CN101819683A - Method for reconstructing Chinese character font - Google Patents
Method for reconstructing Chinese character font Download PDFInfo
- Publication number
- CN101819683A CN101819683A CN200910191209A CN200910191209A CN101819683A CN 101819683 A CN101819683 A CN 101819683A CN 200910191209 A CN200910191209 A CN 200910191209A CN 200910191209 A CN200910191209 A CN 200910191209A CN 101819683 A CN101819683 A CN 101819683A
- Authority
- CN
- China
- Prior art keywords
- chinese character
- parts
- template
- make
- matching block
- 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
Images
Landscapes
- Document Processing Apparatus (AREA)
- Controls And Circuits For Display Device (AREA)
Abstract
The invention discloses a method for reconstructing a character font by editing composite figures or texts. The method overcomes the drawbacks of high cost and low quality of the conventional method for reconstructing the character font. In the method, a mode of software and manual alternate operation is adopted, a round-robin recursive algorithm is applied, decomposition information of template Chinese characters and Chinese characters to be made in a database is utilized to realize the reconstruction of patterns and characters, the font reconstruction quality is guaranteed, the cost is reduced and the efficiency is improved.
Description
Technical field
Present technique belongs to the design field of literal or figure, is specifically related to a kind of by editing composite figure or text, the method for realization font reconstruct.
Background technology
Chinese character is widely used in field of media such as commercial publication, art design, advertising, and these fields require to produce the font of multiple shape color lace shading, to produce good art and reading effect and uniqueness.For utilizing design software that various literal are carried out particular design processing, all be to operate generally by professional with fine arts basis, this has just brought extra design cost and manpower and time cost.
Relevant font design method in the prior art as the emulation software of undefined font, can only be imitated the font of specification comparatively, and the calligraphy font of original creation, individual write font, new artistic font, its reconstruct poor effect.
Summary of the invention
Technical matters to be solved by this invention provides a kind of saving cost, realizes the method to the effective reconstruct of sytlized font.
For achieving the above object, the present invention adopts following technical scheme: a kind of reconstructing method of Chinese character style, this method is by the Chinese character to be made that belongs to conventional font, the template Chinese character that belongs to same sytlized font and pattern thereof being carried out the mode of data, Flame Image Process, realize the method for sytlized font reconstruct, it is characterized in that described reconstructing method comprises the steps:
(1) passes through man-machine interactive operation, remain to be made Chinese character and template Chinese character are decomposed by parts, and all parts of the single Chinese character of correspondence and the relevant decomposed information mode with data is entered in the database, it is the Hanzi features database, wherein relevant decomposed information comprises each position component characteristic information, and the numeric indicia or the parts character that are used to characterize different parts.By man-machine interactive operation, remain to be made Chinese character and template Chinese character are decomposed by parts, handle compared with simple software identification, can guarantee the accuracy that parts decompose more effectively, for subsequent treatment work provides reliable analyzing and processing material.
(2) according to the position feature information of template Chinese character corresponding component, through manually confirming, the template Hanzi component pattern that each parts is answered is sampled and is extracted and preserve.Integrating step (1), those skilled in the art are not difficult to find out, the present invention is by the position feature information of template Chinese character corresponding component, make the parts pattern corresponding one by one with parts in the database, and this position feature information is to pass through man-machine interactive operation, obtain through artificial affirmation, corresponding relation accurately and reliably.In the actual treatment, the existing template Chinese character that belongs to same sytlized font, promptly its quantity of Chinese character of having write or made with same sytlized font is few more than waiting to make Chinese character, so therefore manually-operated labour intensity will reduce greatly, manipulation accuracy also will be guaranteed; Before carry out this step, must carry out sampling processing to the template Chinese character pattern that is illustrated on picture or the photograph earlier, make it to become and can be the picture information of machine recognition
(3) by the corresponding software program according to the data in the Hanzi features database, with all template Chinese characters with determine singlely wait to make Chinese character or with remain to be made Chinese character and the single template Chinese character of determining, carry out the match search between parts, and the pairing template Hanzi component of the Knock-Down Component of matching block and matching block pattern saved as wait to make the Hanzi component pattern, and according to matching block with respect to the position feature information of waiting to make Chinese character, in single blank pattern, finish the corresponding single size of waiting to make each parts pattern of Chinese character, the adjustment of position, finish the single preservation of waiting to make all parts patterns of Chinese character and adjustment, promptly form integral body and parts pattern that this waits to make Chinese character, realization waits to make the font reconstruct of Chinese character to this, and in the Hanzi features database, this Chinese character to be made redefined and be the template Chinese character, wherein Knock-Down Component is the parts that decompose gained according to the decomposition time parts that ordered pair is asked of step (1).
(4) by changing single template or the Chinese character of determining in the step (3) to be made, repeating step (3) only has the template Chinese character in the Hanzi features database, promptly finishes all typings are waited to make the font reconstruct of Chinese character about a certain sytlized font.
The working method that the present invention uses software to match with man-machine interactive operation by oneself, the application cycle recursive algorithm, by utilization to data message in the database, formation waits to make the pattern of Chinese character, realize the reconstruct of font, when guaranteeing the font reconstruction quality, provide cost savings, improved efficient.Chinese character with existing a small amount of sytlized font is a template, can re-construct out the Chinese character of a large amount of similar font effects through the art of this patent, promptly generate the character library of sytlized font,, can satisfy the specific demand in medium, office field as the artistic body character library of using among the WORD.
Further, described parts comprise radicals by which characters are arranged in traditional Chinese dictionaries, stroke, stroke unit, described each step all is that priority order by radicals by which characters are arranged in traditional Chinese dictionaries, stroke, stroke unit carries out to the processing of parts, wherein radicals by which characters are arranged in traditional Chinese dictionaries are the high priority components that have a priority at least, stroke unit is not subdivisible lowest priority parts, the priority of stroke is between radicals by which characters are arranged in traditional Chinese dictionaries and stroke unit, and the parts with lower priority are the further decomposition to the upper level parts.Hierarchical processing mode can effectively improve match search efficient, because bigger parts priority height, so preferentially choose bigger parts as the composition of waiting to make Chinese character, the font after the reconstruct is compared with the mode of all adjusting with stroke unit, and the reconstruct effect will be got well; Stroke is the parts that have a priority at least, and promptly stroke can be according in the practical application, and each neighborhood is to the different requirements of Chinese character details, the progression of corresponding adjustment stroke, but this progression should be less than the stroke unit number that stroke had.As " one ", it has only a priority to the better simply Chinese character of stroke, then its only parts " horizontal stroke " can be defined as radicals by which characters are arranged in traditional Chinese dictionaries.For the Chinese character of complexity, the priority orders of its decomposition is radicals by which characters are arranged in traditional Chinese dictionaries, stroke, stroke unit, and wherein radicals by which characters are arranged in traditional Chinese dictionaries are not defined as traditional Chinese character radicals, but has the high priority component that a plurality of priority are decomposed order.As a kind of concrete scheme, " rut " can tell radicals by which characters are arranged in traditional Chinese dictionaries " car ", " educating ", " The-Fan ", " educate " and can tell radicals by which characters are arranged in traditional Chinese dictionaries " moon " again, decomposition along with Chinese character, parts, its priority reduces gradually, and the Knock-Down Component of the stroke radicals by which characters are arranged in traditional Chinese dictionaries that to be priority minimum, stroke unit is the Knock-Down Component of the minimum stroke of priority, no longer decomposes after the stroke unit.As from the foregoing, though the present invention does not do concrete qualification to the parts classification, but use hierarchical processing mode, all can effectively improve match search efficient, generally speaking, the technical scheme of this supplementary features institute combination has multiple implementation among the present invention, and its general effect reaches unanimity, and all can solve the pointed technical matters of the present invention.
Further, described relevant decomposed information also comprises the classification number of Chinese character, the priority sequence number of the classification number of parts and each parts thereof, wherein Chinese characters kind alias and component categories number are divided into template and wait to make two kinds of fixing default marker codes, described step (3) is by changing the classification number of Chinese character, realization is treated when making the redefining of Chinese character, and treats each parts of making Chinese character in an identical manner and redefines; The priority sequence number of each parts adopts the mode of descending or ascending order to characterize the height of each parts priority, and its medium priority is determined to the concrete decomposition order of each parts of Chinese character according to described step (1), and decomposes order parts the preceding, its priority height.In database, use the mark of a series of data labels as respective attributes, be convenient to the digit recognition of program, help to improve treatment effeciency of the present invention.
Further, as two kinds of feasible circulation recursive algorithms of the present invention, in the Hanzi features data, all parts of a certain template Chinese character are compared with the single a certain parts of determining of making Chinese character of waiting, this template Chinese character has parts and the parts match of waiting to make Chinese character, the template Hanzi component pattern of this matching block correspondence is saved as the parts pattern that this waits to make Chinese character, and continue to this template Chinese character with wait that the miscellaneous part of making Chinese character compares, after above-mentioned processing, this template Chinese character with do not wait to make Chinese character not or no longer include same parts, and do not finish this and wait to make Chinese character all parts patterns storages, the Chinese character to be made that uses another template Chinese character and determine carries out the contrast between parts, wherein contrast is with radicals by which characters are arranged in traditional Chinese dictionaries, stroke, the priority order of stroke unit contrasts all parts of template Chinese character with waiting a certain parts of making Chinese character successively one by one; Perhaps in the Hanzi features data, the a certain parts of a certain single template Chinese character of waiting to make all parts of Chinese character and determining are compared, this Chinese character to be made has parts and the parts match of waiting to make Chinese character, the template Hanzi component pattern of this matching block correspondence is saved as the parts pattern that this waits to make Chinese character, and continue this is waited that the miscellaneous part of making Chinese character and template Chinese character compares, after above-mentioned processing, this does not wait to make Chinese character and template Chinese character not or no longer include same parts, use another to wait to make Chinese character and the template Chinese character determined carries out contrast between parts, wherein contrast is with radicals by which characters are arranged in traditional Chinese dictionaries, stroke, the priority order of stroke unit contrasts with a certain parts of template Chinese character successively one by one with waiting to make all parts of Chinese character.
When remaining to be made Chinese character style reconstruct finishing, the operation times of above-mentioned two kinds of algorithms reaches unanimity.All belong to feasible scheme of the present invention, and finish, efficient high and not waste of manpower and time cost by software program.Above-mentioned two kinds of algorithms all adopt following design:
Assert has matching block, do not treat the Knock-Down Component of making the Chinese character corresponding component and proceed contrast, and matching block is not arranged, and treats the Knock-Down Component of making the Chinese character corresponding component and proceeds contrast; Wherein the identification of matching block realizes by following method, both contrast the numeric indicia of parts or character marking unanimity, assert that this is the participation in the election matching block to the contrast parts, participation in the election matching block corresponding position feature information is also consistent, assert that this is a matching block to the contrast parts, otherwise assert that the participation in the election matching block is a matching block.
Because identification has matching block, do not treat the Knock-Down Component of making the Chinese character corresponding component and proceed contrast, promptly be that priority height, parts are decomposed the combiner that less bigger in other words parts are treated preferential conduct to make Chinese character, this design makes font after the reconstruct compared with the mode of all adjusting with stroke unit, and effect will be got well; By judging that whether consistent both contrast the numeric indicia of parts or character marking, the position feature information consistance that replaces on the view that naked eyes, image recognition come decision means, make full use of database technology, effectively raise the efficiency;
Further, described stroke is conventional stroke writing, stroke unit only comprise point, horizontal, vertical, carry, press down, left-falling stroke, hook.Categorised demarcation line between this design clear and definite radicals by which characters are arranged in traditional Chinese dictionaries, stroke, stroke unit, and be defined into the least member stroke unit of parts as above several, all do not have in other priority under the prerequisite of matching block, can guarantee to wait to make the pattern that all of Chinese character must parts can both be preserved.
Further, the position component characteristic information of corresponding single Chinese character is the decomposition order according to Chinese character in the step (1) in described step (1), (2), the permutation and combination of the parts of asking and combiner relative position information thereof, wherein combiner is all parts of being made up of asking parts in the corresponding Chinese character, relative position information is in single decomposition order, the position relation of the parts of asking or the relative miscellaneous part of its combiner, wherein the position relation comprise upper and lower, left and right, in, interior, semi-surrounding, three surrounds, surround, intersect entirely.Design determined position feature information with this, make the corresponding relation of the parts in parts pattern and the database more accurate, avoid owing to the font structural similarity, program is preserved error pattern, thus the unnecessary adjustment that brings.
Further, the template Chinese character pattern in the described step (2) is stored with the form of bitmap, and according to each position component characteristic information, utilizes pattern edge recognition technology, realizes extraction to each parts pattern by the edge that extracts each parts pattern.As a kind of attainable prioritization scheme, this simplicity of design is easily gone, and can change the preservation form of pattern according to actual needs.
Further, by described corresponding software program finish to this adjustment and formed pattern of waiting to make Chinese character thereof of waiting to make Chinese character, do not meet sytlized font, by manually-operated mode it is further revised.According to specific requirement, can be reconstructed at a spot of Chinese character to be made earlier, by manually-operated mode it is further revised, increased the quantity of template Chinese character and pattern thereof after, be applied to again in the reconstructed operation of a large amount of Chinese characters.Can realize better reconstruct effect like this, compare, also can reduce the workload of last manual amendment with disposable reconstruct in enormous quantities.
Description of drawings
Below in conjunction with the drawings and specific embodiments the utility model is described further:
Fig. 1 is for realizing a kind of process flow diagram of the present invention
Embodiment
As shown in Figure 1, the present invention is based on the Chinese character reconstructing method that stroke decomposes and position feature extracts.This method comprises the steps:
(1) passes through man-machine interactive operation, remain to be made Chinese character and template Chinese character are decomposed by parts, and all parts of the single Chinese character of correspondence and the relevant decomposed information mode with data is entered in the database, it is the Hanzi features database, wherein relevant decomposed information comprises each position component characteristic information, and the character marking that is used to characterize different parts;
(2), through manually confirming, each parts of all template Chinese character pattern correspondences are carried out pattern extract and preserve according to the position feature information of template Chinese character corresponding component;
(3) by the corresponding software program according to the data in the Hanzi features database, different templates Chinese character and the Chinese character single to be made determined are carried out laddering match search between parts, and the template Hanzi component pattern of gained matching block correspondence saved as the parts pattern that this waits to make Chinese character, this waits to make the pattern preservation of all parts of Chinese character until finishing structure, wait to make the architectural feature of Chinese character then according to this, finish to this wait to make Chinese character all must the parts pattern size and the adjustment of position, form the pattern that this waits to make Chinese character, promptly realize the font reconstruct of this being waited to make Chinese character, and in the Hanzi features database, this Chinese character to be made redefined and be the template Chinese character;
(4) wait to make Chinese character repeating step (3) at difference, in the Hanzi features database, only have the template Chinese character, promptly finish remain the to be made font reconstruct of Chinese character about a certain sytlized font.
Wherein pass through the decomposition of the first step,, form the Hanzi features storehouse, and define its positional information of the form storage of all decomposed information with database.
Row " id ": the sequence number of all Chinese characters in the Chinese Character Set;
Row " zi ": Chinese character;
Row " zs ": the sequence number that belongs to the stroke unit of certain single Chinese character;
Row " zt ": the mark of Chinese character, zt=1 represent that this Chinese character is a Chinese character to be constructed, and zt=2 represents that this Chinese character is the template Chinese character;
Row " i " (i=0,1,2 ...): the radical, stroke, the stroke unit that constitute Chinese character;
Row " iw " (i=0,1,2 ...): the position feature of the radical of formation Chinese character, stroke, stroke unit;
Row " is " (i=0,1,2 ...): the stroke unit sum that constitutes Hanzi component (radical/stroke/stroke unit);
Row " it " (i=0,1,2 ...): constitute the mark of the radical/stroke/stroke unit of Chinese character, it=1 represents that this radical/stroke/stroke unit waits to construct, and it=2 represents that this radical/stroke/stroke unit is a template; With " version " be example, its database information is as follows
And " in " be divided into upper, middle and lower structure and left, center, right structure,
Represent the left, center, right structure,
Represent the upper, middle and lower structure, Chuo, factory, Yin, the semi-surrounding that the representative is dissimilar, Contraband, Qian, three encirclements that the Jiong representative is dissimilar,
Representative is complete surrounds,
Represent decussate texture.
Hanzi features storehouse wherein, match search is followed successively by 0 in proper order, 1,2 ... whether identical row promptly find out parts, has only when the front and all do not find, just with the parts of last stroke unit as the structure Chinese character, look for the row number big parts of (i) possibility in table, only in this way, the parts of finding out just mate most with waiting certain parts of constructing Chinese character as far as possible.
Above-mentioned Hanzi features storehouse uses SQL Server to create, and with the form of bitmap, as BMP, stores the various patterns that generate in the restructuring procedure.And according to actual needs,, all patterns can be transferred to character library or carry out artistic font processing at several words by the figure switching software.
Claims (10)
1. the reconstructing method of a Chinese character style, this method is by the Chinese character to be made that belongs to conventional font, the template Chinese character that belongs to same sytlized font and pattern thereof being carried out the mode of data decomposition analysis, Flame Image Process, realize the method for sytlized font reconstruct, it is characterized in that described reconstructing method comprises the steps:
(1) passes through man-machine interactive operation, remain to be made Chinese character and template Chinese character are decomposed by parts, and all parts of the single Chinese character of correspondence and the relevant decomposed information mode with data is entered in the database, it is the Hanzi features database, wherein relevant decomposed information comprises each position component characteristic information, and the numeric indicia or the parts character that are used to characterize different parts;
(2) according to the position feature information of template Chinese character corresponding component,, the template Hanzi component pattern of each parts correspondence is sampled extract and preserve through manually confirming;
(3) by the corresponding software program according to the data in the Hanzi features database, with all template Chinese characters with determine singlely wait to make Chinese character or with remain to be made Chinese character and the single template Chinese character of determining, carry out the match search between parts, and the pairing template Hanzi component of the Knock-Down Component of matching block and matching block pattern saved as wait to make the Hanzi component pattern, and according to matching block with respect to the position feature information of waiting to make Chinese character, in single blank pattern, finish the corresponding single size of waiting to make each parts pattern of Chinese character, the adjustment of position, finish the single preservation of waiting to make all parts patterns of Chinese character and adjustment, promptly form integral body and parts pattern that this waits to make Chinese character, realization waits to make the font reconstruct of Chinese character to this, and in the Hanzi features database, this Chinese character to be made redefined and be the template Chinese character, wherein Knock-Down Component is the parts that decompose gained according to the decomposition time parts that ordered pair is asked of step (1);
(4) by changing single template or the Chinese character of determining in the step (3) to be made, repeating step (3) only has the template Chinese character in the Hanzi features database, promptly finishes all typings are waited to make the font reconstruct of Chinese character about a certain sytlized font.
2. the reconstructing method of a kind of Chinese character style as claimed in claim 1 is characterized in that, described sytlized font comprise original creation calligraphy font, individual write font, new artistic font.
3. the reconstructing method of a kind of Chinese character style as claimed in claim 1, it is characterized in that, described parts comprise radicals by which characters are arranged in traditional Chinese dictionaries, stroke, stroke unit, described each step all is that priority order by radicals by which characters are arranged in traditional Chinese dictionaries, stroke, stroke unit carries out to the processing of parts, wherein radicals by which characters are arranged in traditional Chinese dictionaries are the high priority components that have a priority at least, stroke unit is not subdivisible lowest priority parts, the priority of stroke is between radicals by which characters are arranged in traditional Chinese dictionaries and stroke unit, and the parts with lower priority are the further decomposition to the upper level parts.
4. as the reconstructing method of claim 1 or 3 described a kind of Chinese character styles, it is characterized in that, described relevant decomposed information also comprises the classification number of Chinese Chinese character, the priority sequence number of the classification number of parts and each parts thereof, wherein Chinese characters kind alias and component categories number are divided into template and wait to make two kinds of fixing default marker codes, described step (3) is by changing the classification number of Chinese character, realization is treated when making the redefining of Chinese character, and treats each parts of making Chinese character in an identical manner and redefines; The priority sequence number of each parts adopts the mode of descending or ascending order to characterize the height of each parts priority, and its medium priority is determined to the concrete decomposition order of each parts of Chinese character according to described step (1), and decomposes order parts the preceding, its priority height.
5. as the reconstructing method of claim 1 or 3 described a kind of Chinese character styles, it is characterized in that, the process of in the described step (3) all template Chinese characters and the Chinese character single to be made determined being carried out the match search between parts is: in the Hanzi features data, all parts of a certain template Chinese character are compared with the single a certain parts of determining of making Chinese character of waiting, this template Chinese character has parts and the parts match of waiting to make Chinese character, the template Hanzi component pattern of this matching block correspondence is saved as the parts pattern that this waits to make Chinese character, and continue to this template Chinese character with wait that the miscellaneous part of making Chinese character compares, after above-mentioned processing, this template Chinese character with do not wait to make Chinese character not or no longer include same parts, and do not finish this and wait to make Chinese character all parts patterns storages, the Chinese character to be made that uses another template Chinese character and determine carries out the contrast between parts, wherein contrast is with radicals by which characters are arranged in traditional Chinese dictionaries, stroke, the priority order of stroke unit, all parts of template Chinese character are contrasted one by one with waiting a certain parts of making Chinese character successively, identification has matching block, do not treat the Knock-Down Component of making the Chinese character corresponding component and proceed contrast, matching block is not arranged, treat the Knock-Down Component of making the Chinese character corresponding component and proceed contrast; Wherein the identification of matching block realizes by following method, both contrast the numeric indicia of parts or character marking unanimity, assert that this is the participation in the election matching block to the contrast parts, participation in the election matching block corresponding position feature information is also consistent, assert that this is a matching block to the contrast parts, otherwise assert that the participation in the election matching block is a matching block.
6. as the reconstructing method of claim 1 or 3 described a kind of Chinese character styles, it is characterized in that, in the described step (3) with remain to be made Chinese character and process that the single template Chinese character determined carries out the match search between parts is: in the Hanzi features data, the a certain parts of a certain single template Chinese character of waiting to make all parts of Chinese character and determining are compared, this Chinese character to be made has parts and the parts match of waiting to make Chinese character, the template Hanzi component pattern of this matching block correspondence is saved as the parts pattern that this waits to make Chinese character, and continue this is waited that the miscellaneous part of making Chinese character and template Chinese character compares, after above-mentioned processing, this does not wait to make Chinese character and template Chinese character not or no longer include same parts, use another to wait to make Chinese character and the template Chinese character determined carries out contrast between parts, wherein contrast is with radicals by which characters are arranged in traditional Chinese dictionaries, stroke, the priority order of stroke unit, contrast one by one with a certain parts of template Chinese character successively waiting to make all parts of Chinese character, identification has matching block, wait to make the Knock-Down Component of Chinese character corresponding component and do not proceed contrast, matching block is not arranged, will wait that the Knock-Down Component of making the Chinese character corresponding component proceeds contrast; Wherein the identification of matching block realizes by following method, both contrast the numeric indicia of parts or character marking unanimity, assert that this is the participation in the election matching block to the contrast parts, participation in the election matching block corresponding position feature information is also consistent, assert that this is a matching block to the contrast parts, otherwise assert that the participation in the election matching block is a matching block.
7. as the reconstructing method of claim 1 or 3 described a kind of Chinese character styles, it is characterized in that described stroke is conventional stroke writing, stroke unit only comprise point, horizontal, vertical, carry, press down, left-falling stroke, hook.
8. the reconstructing method of a kind of Chinese character style as claimed in claim 1, it is characterized in that, the position component characteristic information of corresponding single Chinese character is the decomposition order according to Chinese character in the step (1) in described step (1), (2), the permutation and combination of relative position information of the parts of asking and combiner thereof, wherein combiner is all parts of being made up of asking parts in the corresponding single Chinese character, wherein position relation comprise upper and lower, left and right, in, interior, semi-surrounding, three surrounds, surround, intersect entirely.
9. the reconstructing method of a kind of Chinese character style as claimed in claim 1, it is characterized in that, template Chinese character pattern in the described step (2) is stored with the form of bitmap, and according to each position component characteristic information, utilize pattern edge recognition technology, by extracting each parts pattern relative position information in single decomposition order, the position relation of institute's parts of asking or the relative miscellaneous part of its combiner, the edge realization to the extraction of each parts pattern.
10. the reconstructing method of a kind of Chinese character style as claimed in claim 1, it is characterized in that, by described corresponding software program finish to this adjustment and formed pattern of waiting to make Chinese character thereof of waiting to make Chinese character, do not meet sytlized font, by manually-operated mode it is further revised.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910191209A CN101819683A (en) | 2009-10-26 | 2009-10-26 | Method for reconstructing Chinese character font |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200910191209A CN101819683A (en) | 2009-10-26 | 2009-10-26 | Method for reconstructing Chinese character font |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101819683A true CN101819683A (en) | 2010-09-01 |
Family
ID=42654770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200910191209A Pending CN101819683A (en) | 2009-10-26 | 2009-10-26 | Method for reconstructing Chinese character font |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101819683A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104424195A (en) * | 2013-08-20 | 2015-03-18 | 北大方正集团有限公司 | Method and device for constructing widget library |
| CN106371777A (en) * | 2016-08-25 | 2017-02-01 | 广州御银科技股份有限公司 | Form printing system |
| CN106445888A (en) * | 2016-09-30 | 2017-02-22 | 广州视睿电子科技有限公司 | Wordart manufacturing method and device |
| CN106503706A (en) * | 2016-09-23 | 2017-03-15 | 北京大学 | The method of discrimination of Chinese character pattern cutting result correctness |
| CN110135530A (en) * | 2019-05-16 | 2019-08-16 | 京东方科技集团股份有限公司 | Convert method and system, computer equipment and the medium of Chinese character style in image |
-
2009
- 2009-10-26 CN CN200910191209A patent/CN101819683A/en active Pending
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104424195A (en) * | 2013-08-20 | 2015-03-18 | 北大方正集团有限公司 | Method and device for constructing widget library |
| CN104424195B (en) * | 2013-08-20 | 2018-03-23 | 北大方正集团有限公司 | A kind of method and device for building part library |
| CN106371777A (en) * | 2016-08-25 | 2017-02-01 | 广州御银科技股份有限公司 | Form printing system |
| CN106503706A (en) * | 2016-09-23 | 2017-03-15 | 北京大学 | The method of discrimination of Chinese character pattern cutting result correctness |
| CN106503706B (en) * | 2016-09-23 | 2019-06-07 | 北京大学 | The method of discrimination of Chinese character pattern cutting result correctness |
| CN106445888A (en) * | 2016-09-30 | 2017-02-22 | 广州视睿电子科技有限公司 | Wordart manufacturing method and device |
| CN106445888B (en) * | 2016-09-30 | 2019-06-14 | 广州视睿电子科技有限公司 | The production method and device of characters in a fancy style |
| CN110135530A (en) * | 2019-05-16 | 2019-08-16 | 京东方科技集团股份有限公司 | Convert method and system, computer equipment and the medium of Chinese character style in image |
| US11587343B2 (en) | 2019-05-16 | 2023-02-21 | Boe Technology Group Co., Ltd. | Method and system for converting font of Chinese character in image, computer device and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109871851B (en) | Chinese character writing normalization judging method based on convolutional neural network algorithm | |
| CN106384094A (en) | Chinese word stock automatic generation method based on writing style modeling | |
| CN101377854B (en) | Method for simulating Chinese characters hand-written handwriting by a computer | |
| CN110570481A (en) | calligraphy word stock automatic repairing method and system based on style migration | |
| CN101819683A (en) | Method for reconstructing Chinese character font | |
| CN103186511A (en) | Method and equipment for word formation of Chinese characters, and method for constructing font object library | |
| CN101599180B (en) | Automatic generation method of imitative computer calligraphy based on handwriting style | |
| CN102096934A (en) | Human face cartoon generating method based on machine learning | |
| Garz et al. | Creating ground truth for historical manuscripts with document graphs and scribbling interaction | |
| CN106598920A (en) | Similar Chinese character classification method combining stroke codes with Chinese character dot matrixes | |
| CN101493887A (en) | Eyebrow image segmentation method based on semi-supervision learning and Hash index | |
| CN106056055B (en) | Brahma-sutra Tibetan hand script Chinese input equipment sample generating method based on component combination | |
| CN112784531A (en) | Chinese font and word stock generation method based on deep learning and part splicing | |
| CN104063359B (en) | Implementation method for personalized Chinese character word library | |
| CN103914503A (en) | System and method for generating personalized handwriting font | |
| Inunganbi et al. | Recognition of handwritten Meitei Mayek script based on texture feature | |
| CN110232337A (en) | Chinese character image stroke extraction based on full convolutional neural networks, system | |
| CN110211032A (en) | Generation method, device and the readable storage medium storing program for executing of chinese character | |
| CN109670365B (en) | Handwriting identification system and method | |
| CN112148735B (en) | Construction method for structured form data knowledge graph | |
| CN109240549B (en) | Calligraphy corrector based on external digital equipment and big data intelligent analysis | |
| CN109299726A (en) | A kind of Chinese character pattern Similarity algorithm based on feature vector and stroke order coding | |
| CN114861595B (en) | Vector line transformation-based individual font generation method | |
| Zhang et al. | Visual knowledge guided intelligent generation of Chinese seal carving | |
| CN114821308A (en) | Furniture style identification and generation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20100901 |