CN110580349A - chinese character and Persian intercommunication mutual identification technical method - Google Patents

chinese character and Persian intercommunication mutual identification technical method Download PDF

Info

Publication number
CN110580349A
CN110580349A CN201710540897.0A CN201710540897A CN110580349A CN 110580349 A CN110580349 A CN 110580349A CN 201710540897 A CN201710540897 A CN 201710540897A CN 110580349 A CN110580349 A CN 110580349A
Authority
CN
China
Prior art keywords
picture
chinese
character
characters
chinese 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
Application number
CN201710540897.0A
Other languages
Chinese (zh)
Inventor
艾朝君
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Individual
Original Assignee
Individual
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Individual filed Critical Individual
Priority to CN201710540897.0A priority Critical patent/CN110580349A/en
Publication of CN110580349A publication Critical patent/CN110580349A/en
Pending legal-status Critical Current

Links

Landscapes

  • Machine Translation (AREA)

Abstract

The invention relates to a method for realizing a system for mutually recognizing Boses in Chinese character intercommunication, which comprises a method for mutually recognizing Chinese character patterns according to the mutual communication of the Boses and a method for inquiring corresponding Boses according to the Chinese character patterns, wherein the method comprises the following steps: the method for mutually recognizing the character patterns of the Chinese characters according to the mutual communication of the Boses comprises two steps of establishing data mapping of the character patterns of the Chinese characters and the corresponding Boses, realizing network service and providing a mutual communication and recognition function; the invention relates to a method for inquiring corresponding Boss characters according to Chinese character patterns, which comprises two steps of establishing a Chinese character pattern characteristic character string database and a Chinese character pattern recognition realization method and an algorithm.

Description

chinese character and Persian intercommunication mutual identification technical method
1. field of the invention
the invention relates to the field of intercommunication and mutual identification of Chinese characters and various languages, in particular to a method for realizing direct intercommunication and mutual identification of Chinese and Bossword applied to a intercommunication and mutual identification system of Chinese and various languages.
2. background of the invention
the characters are tools for expressing ideas and developing life communication for human beings, have long history and huge characters, and are universal for human beings speaking Chinese. The number of Chinese characters is the first in the world at present, and 5000 years of culture inherits China to enhance the centripetal force and cohesion of each nation. The culture essence propagated by the Chinese characters strengthens the recognition among all nationalities, and is a binder for cultural communication of all nationalities in history. The Chinese spline is used as a long-term basis for the large country, and one of the important reasons is that the Chinese character-carrying culture is always recognized by each nation.
chinese characters are one of official characters of the united nations, all files must be translated into Chinese characters for storage, and foreigners learning Chinese \ Chinese characters are increasing along with increasing strength of Chinese nations. With the historical status of China in the world, the essence of Chinese famous family, Chinese character, should also become the universal language in the world.
However, in order to promote the Chinese character culture more quickly and more widely, a set of system for intercommunicating and mutually recognizing the Chinese characters and the languages and characters of all countries in the world needs to be established by means of the current high technology, each Chinese character is collected into a database of the system by the system, then a Chinese character learner accesses the database of the system by using a terminal capable of being connected with the internet, information in the database is fed back to the terminal, and the learner queries the character patterns of the Chinese characters according to the languages and characters in the world or queries the corresponding languages and characters in the world according to the character patterns of the Chinese characters.
3. summary of the invention
The invention aims to overcome the defects in the prior art and provides a method for realizing direct intercommunication and mutual recognition of Chinese and Bose in a intercommunication and mutual recognition system of Chinese and various languages.
a system implementation method for Chinese direct intercommunication mutual recognition of Persian is characterized in that: the method comprises a method for mutually recognizing Chinese character patterns according to the Gaussian character intercommunication and a method for inquiring corresponding Gaussian characters according to the Chinese character patterns.
the method for mutually recognizing the font of the Chinese character book according to the Bosswary intercommunication comprises the following steps:
Step 1), establishing data mapping of Chinese character patterns corresponding to the Bose text: all the Boussian translations are translated and written into Chinese character patterns, the written Chinese character patterns are scanned into an electronic version, each character generates a picture and is stored into a jpeg format picture file named by the corresponding Boussian, the jpeg format picture file and the corresponding Chinese character are mapped one to one, and a database is established.
Step 2), realizing network service, and providing the intercommunication mutual identification function of Chinese characters and Persian: installing a Chinese character text input box with a Chinese character intercommunication mutual recognition Persian function on hardware connected with the Internet for a user to input Chinese characters, wherein the Chinese character text input box is connected with a database storing a jpeg format picture file, the user selects the Persian intercommunication mutual recognition function on the Chinese character text input box, and a background service inquires a picture corresponding to Persian from the database mapped by Persian and Chinese character font pictures according to the Chinese characters, transmits the picture to a client and displays the picture on the client for the user to check and use;
the method for mutually identifying corresponding Boses text according to Chinese character intercommunication comprises the following steps:
Step 1), establishing a Chinese character font characteristic character string database;
Compiling and writing all the Boses characters into corresponding Chinese characters, scanning the written Chinese characters into an electronic edition, generating a picture for each character, storing the picture into a JPEG format picture file named by the corresponding Boses characters, and respectively processing each picture file to generate corresponding characteristic character strings, wherein the generation method of the characteristic character strings comprises the following steps:
firstly, reading an image;
reading the generated original pictures in the JPEG format named in the corresponding Bose language into picture processing software;
Secondly, color processing;
Processing the picture added in the first step in picture processing software to completely generate white black characters, wherein the white black characters are black fonts, and the background except the fonts is white;
Thirdly, cutting;
Processing the picture obtained in the second step through picture processing software, cutting off the vacant part outside the character horizontally and vertically, and overlapping the edge of the outermost side of the character with the edge of the picture;
Fourthly, compressing;
compressing the picture obtained after the third step to obtain a picture with a standard size;
fifthly, generating a characteristic string;
Scanning each pixel point of the picture obtained after the fourth step, taking black as 1 and white as 0 to obtain a 64-bit string,
all Chinese character font is processed according to the method to obtain character strings, pictures and Bose translation one-to-one mapping, and a character database is established;
step 2), a Chinese character font identification realization method and an algorithm:
step one, imaging:
The method comprises the steps that Chinese character recognition software with a photographing function is installed on hardware equipment connected with the Internet, the equipment connected with the Internet has the photographing function, Chinese characters needing to be recognized are photographed and taken by the hardware equipment, the size of an image obtained by photographing is set to be a fixed size, and only a single Chinese character font needing to be recognized is required to be ensured in the image obtained by photographing during photographing.
and a second step of treatment:
processing the picture generated in the first step according to the picture processing method in the step 1) of establishing the Chinese character font characteristic character string to obtain the Chinese character font characteristic character string in the picture.
Step three, comparison:
And uploading the character string of the Chinese character font to be identified, which is calculated in the second step, to a server, and comparing the character string with all character strings in the database to find the character string with the highest similarity to the character string of the Chinese character font to be identified.
and fourthly, displaying:
and after finding out the character string with the highest similarity to the characteristic character string of the character pattern of the Chinese character to be identified according to the third step, searching the picture and the Bose translation corresponding to the character string from the database according to the character string, transmitting the picture and the Bose translation to software installed on hardware connected with the Internet by a background through the Internet, and displaying the picture and the Bose translation through an interface of the software for comparison, study and use of a user.
In the step 1) of the method for mutually identifying corresponding Boses characters according to the character patterns of the Chinese characters, the size of the picture of the standard size picture generated in the fourth step is 8 x 8, and the unit is millimeter.
the size of the picture obtained by photographing in the first step of the step 2) of the method for mutually identifying corresponding Boses characters according to the intercommunication of the Chinese characters is set to be 800 × 600 in unit of millimeter.
in the step 2), the hardware connected with the internet is a computer with a photographing function in the first step.
In the first step of the method step 2) for mutually identifying corresponding Persian according to Chinese character font intercommunication, hardware connected with the Internet is other intelligent equipment such as a smart phone, a smart watch and the like with a photographing function.
The invention has originality, the invention uses the invention to make Chinese character form into high-tech informatization, each Chinese character is recorded and input into the Chinese character database by camera shooting, each Chinese character has corresponding Persian translation, the Chinese intercommunicating mutual recognition Persian system established by the method is used for Bosian users to intercommunicate and recognize corresponding Persian immediately according to the writing method of Chinese character straight-through Persian and after Bosian learners see a certain Chinese character, especially when the Chinese character form intercommunicates and recognizes corresponding Persian, the Chinese intercommunicating mutual recognition Persian system established by the invention is used to recognize Chinese character form with accuracy over 99%, which is beneficial for people to recognize and learn Chinese, and is beneficial for popularization and use of Chinese characters in the whole world
4. description of the drawings
The above and other aspects and advantages of the present invention will become more readily apparent by describing in more detail exemplary embodiments thereof with reference to the attached drawings, in which:
FIG. 1: the design method adopted by the invention is a flow chart;
fig. 2 is a picture in an embodiment of the invention.
fig. 3 is a picture in an embodiment of the invention.
fig. 4 is a picture in an embodiment of the invention.
5. Detailed description of the preferred embodiments
the present invention now will be described more fully hereinafter with reference to the accompanying drawings, in which various embodiments are shown. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
hereinafter, exemplary embodiments of the present invention will be described in more detail with reference to the accompanying drawings.
example (b): as shown in FIG. 1, a method for implementing a Chinese intercommunication mutual recognition Persian system includes a method for mutually recognizing Persian according to Chinese intercommunication and a method for mutually recognizing corresponding Chinese characters according to Persian intercommunication;
the method for mutually recognizing the Persian according to the Chinese character intercommunication comprises the following steps:
step 1) establishing data mapping between Chinese character patterns and corresponding Boses' texts: writing all the Boses characters into Chinese character patterns, scanning the written Chinese character patterns into an electronic version, generating a picture for each character, storing the picture into a Peg format picture file named by the corresponding Boses characters, mapping the Peg format picture file and the corresponding Boses characters in a one-to-one manner, and storing the Peg format picture file and the corresponding Boses characters into a database;
the chinese characters and the corresponding Peg format picture file named in bosch are exemplified as follows:
Chinese characters chinese character font picture named by Bose
han dynasty style toy han, JP
character (Chinese character) Word, JP
character (Chinese character) Word, JP
Shape of Form, JP
step 2), realizing network service, and providing a query function: mobile phone software with a Chinese character text input box with an inquiry function is installed on a mobile phone connected with the Internet for a user to input Chinese characters, the Chinese character text input box is connected with a database storing a Peg format picture file, the user selects a Bose intercommunication mutual identification function on the Chinese character text input box, a background service inquires out a picture corresponding to Bose according to a database mapped by Chinese characters and Chinese character font pictures and transmits the picture to a client, and the picture is displayed on the client for the user to check and learn;
the method for inquiring the corresponding Bos language according to the Chinese character patterns comprises the following steps:
step 1), establishing a font character string database;
Writing all the Boses characters into Chinese character font, scanning the written Chinese character font into electronic edition, generating a picture for each character, storing the picture into a Peg format picture file named by the corresponding Boses characters, processing each picture file respectively to generate corresponding characteristic character strings, wherein the generation method of the characteristic character strings comprises the following steps:
first step, image reading:
Reading the generated Peg format original picture named in corresponding Bose language into picture processing software, wherein the read original picture is shown in FIG. 2
step two, color processing:
The picture added in the first step is processed in the picture processing software, and the 'white (0xFFFFFF) black (0x000000) character' is completely generated, wherein the 'white black character' is that the font is black, the background except the font is white, and the processed picture is as shown in figure 3
third, cutting treatment:
processing the picture obtained in the second step through picture processing software, horizontally and vertically cutting off the spare part outside the character, and overlapping the edges of the outermost sides of the upper direction, the lower direction, the left direction and the right direction of the character with the edges of the picture;
the processed picture is shown in fig. 4;
Step four, compression treatment:
compressing each pixel point of the picture obtained after the third step to obtain an 8 x 8 picture;
Fifthly, generating a characteristic string:
scanning each pixel point of the picture obtained after the fourth step, wherein black is 1, white is 0, a 64-bit character string can be obtained, and the character string obtained after the Chinese character font of the 'Ming' character is processed is as follows:
0000001100000100000100001000101011111110000101000010001000100100
the word strings obtained after processing are translated into one-to-one mapping with pictures, Chinese characters, pinyin and Bose, and the mapping is stored in a database;
step 2), a Chinese character font identification realization method and an algorithm:
The first step is as follows: imaging:
The method comprises the steps that Chinese character recognition software with a photographing function is installed on a smart phone connected with the Internet, the smart phone connected with the Internet has the photographing function, a smart camera is used for photographing and taking images of Chinese character patterns needing to be recognized, a flash lamp on the smart phone is turned on during photographing, accordingly, the phenomenon that shadow exists on a picture and the picture quality is affected is avoided, the size of the picture obtained through photographing is set to be 800 x 600, and during photographing, it is required to be ensured that the picture obtained through photographing only has a single Chinese character pattern needing to be recognized;
the second step is that: and (3) treatment:
processing the picture generated in the first step according to the picture processing method in the step 1) of establishing the character string of the Chinese character font to obtain the character string of the Chinese character font in the picture;
The third step: and (3) comparison:
Uploading the characteristic character string of the Chinese character font to be identified calculated in the second step to a server, comparing the characteristic character string with all character strings in a database, and finding out the character string with the highest similarity with the characteristic character string of the Chinese character font to be identified, wherein a similarity comparison algorithm is shown as the following table:
the fourth step: displaying:
After finding out the character string with the highest similarity to the characteristic character string needing to identify the character pattern of the Chinese character according to the third step, the picture Chinese character, the pinyin and the Persian character corresponding to the character string can be found out from the database according to the character string, and the picture Chinese character, the pinyin and the Persian character are compared and learned by the user through the Internet by the background.
through tests, according to the algorithm, the accuracy of the Chinese character pattern recognition is over 99%.
the above description is only an example of the present invention, and is not intended to limit the present invention. The invention is susceptible to various modifications and alternative forms. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (5)

1. a Chinese character and Persian intercommunication mutual identification technical method,
the method is characterized in that:
The method comprises a method for directly corresponding to the Bose language through Chinese characters and a method for directly corresponding to the Chinese characters through the Bose language;
the technical method for intercommunicating and mutually identifying the Chinese characters and the Persian comprises the following steps:
step 1, establishing data mapping of Chinese characters and corresponding Bose texts: compiling and writing all the Boussian texts into Chinese characters, scanning the written Chinese character patterns into an electronic version, generating a picture for each character, storing the picture into a jpeg format picture file named by the corresponding Boussian texts, and mapping the jpeg format picture file and the corresponding Chinese characters one to build a database;
step 2, realizing network service, and providing the intercommunication mutual identification function of Chinese characters and Persian: installing a Chinese character text input box with a Chinese character intercommunication mutual recognition Persian function on hardware connected with the Internet for a user to input Chinese characters, wherein the Chinese character text input box is connected with a database storing a jpeg format picture file, the user selects the Persian intercommunication mutual recognition function on the Chinese character text input box, and a background service inquires a picture corresponding to Persian from the database mapped by Persian and Chinese character font pictures according to the Chinese characters, transmits the picture to a client and displays the picture on the client for the user to check and use;
The method for mutually identifying corresponding Boses text according to Chinese character intercommunication comprises the following steps:
step 1), establishing a Chinese character characteristic character string database;
Compiling and writing all the Boses characters into corresponding Chinese characters, scanning the written Chinese characters into an electronic edition, generating a picture for each character, storing the picture into a JPEG format picture file named by the corresponding Boses characters, and respectively processing each picture file to generate corresponding characteristic character strings, wherein the generation method of the characteristic character strings comprises the following steps:
firstly, reading an image;
reading the generated original pictures in the JPEG format named in the corresponding Bose language into picture processing software;
Secondly, color processing;
Processing the picture added in the first step in picture processing software to completely generate white black characters, wherein the white black characters are black fonts, and the background except the fonts is white;
Thirdly, cutting;
Processing the picture obtained in the second step through picture processing software, cutting off the vacant part outside the character horizontally and vertically, and overlapping the edge of the outermost side of the character with the edge of the picture;
fourthly, compressing;
compressing the picture obtained after the third step to obtain a picture with a standard size;
Fifthly, generating a characteristic string;
scanning each pixel point of the picture obtained after the fourth step, taking black as 1 and white as 0 to obtain a 64-bit string,
all Chinese character font is processed according to the method to obtain character strings, and the character strings are translated into one-to-one mapping with pictures and Bose texts to establish a character string database;
Step 2), a Chinese character recognition realization method and algorithm:
step one, imaging:
the method comprises the steps that Chinese character recognition software with a photographing function is installed on hardware equipment connected with the Internet, the equipment connected with the Internet has the photographing function, the hardware equipment is used for photographing Chinese characters to be recognized, the size of an image obtained by photographing is set to be a fixed size, and only a single Chinese character font needing to be recognized is required to be ensured in the image obtained by photographing during photographing.
And a second step of treatment:
processing the picture generated in the first step according to the picture processing method in the step 1) of establishing the Chinese character font characteristic character string to obtain the Chinese character font characteristic character string in the picture.
Step three, comparison:
And uploading the character string of the Chinese character font to be identified, which is calculated in the second step, to a server, and comparing the character string with all character strings in the database to find the character string with the highest similarity to the character string of the Chinese character font to be identified.
and fourthly, displaying:
and after finding out the character string with the highest similarity to the characteristic character string of the character pattern of the Chinese character to be identified according to the third step, searching the picture and the Bose translation corresponding to the character string from the database according to the character string, transmitting the picture and the Bose translation to software installed on hardware connected with the Internet by a background through the Internet, and displaying the picture and the Bose translation through an interface of the software for comparison, study and use of a user.
2. the method for implementing intercommunication between Chinese characters and Bosswords as claimed in claim 1, wherein: in the step 1) of the method for mutually identifying corresponding Boses characters according to the character patterns of the Chinese characters, the size of the picture of the standard size picture generated in the fourth step is 8 x 8, and the unit is millimeter.
3. The method for implementing intercommunication between Chinese characters and Bosswords as claimed in claim 1, wherein: the size of the picture obtained by photographing in the first step of the step 2) of the method for mutually identifying corresponding Boses characters according to the intercommunication of the Chinese characters is set to be 800 × 600 in unit of millimeter.
4. the method for implementing intercommunication between Chinese characters and Bosswords as claimed in claim 1, wherein:
In the step 2), the hardware connected with the internet is a computer with a photographing function in the first step.
5. The method for implementing intercommunication between Chinese characters and Bosswords as claimed in claim 1, wherein:
In the first step of the method step 2) for mutually identifying corresponding Persian according to Chinese character font intercommunication, hardware connected with the Internet is other intelligent equipment such as a smart phone, a smart watch and the like with a photographing function.
CN201710540897.0A 2017-07-04 2017-07-04 chinese character and Persian intercommunication mutual identification technical method Pending CN110580349A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710540897.0A CN110580349A (en) 2017-07-04 2017-07-04 chinese character and Persian intercommunication mutual identification technical method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710540897.0A CN110580349A (en) 2017-07-04 2017-07-04 chinese character and Persian intercommunication mutual identification technical method

Publications (1)

Publication Number Publication Date
CN110580349A true CN110580349A (en) 2019-12-17

Family

ID=68808754

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710540897.0A Pending CN110580349A (en) 2017-07-04 2017-07-04 chinese character and Persian intercommunication mutual identification technical method

Country Status (1)

Country Link
CN (1) CN110580349A (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1529219A (en) * 2002-09-05 2004-09-15 刘荣杰 Language code inputting method
CN103778250A (en) * 2014-02-19 2014-05-07 张朝亮 Implement method for Chinese wubi cursive script dictionary query system

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1529219A (en) * 2002-09-05 2004-09-15 刘荣杰 Language code inputting method
CN103778250A (en) * 2014-02-19 2014-05-07 张朝亮 Implement method for Chinese wubi cursive script dictionary query system

Similar Documents

Publication Publication Date Title
US10402640B1 (en) Method and system for schematizing fields in documents
CN109753968A (en) Generation method, device, equipment and the medium of character recognition model
RU2634194C1 (en) Verification of optical character recognition results
WO2022134771A1 (en) Table processing method and apparatus, and electronic device and storage medium
CN103778250A (en) Implement method for Chinese wubi cursive script dictionary query system
US10460192B2 (en) Method and system for optical character recognition (OCR) of multi-language content
CN110263792B (en) Image recognizing and reading and data processing method, intelligent pen, system and storage medium
CN109993075B (en) Chat application session content storage method, system and device
CN109034148A (en) One kind is based on character image identification audio reading method and its device
CN110516125B (en) Method, device and equipment for identifying abnormal character string and readable storage medium
CN111881900A (en) Corpus generation, translation model training and translation method, apparatus, device and medium
CN110580359A (en) Chinese character and Arabic intercommunication mutual identification technical method
CN110580343A (en) Chinese character and Urdu intercommunication mutual recognition technical method
CN110134920A (en) Draw the compatible display methods of text, device, terminal and computer readable storage medium
CN110580349A (en) chinese character and Persian intercommunication mutual identification technical method
CN110580355A (en) Intercommunication mutual identification technique for Chinese characters and all language characters
CN110580360A (en) intercommunication mutual identification technique for Chinese characters and all language characters
CN110580353A (en) intercommunication mutual identification technical method for Chinese characters and Vietnamese
CN110580345A (en) chinese character and French intercommunication mutual identification technical method
CN110580356A (en) Chinese character and German intercommunication mutual identification technical method
CN110580348A (en) chinese character and Russian intercommunication mutual recognition technical method
CN110580344A (en) intercommunication mutual identification technical method of Chinese characters and Spanish language
CN110580357A (en) chinese character and Korean intercommunication mutual identification technical method
CN110580351A (en) chinese character and Italian intercommunication mutual recognition technical method
CN110580358A (en) intercommunication mutual identification technical method for Chinese characters and Sanskrit

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
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20191217