for cluttered scenes and method of operation thereof | |
| CN110738125B (en) | Method, device and storage medium for selecting detection frame by Mask R-CNN | |
| US20150039637A1 (en) | Systems Apparatus and Methods for Determining Computer Apparatus Usage Via Processed Visual Indicia | |
| CN112162930B (en) | Control identification method, related device, equipment and storage medium | |
| CN111771226A (en) | Electronic device, image processing method thereof, and computer-readable recording medium | |
| CN104023249A (en) | Method and device of identifying television channel | |
| CN106874906B (en) | Image binarization method and device and terminal | |
| CN106250831A (en) | Image detecting method, device and the device for image detection | |
| CN111932544A (en) | Tampered image detection method and device and computer readable storage medium | |
| CN113781406B (en) | Scratch detection method and device for electronic component and computer equipment | |
| CN112101386B (en) | Text detection method, device, computer equipment and storage medium | |
| CN110414649B (en) | DM code positioning method, device, terminal and storage medium | |
| KR101602591B1 (en) | Methods and apparatuses for facilitating detection of text within an image | |
| CN106204552A (en) | The detection method of a kind of video source and device | |
| CN111080665B (en) | Image frame recognition method, device, equipment and computer storage medium | |
| CN111598084A (en) | Defect segmentation network training method, device and equipment and readable storage medium | |
| CN112634382B (en) | Method and device for identifying and replacing images of unnatural objects | |
| CN114663418A (en) | Image processing method and device, storage medium and electronic equipment | |
| CN118135253A (en) | Identification detection method, identification detection device, electronic equipment and storage medium | |
| CN115965848B (en) | Image processing method and related device | |
| CN107392205B (en) | Code value table generation method and device of remote controller | |
| CN116363049A (en) | Image processing method, apparatus, computer device, storage medium, and program product | |
| CN112686873A (en) | Image detection method and device |
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: 20151111 |
|
| RJ01 | Rejection of invention patent application after publication |