CN101377854A - Method for simulating Chinese characters hand-written handwriting by a computer - Google Patents
Method for simulating Chinese characters hand-written handwriting by a computer Download PDFInfo
- Publication number
- CN101377854A CN101377854A CNA2008101214905A CN200810121490A CN101377854A CN 101377854 A CN101377854 A CN 101377854A CN A2008101214905 A CNA2008101214905 A CN A2008101214905A CN 200810121490 A CN200810121490 A CN 200810121490A CN 101377854 A CN101377854 A CN 101377854A
- Authority
- CN
- China
- Prior art keywords
- stroke
- chinese character
- font
- characters
- 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.)
- Granted
Links
Images
Abstract
The invention provides a method for imitating handwriting of Chinese characters by using a computer. A computer image processing and artificial intelligent method can be adopted for learning and imitating personal handwriting with a computer. In the method, the available personal Chinese character samples in handwritten form are resolved in strokes and classified; each stroke, each radical, a character and the inner space structure of the character are parameterized in a unified way, and a personal handwritten character font database is established in combination with a plurality of ordinary types; when the personal handwriting is imitated, the Chinese character to be imitated is resolved into a radical or strokes, and each radical or stroke is found from the personal handwritten character font database one by one; the radical or the stroke is reconstituted according to the inner space structure features of the personal character as the output of the imitated handwriting. In the method, the stroke radical constitution rules of Chinese characters are analyzed directly; the characteristics of personal handwriting are seized more essentially, and personal handwriting is imitated better.
Description
Technical field
The present invention relates to computer art and aesthetics and artificial intelligence field, relate in particular to a kind of method of computing machine imitation Chinese character hand-written person's handwriting.
Background technology
The art thinking that has had a large amount of work to come simulating human, and further set up the computer intelligence system to solve the problem in the real world.Aspect Chinese words, Proceedings of the InternationalConference on Computer Processing of Oriental Languages (ICCPOL) proceeding of nineteen ninety-five (article title " Chinese glyph generation using character composition and beautyevaluation metrics ") has been announced a problem of using didactic method to attempt qualitative assessment Chinese font aesthetic feeling: they have defined four rules in writing of Chinese character, and have been implemented in their the rule-based aesthstic grading module; This module is calculated corresponding mark one by one to four rules simply, and obtains their weighted sum.IEEE Intelligent Systems magazine in 2005 (article title " Automaticgeneration of artistic Chinese calligraphy " is hereinafter to be referred as document IS2005) has been published the automatic creation system of a Chinese art calligraphy.But their work mainly focuses on use and generates formative Chinese font based on the reasoning that retrains, and how not to have aesthetic feeling and almost be concerned about these generations result.
Generate the result in order to obtain better computing machine Chinese font, also aesthetics is done quantitative Analysis, thereby we have realized the scoring of Chinese character aesthetics by learning basic numerical relation training set behind in order to attempt.Manyly used the people of expert system to know at work, senior Expert Rules can operate as normal; And this might not be the knowledge blind spot owing to expert system itself sometimes, and perhaps problem can't be summed up at all.Therefore we think that we can provide a kind of brain than the human expert to evaluate and test better machine evaluating ability based on the data-driven method of learning art.
Aspect drawing, the work that has some to study automatic painting creation equally in the field of Computer Graphics, but this mostly is to finish on the basis of a given photos.Other also the someone explored the animation of creating the drawing style in conjunction with artificial intelligence and human-computer interaction technology, the method for decomposing with stroke as the article " Animating Chinese paintings through stroke-based decomposition " of ACM journal ACM Trans.Graph publication in 2006 realizes dynamic drawing.Outside the visual art field, Computer Music is the successful direction that creation is carried out or assisted to the Another application artificial intelligence technology.In international artificial intelligence associating conference (IJCAI2007) in 2007, have one independently the special topic make music artificial intelligence (MUSIC-AI2007) discuss this topic specially.It should be noted that the research for Computer Music comprises automatic music creation and music evaluation, this is more similar to our thinking on Chinese font.Also have other number of research projects in addition: as the story creation, credible law enforcement official, interactive story, or the like, all be intended to catch aesthstic calculability.
Summary of the invention
The objective of the invention is to overcome the deficiencies in the prior art, a kind of method of computing machine imitation Chinese character hand-written person's handwriting is provided.
The method of computing machine imitation Chinese character hand-written person's handwriting may further comprise the steps:
1) in advance existing personal handwritten body Hanzi specimen being carried out stroke decomposes and classification, each stroke, radicals by which characters are arranged in traditional Chinese dictionaries, whole word and font interior spatial structure that each user was write have all carried out unified parametrization, and, set up the personal handwritten font database together with several fonts commonly used;
2) treat the imitation Chinese character, on its corresponding regular script word, do stroke and decompose and parametrization;
3) each radicals by which characters are arranged in traditional Chinese dictionaries or the stroke of waiting to imitate Chinese character according to personal handwritten font database structure one by one;
4) imitate the interior spatial structure of waiting to imitate Chinese character according to the personal handwritten font database, each radicals by which characters are arranged in traditional Chinese dictionaries or stroke that imitation is obtained are spliced into complete Chinese character, as imitation writing result; If a plurality of alternativess are arranged, then choose one as imitation writing result.
Describedly in advance existing personal handwritten body Hanzi specimen is carried out stroke and decompose and classification, each stroke, radicals by which characters are arranged in traditional Chinese dictionaries, whole word and font interior spatial structure that each user was write have all carried out unified parametrization, and, set up personal handwritten font database step together with several fonts commonly used:
(1) to each existing personal handwritten body Chinese character image, it is done refinement, stroke is decomposed, and extracts its track and writes width characteristics, represents each Chinese character with the form of parameter vector;
(2) according to the parameter vector of step (1) gained, become the tree structure of hierarchy type to represent by whole word, radicals by which characters are arranged in traditional Chinese dictionaries, stroke organization each Chinese character; Each node in the tree structure has all been represented individual character or radicals by which characters are arranged in traditional Chinese dictionaries or the stroke in the individual written handwriting, and each subdivision of each individual character or radicals by which characters are arranged in traditional Chinese dictionaries all is the child node of its corresponding node;
(3) in step (2) gained tree structure,, calculate the parameterization matrix of its interior spatial structure to the individual character or the radicals by which characters are arranged in traditional Chinese dictionaries of each node.
Described each existing personal handwritten body Chinese character image is done refinement to it, stroke is decomposed, and extracts its track and writes width characteristics, represents each Chinese character step with the form of parameter vector:
A) Chinese character image is done refinement and handle, to obtain the skeleton image of this word;
B) this word and its standard regular script font are done the stroke coupling, found out the one-to-one relationship of skeleton each several part and standard stroke, finish the stroke decomposition on the skeleton with the method for heuristic search;
C) to each the skeleton point on every stroke, it is oval to be with it that center of circle is drawn, and makes this ellipse big as far as possible and don't comprise blank parts on any former font image, and all elliptic region summations of this stroke are the image outline that stroke is decomposed gained;
D) all are oval major and minor axis, central coordinate of circle are classified a matrix as, are the parameter vector of this font.
Described in step (2) gained tree structure, to the individual character or the radicals by which characters are arranged in traditional Chinese dictionaries of each node, calculate the parameterization matrix step of its interior spatial structure:
E) to each subdivisions of each individual character or radicals by which characters are arranged in traditional Chinese dictionaries: radicals by which characters are arranged in traditional Chinese dictionaries or stroke are made its scope rectangle, promptly comprise the area minimum rectangle that this character segment and frame are parallel to x axle and y axle on two dimensional surface;
F) their laps on level, vertical direction are promptly calculated to per two scope rectangles in the mutual locus between the scope rectangle of per two subdivisions of calculating, establish two amounts that obtain and are respectively Bh, Bv; If this individual character or radicals by which characters are arranged in traditional Chinese dictionaries have n subdivision, then obtain the matrix of a n * n, wherein each matrix element be one two tuple (Bh, Bv), i.e. the parameterization matrix of the interior spatial structure of this individual character or radicals by which characters are arranged in traditional Chinese dictionaries.
The described imitation Chinese character for the treatment of, on its corresponding regular script word, do stroke and decompose and the parametrization step:
(4) to this Chinese character to be imitated, as described in claim 3, it is done refinement, stroke is decomposed, and extracts its track and writes width characteristics, represents each Chinese character with the form of parameter vector;
(5), as described in claim 4, calculate the parameterization matrix of its interior spatial structure to this Chinese character to be imitated.
Described each radicals by which characters are arranged in traditional Chinese dictionaries or stroke step of waiting to imitate Chinese character according to personal handwritten font database structure one by one:
(6) enumerate the subdivision splitting scheme of all possible radicals by which characters are arranged in traditional Chinese dictionaries level of this Chinese character and stroke level;
(7),, in the personal handwritten font database, search this subdivision and whether in the existing person's handwriting of this individual, occur each subdivision in the scheme to each the subdivision splitting scheme in the step (6); If have, the person's handwriting of then selecting all these subdivisions, is then supplied with this subdivision of font commonly used if having 5～10 of person's handwriting less thaies at random as the candidate;
(8) be each candidate of each subdivision in the step (7), calculate the imitative fiduciary level of writing of its subdivision; If this candidate's person's handwriting derives from this individual, then imitative to write fiduciary level be 1 to this candidate's subdivision, otherwise be 0;
(9) be each subdivision splitting scheme in the step (6), calculate its imitative fiduciary level of writing; If by this scheme, treat that imitative writing of Chinese characters is made of n subdivision, then imitative fiduciary level X=x1A1+x2A2+...+xnAn, the wherein x1 of writing of this scheme, x2, ..., xn is respectively the imitative fiduciary level, A1 write of subdivision of each subdivision under this scheme, A2, ..., An is in the standard regular script word for the treatment of imitative writing of Chinese characters, and each subdivision scope rectangle area occupied is in the ratio of whole word scope rectangle area occupied;
(10) select the imitative one group of the highest imitative result that writes of fiduciary level that writes for each subdivision splitting scheme.
Describedly wait to imitate the interior spatial structure of Chinese character according to personal handwritten font database imitation, each radicals by which characters are arranged in traditional Chinese dictionaries or the stroke that in view of the above imitation are obtained are spliced into complete Chinese character, as imitation writing result; If a plurality of alternativess are arranged, then choose one as imitation writing result step:
(11) in advance in standard regular script font, according to textural classification, classification comprises with all Chinese characters: independent body structure, left and right sides structure, up-down structure, external and internal compositions, left, center, right structure, upper, middle and lower structure;
(12) treat the imitation Chinese character, in the word that this individual had write, search this Chinese character and whether write by it; Then the interior spatial structure parameter matrix of this Chinese character handwriting that all these people were write is as the candidate;
(13) if this Chinese character was not write by this people, then in the word that this individual had write, find out all and belong to the Chinese character of same textural classification with Chinese character to be imitated;
(14) Chinese character that step (13) has been found out calculates the corresponding font similarity on each font commonly used with it of each Chinese character; Font similarity between two fonts is defined as: when the scaling font made the scope rectangular area of two fonts the same, the coincidence area of the writing part of two fonts accounted for the ratio of scope rectangular area; To each font commonly used, get ask the font similarity to some extent mean value as should font commonly used with treat the imitative overall similarity of writing people's writing;
(15) get the font commonly used of overall similarity maximum,, will become whole word, write output as this word imitative as the imitative result combinations of writing of described each radicals by which characters are arranged in traditional Chinese dictionaries of step (10) or stroke according to waiting to imitate the inner structure parameter matrix of Chinese character in this font commonly used.
The beneficial effect that the present invention compared with prior art has:
(1) realized that supermatic person's handwriting is imitative and write, significantly reduced wherein originally loaded down with trivial details manually-operated;
(2) close from the stroke shape of Chinese character and space structure and fasten direct analysis and preservation, Ben Zhi the potential feature of having caught individual person's handwriting more makes and imitates that to write the result more reasonable;
(3) select radicals by which characters are arranged in traditional Chinese dictionaries rationally rational more, make to imitate and write writing more near my person's handwriting with the strategy of stroke.
Description of drawings
Fig. 1 is the embodiment process flow diagram of system of the present invention;
Fig. 2 (a) is the Hanzi specimen font;
Fig. 2 (b) is the refinement result of font among Fig. 2 (a);
Fig. 2 (c) is " geometric graph " of font among Fig. 2 (a);
Fig. 3 is that stroke of the present invention is decomposed and the parameterized flow example figure of Chinese character;
Fig. 3 (a) is the Hanzi specimen font;
Fig. 3 (b) is " geometric graph " of Fig. 3 (a);
Fig. 3 (c) is the corresponding standard letter of Fig. 3 (a), i.e. round hand;
Fig. 3 (d) is the stroke decomposition result of Fig. 3 (a) on skeleton;
Fig. 3 (d) is the final stroke decomposition result of Fig. 3 (a);
Fig. 4 is that the User Interface that utilizes of the present invention assists stroke to decompose and the parameterized flow example figure of Chinese character;
Fig. 4 (a) is the Hanzi specimen font;
Fig. 4 (b) is " geometric graph " of Fig. 4 (a);
Fig. 4 (c) is the standard letter of Fig. 4 (a), i.e. round hand;
Fig. 4 (d) is the automatic decomposition result of Fig. 4 (a), and colored stroke is illustrated in the stroke of automatic decomposition success;
Fig. 4 (e) is the residue stroke sketch that the user sketches the contours on font by interactive interface;
Fig. 4 (f) is the stroke matching result on the skeleton that obtains according to user's sketch;
Fig. 4 (g) is the stroke skeleton behind the result shown in synthesizing map 4 (d) and Fig. 4 (f);
Fig. 4 (h) is the final stroke decomposition result of Fig. 4 (a);
Fig. 5 is in the hand-written script database, two exemplary plot that Chinese character style is represented with tree;
Fig. 6 is some examples of Chinese character hand-written person's handwriting imitation result, and wherein the 1st, 3 row are respectively two different individuals' handwritings, and the 2nd, 4 row are respectively that system of the present invention imitates the imitative result of writing who obtains by other hand-written writings of this individual;
Fig. 7 is some examples of Chinese character hand-written person's handwriting imitation result, and wherein preceding 4 row are as the personal handwritten person's handwriting sample of setting up the personal handwritten font database, and back 4 row are that person's handwriting samples that utilization preceding 4 is gone are used the imitative result of writing that embodiment of the present invention system obtains.
Embodiment
The method of computing machine imitation Chinese character hand-written person's handwriting may further comprise the steps:
1) in advance existing personal handwritten body Hanzi specimen being carried out stroke decomposes and classification, each stroke, radicals by which characters are arranged in traditional Chinese dictionaries, whole word and font interior spatial structure that each user was write have all carried out unified parametrization, and, set up the personal handwritten font database together with several fonts commonly used;
2) treat the imitation Chinese character, on its corresponding regular script word, do stroke and decompose and parametrization;
3) each radicals by which characters are arranged in traditional Chinese dictionaries or the stroke of waiting to imitate Chinese character according to personal handwritten font database structure one by one;
4) imitate the interior spatial structure of waiting to imitate Chinese character according to the personal handwritten font database, each radicals by which characters are arranged in traditional Chinese dictionaries or stroke that imitation is obtained are spliced into complete Chinese character, as imitation writing result; If a plurality of alternativess are arranged, then choose one as imitation writing result.
Describedly in advance existing personal handwritten body Hanzi specimen is carried out stroke and decompose and classification, each stroke, radicals by which characters are arranged in traditional Chinese dictionaries, whole word and font interior spatial structure that each user was write have all carried out unified parametrization, and, set up personal handwritten font database step together with several fonts commonly used:
(1) to each existing personal handwritten body Chinese character image, it is done refinement, stroke is decomposed, and extracts its track and writes width characteristics, represents each Chinese character with the form of parameter vector;
(2) according to the parameter vector of step (1) gained, become the tree structure of hierarchy type to represent by whole word, radicals by which characters are arranged in traditional Chinese dictionaries, stroke organization each Chinese character; Each node in the tree structure has all been represented individual character or radicals by which characters are arranged in traditional Chinese dictionaries or the stroke in the individual written handwriting, and each subdivision of each individual character or radicals by which characters are arranged in traditional Chinese dictionaries all is the child node of its corresponding node;
(3) in step (2) gained tree structure,, calculate the parameterization matrix of its interior spatial structure to the individual character or the radicals by which characters are arranged in traditional Chinese dictionaries of each node.
Described each existing personal handwritten body Chinese character image is done refinement to it, stroke is decomposed, and extracts its track and writes width characteristics, represents each Chinese character step with the form of parameter vector:
A) Chinese character image is done refinement and handle, to obtain the skeleton image of this word;
B) this word and its standard regular script font are done the stroke coupling, found out the one-to-one relationship of skeleton each several part and standard stroke, finish the stroke decomposition on the skeleton with the method for heuristic search;
C) to each the skeleton point on every stroke, it is oval to be with it that center of circle is drawn, and makes this ellipse big as far as possible and don't comprise blank parts on any former font image, and all elliptic region summations of this stroke are the image outline that stroke is decomposed gained;
D) all are oval major and minor axis, central coordinate of circle are classified a matrix as, are the parameter vector of this font.
Described in step (2) gained tree structure, to the individual character or the radicals by which characters are arranged in traditional Chinese dictionaries of each node, calculate the parameterization matrix step of its interior spatial structure:
E) to each subdivisions of each individual character or radicals by which characters are arranged in traditional Chinese dictionaries: radicals by which characters are arranged in traditional Chinese dictionaries or stroke are made its scope rectangle, promptly comprise the area minimum rectangle that this character segment and frame are parallel to x axle and y axle on two dimensional surface;
F) their laps on level, vertical direction are promptly calculated to per two scope rectangles in the mutual locus between the scope rectangle of per two subdivisions of calculating, establish two amounts that obtain and are respectively Bh, Bv; If this individual character or radicals by which characters are arranged in traditional Chinese dictionaries have n subdivision, then obtain the matrix of a n * n, wherein each matrix element be one two tuple (Bh, Bv), i.e. the parameterization matrix of the interior spatial structure of this individual character or radicals by which characters are arranged in traditional Chinese dictionaries.
The described imitation Chinese character for the treatment of, on its corresponding regular script word, do stroke and decompose and the parametrization step:
(4) to this Chinese character to be imitated, as described in claim 3, it is done refinement, stroke is decomposed, and extracts its track and writes width characteristics, represents each Chinese character with the form of parameter vector;
(5), as described in claim 4, calculate the parameterization matrix of its interior spatial structure to this Chinese character to be imitated.
Described each radicals by which characters are arranged in traditional Chinese dictionaries or stroke step of waiting to imitate Chinese character according to personal handwritten font database structure one by one:
(6) enumerate the subdivision splitting scheme of all possible radicals by which characters are arranged in traditional Chinese dictionaries level of this Chinese character and stroke level;
(7),, in the personal handwritten font database, search this subdivision and whether in the existing person's handwriting of this individual, occur each subdivision in the scheme to each the subdivision splitting scheme in the step (6); If have, the person's handwriting of then selecting all these subdivisions, is then supplied with this subdivision of font commonly used if having 5～10 of person's handwriting less thaies at random as the candidate;
(8) be each candidate of each subdivision in the step (7), calculate the imitative fiduciary level of writing of its subdivision; If this candidate's person's handwriting derives from this individual, then imitative to write fiduciary level be 1 to this candidate's subdivision, otherwise be 0;
(9) be each subdivision splitting scheme in the step (6), calculate its imitative fiduciary level of writing; If by this scheme, treat that imitative writing of Chinese characters is made of n subdivision, then imitative fiduciary level X=x1A1+x2A2+...+xnAn, the wherein x1 of writing of this scheme, x2, ..., xn is respectively the imitative fiduciary level, A1 write of subdivision of each subdivision under this scheme, A2, ..., An is in the standard regular script word for the treatment of imitative writing of Chinese characters, and each subdivision scope rectangle area occupied is in the ratio of whole word scope rectangle area occupied;
(10) select the imitative one group of the highest imitative result that writes of fiduciary level that writes for each subdivision splitting scheme.
Describedly wait to imitate the interior spatial structure of Chinese character according to personal handwritten font database imitation, each radicals by which characters are arranged in traditional Chinese dictionaries or the stroke that in view of the above imitation are obtained are spliced into complete Chinese character, as imitation writing result; If a plurality of alternativess are arranged, then choose one as imitation writing result step:
(11) in advance in standard regular script font, according to textural classification, classification comprises with all Chinese characters: independent body structure, left and right sides structure, up-down structure, external and internal compositions, left, center, right structure, upper, middle and lower structure;
(12) treat the imitation Chinese character, in the word that this individual had write, search this Chinese character and whether write by it; Then the interior spatial structure parameter matrix of this Chinese character handwriting that all these people were write is as the candidate;
(13) if this Chinese character was not write by this people, then in the word that this individual had write, find out all and belong to the Chinese character of same textural classification with Chinese character to be imitated;
(14) Chinese character that step (13) has been found out calculates the corresponding font similarity on each font commonly used with it of each Chinese character; Font similarity between two fonts is defined as: when the scaling font made the scope rectangular area of two fonts the same, the coincidence area of the writing part of two fonts accounted for the ratio of scope rectangular area; To each font commonly used, get ask the font similarity to some extent mean value as should font commonly used with treat the imitative overall similarity of writing people's writing;
(15) get the font commonly used of overall similarity maximum,, will become whole word, write output as this word imitative as the imitative result combinations of writing of described each radicals by which characters are arranged in traditional Chinese dictionaries of step (10) or stroke according to waiting to imitate the inner structure parameter matrix of Chinese character in this font commonly used.
As shown in Figure 1, embodiment of the present invention system comprise individual written handwriting sample 10, stroke decompose with parametrization 20, hand-written script database set up 30, stroke and radicals by which characters are arranged in traditional Chinese dictionaries imitatively write 40, font space structure imitation 50, individual person's handwriting are imitated and write result 60.
Individual's written handwriting sample 10: this part comprises a plurality of font image that should individual's person's handwriting; In the present embodiment, all font image all have been separated into individual character one by one, then they are normalized into the two-value black white image (length and width are 300 pixels) of same size; Its example is shown in Fig. 2 A.
Stroke is decomposed and parametrization 20: in the present embodiment, this part may further comprise the steps:
(A) extract its architectural feature from font image, details are as follows for its step (referring to Fig. 2 A, Fig. 2 B, Fig. 2 C):
1) Chinese character image 101 is done refinement (Thinning) and handle, to obtain the skeleton image of this word; Present embodiment has been used the image thinning algorithm that the ACM journal was announced in 1994 (" A noniterativethinning algorithm " ACM Transactions on Mathematical Software, 20 (1): 5-20,1994); Its example is shown in Fig. 2 B;
2) from skeleton image, extract " unique point " (one piece of article " Identification of forkpoints on the skeletons of handwritten Chinesecharacters " IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) 21 (10): 1095-1100 that the definition of " unique point " was announced with reference to the IEEE journal in 1999,1999, hereinafter to be referred as document PAMI99), these unique points will be divided into some segment of curve to whole skeleton;
3) all use many end to end straight-line segments to be similar to every segment of curve, concrete steps are as follows: to the segment of curve AB that each bar is not replaced by straight-line segment, establishing A, B is respectively its two ends end points; Calculating is with certain 1 the included angle A CB that C is the summit on the segment of curve AB, and the angle value when angle ACB is maximum then is divided into AC with segment of curve AB, two sections of CB less than a predetermined value (as 135 degree); Otherwise connect AB 2 points with straight-line segment, replace original segment of curve AB; This step constantly carries out all being replaced by straight-line segment until all segment of curve;
4) figure that constitutes by a series of straight-line segments and end points thereof be called as this font " geometric graph " (geometricgraph); " geometric graph " done correction and beta pruning; Present embodiment has been used the skeleton diagram correction technique that uses among the document PAMI99; " geometric graph " example that finally obtains is shown in Fig. 2 C;
(B) calculating the stroke coupling an of the best described in the step (A) between Chinese character style and its standard letter, decompose thereby finish stroke, details are as follows for its step (referring to Fig. 3):
1), obtains " geometric graph " of this standard letter to the standard letter repeating step (A) of the described font of step (A); And the stroke decomposition result of tentative standard font is predicted;
2) between " geometric graph " of " geometric graph " of font described in the step (A) and its standard letter, calculate the stroke matching result an of the best; Present embodiment has been used one piece of article (" Model-based stroke extraction and matching for handwritten Chinesecharacter recognition " .Pattern Recognition that " pattern-recognition " magazine was announced in calendar year 2001,34 (12): 2339-2352,2001) method of heuristic search described in calculates one-to-one relationship between stroke on " geometric graph ";
3) " geometric graph " gone up each stroke track of representing with many straight-line segments, be converted into the stroke decomposition result on former character contour, its concrete grammar is: to the every bit on each straight-line segment on each stroke, with it is that ellipse is drawn in the center of circle, make this ellipse as far as possible big and don't comprise blank parts on any former font image (promptly on the black white image of former font, all pixels in this elliptic region are black), all elliptic region summations of this stroke are the image outline that stroke is decomposed gained;
(C) to differing bigger font with the standard letter form, to finishing the part stroke of coupling in the step (B), use an interactively user interface to assist stroke to decompose, details are as follows for its step (referring to Fig. 4):
1) user comes to describe its framework sketch for font by interactively user interface;
2) revise " geometric graph " that gets by standard letter according to user's sketch; Present embodiment substitutes part stroke counterpart by user's sketch in standard letter " geometric graph " of not finishing coupling in the step (2);
3) repeating step (B) recomputates the optimum matching scheme between stroke, decomposes thereby finish stroke; (D) to finishing the font that stroke is decomposed, with its parametrization, with the formal representation of vector; Present embodiment has adopted the Chinese character parametric method among one piece of document Automatic generation of artisticChinese calligraphy in the IEEE Intelligent System magazine in 2005, and each font matrix of usefulness all of equal value is represented in vector space.
The hand-written script database sets up 30: as shown in Figure 5, in the present embodiment to existing personal handwritten body Hanzi specimen, and together with several fonts commonly used, set up the personal handwritten font database; Become the tree structure of hierarchy type to represent by whole word, radicals by which characters are arranged in traditional Chinese dictionaries, stroke organization each Chinese character; Each node in the tree structure has all been represented individual character or radicals by which characters are arranged in traditional Chinese dictionaries or the stroke in the individual written handwriting, and each subdivision of each individual character or radicals by which characters are arranged in traditional Chinese dictionaries all is the child node of its corresponding node;
To the individual character or the radicals by which characters are arranged in traditional Chinese dictionaries of each node, calculate the parameterization matrix of its interior spatial structure:
1) to each subdivisions of each individual character or radicals by which characters are arranged in traditional Chinese dictionaries: radicals by which characters are arranged in traditional Chinese dictionaries or stroke are made its scope rectangle, promptly comprise the area minimum rectangle that this character segment and frame are parallel to x axle and y axle on two dimensional surface;
2) their laps on level, vertical direction are promptly calculated to per two scope rectangles in the mutual locus between the scope rectangle of per two subdivisions of calculating, establish two amounts that obtain and are respectively Bh, Bv; If this individual character or radicals by which characters are arranged in traditional Chinese dictionaries have n subdivision, then obtain the matrix of a n * n, wherein each matrix element be one two tuple (Bh, Bv), i.e. the parameterization matrix of the interior spatial structure of this individual character or radicals by which characters are arranged in traditional Chinese dictionaries.Stroke and radicals by which characters are arranged in traditional Chinese dictionaries are imitative writes 40: in the present embodiment, this part may further comprise the steps:
1) treats imitative writing of Chinese characters, its round hand is done stroke decompose and parametrization 20, and calculate the parameterization matrix of its interior spatial structure;
2) by its round hand, enumerate the subdivision splitting scheme of all possible radicals by which characters are arranged in traditional Chinese dictionaries level of this Chinese character and stroke level, as " OK " word among Fig. 5 (a), its possible subdivision splitting scheme comprises: P
0, P
1P
2, P
1P
5P
6, P
3P
4P
2, P
3P
4P
5P
6Totally five kinds;
3) to each subdivision splitting scheme, to each subdivision in the scheme, to set up at the hand-written script database and to obtain searching in the font database this subdivision in 20 and whether exist, the person's handwriting of selecting all these subdivisions is as the candidate;
4) be each candidate of each subdivision, calculate its imitative fiduciary level of writing; If this candidate is write person's handwriting by this individual, then this candidate's the imitative fiduciary level of writing is 1; If this candidate comes from font commonly used, then imitating and writing fiduciary level is 0;
5) be each subdivision splitting scheme, calculate its imitative fiduciary level of writing; If by this scheme, treat that imitative writing of Chinese characters is made of n subdivision, then imitative fiduciary level X=x1A1+x2A2+...+xnAn, the wherein x1 of writing of this scheme, x2, ..., xn is respectively the imitative fiduciary level, A1 write of subdivision of each subdivision under this scheme, A2, ..., An is in the standard regular script word for the treatment of imitative writing of Chinese characters, and each subdivision scope rectangle area occupied is in the ratio of whole word scope rectangle area occupied;
(10) select the imitative the highest prescription case of fiduciary level of writing for each subdivision splitting scheme, as stroke and imitative 40 the imitative result of writing that writes of radicals by which characters are arranged in traditional Chinese dictionaries.
Font space structure imitation 50: in the present embodiment, this part may further comprise the steps:
1) in advance in standard regular script font, according to textural classification, classification comprises with all Chinese characters: independent body structure, left and right sides structure, up-down structure, external and internal compositions, left, center, right structure, upper, middle and lower structure;
2) treat the imitation Chinese character, in the word that this individual had write, search this Chinese character and whether write by it; Then the interior spatial structure parameter matrix of this Chinese character handwriting that all these people were write is as the candidate;
3) if this Chinese character was not write by this people, then in the word that this individual had write, find out all and belong to the Chinese character of same textural classification with Chinese character to be imitated;
4) Chinese character to having found out calculates the corresponding font similarity on each font commonly used with it of each Chinese character; Font similarity between two fonts is defined as: when the scaling font made the scope rectangular area of two fonts the same, the coincidence area of the writing part of two fonts accounted for the ratio of scope rectangular area; To each font commonly used, get ask the font similarity to some extent mean value as should font commonly used with treat the imitative overall similarity of writing people's writing;
5) get the font commonly used of overall similarity maximum, according to waiting to imitate the inner structure parameter matrix of Chinese character in this font commonly used, write each radicals by which characters are arranged in traditional Chinese dictionaries of obtaining in 40 or the imitative result combinations of writing of stroke becomes to put in order word with stroke and radicals by which characters are arranged in traditional Chinese dictionaries are imitative, as the imitative result that writes of this word.
The imitative result 60 that writes of individual's person's handwriting: in the present embodiment, this part adopts the expression mode identical with individual written handwriting sample 10, and promptly the two-value black white image of same size is exported as the imitative result that writes; Its example such as Fig. 6, shown in Figure 7.
Claims (7)
1. the method for computing machine imitation Chinese character hand-written person's handwriting is characterized in that may further comprise the steps:
1) in advance existing personal handwritten body Hanzi specimen being carried out stroke decomposes and classification, each stroke, radicals by which characters are arranged in traditional Chinese dictionaries, whole word and font interior spatial structure that each user was write have all carried out unified parametrization, and, set up the personal handwritten font database together with several fonts commonly used;
2) treat the imitation Chinese character, on its corresponding regular script word, do stroke and decompose and parametrization;
3) each radicals by which characters are arranged in traditional Chinese dictionaries or the stroke of waiting to imitate Chinese character according to personal handwritten font database structure one by one;
4) imitate the interior spatial structure of waiting to imitate Chinese character according to the personal handwritten font database, each radicals by which characters are arranged in traditional Chinese dictionaries or stroke that imitation is obtained are spliced into complete Chinese character, as imitation writing result; If a plurality of alternativess are arranged, then choose one as imitation writing result.
2. the method for a kind of computing machine imitation Chinese character hand-written person's handwriting as claimed in claim 1, it is characterized in that describedly in advance existing personal handwritten body Hanzi specimen being carried out stroke and decomposing and classification, each stroke, radicals by which characters are arranged in traditional Chinese dictionaries, whole word and font interior spatial structure that each user was write have all carried out unified parametrization, and, set up personal handwritten font database step together with several fonts commonly used:
(1) to each existing personal handwritten body Chinese character image, it is done refinement, stroke is decomposed, and extracts its track and writes width characteristics, represents each Chinese character with the form of parameter vector;
(2) according to the parameter vector of step (1) gained, become the tree structure of hierarchy type to represent by whole word, radicals by which characters are arranged in traditional Chinese dictionaries, stroke organization each Chinese character; Each node in the tree structure has all been represented individual character or radicals by which characters are arranged in traditional Chinese dictionaries or the stroke in the individual written handwriting, and each subdivision of each individual character or radicals by which characters are arranged in traditional Chinese dictionaries all is the child node of its corresponding node;
(3) in step (2) gained tree structure,, calculate the parameterization matrix of its interior spatial structure to the individual character or the radicals by which characters are arranged in traditional Chinese dictionaries of each node.
3. the method for a kind of computing machine imitation Chinese character hand-written person's handwriting as claimed in claim 2, it is characterized in that described to each existing personal handwritten body Chinese character image, it is done refinement, stroke is decomposed, extract its track and write width characteristics, represent each Chinese character step with the form of parameter vector:
A) Chinese character image is done refinement and handle, to obtain the skeleton image of this word;
B) this word and its standard regular script font are done the stroke coupling, found out the one-to-one relationship of skeleton each several part and standard stroke, finish the stroke decomposition on the skeleton with the method for heuristic search;
C) to each the skeleton point on every stroke, it is oval to be with it that center of circle is drawn, and makes this ellipse big as far as possible and don't comprise blank parts on any former font image, and all elliptic region summations of this stroke are the image outline that stroke is decomposed gained;
D) all are oval major and minor axis, central coordinate of circle are classified a matrix as, are the parameter vector of this font.
4. the method for a kind of computing machine imitation Chinese character hand-written person's handwriting as claimed in claim 2 is characterized in that describedly in step (2) gained tree structure, to the individual character or the radicals by which characters are arranged in traditional Chinese dictionaries of each node, calculates the parameterization matrix step of its interior spatial structure:
E) to each subdivisions of each individual character or radicals by which characters are arranged in traditional Chinese dictionaries: radicals by which characters are arranged in traditional Chinese dictionaries or stroke are made its scope rectangle, promptly comprise the area minimum rectangle that this character segment and frame are parallel to x axle and y axle on two dimensional surface;
F) their laps on level, vertical direction are promptly calculated to per two scope rectangles in the mutual locus between the scope rectangle of per two subdivisions of calculating, establish two amounts that obtain and are respectively Bh, Bv; If this individual character or radicals by which characters are arranged in traditional Chinese dictionaries have n subdivision, then obtain the matrix of a n * n, wherein each matrix element be one two tuple (Bh, Bv), i.e. the parameterization matrix of the interior spatial structure of this individual character or radicals by which characters are arranged in traditional Chinese dictionaries.
5. the method for a kind of computing machine imitation Chinese character hand-written person's handwriting as claimed in claim 1 is characterized in that the described imitation Chinese character for the treatment of, and does stroke and decompose and the parametrization step on its corresponding regular script word:
(4) to this Chinese character to be imitated, as described in claim 3, it is done refinement, stroke is decomposed, and extracts its track and writes width characteristics, represents each Chinese character with the form of parameter vector;
(5), as described in claim 4, calculate the parameterization matrix of its interior spatial structure to this Chinese character to be imitated.
6. the method for a kind of computing machine imitation Chinese character hand-written person's handwriting as claimed in claim 1 is characterized in that described each radicals by which characters are arranged in traditional Chinese dictionaries or stroke step of waiting to imitate Chinese character according to personal handwritten font database structure one by one:
(6) enumerate the subdivision splitting scheme of all possible radicals by which characters are arranged in traditional Chinese dictionaries level of this Chinese character and stroke level;
(7),, in the personal handwritten font database, search this subdivision and whether in the existing person's handwriting of this individual, occur each subdivision in the scheme to each the subdivision splitting scheme in the step (6); If have, the person's handwriting of then selecting all these subdivisions, is then supplied with this subdivision of font commonly used if having 5～10 of person's handwriting less thaies at random as the candidate;
(8) be each candidate of each subdivision in the step (7), calculate the imitative fiduciary level of writing of its subdivision; If this candidate's person's handwriting derives from this individual, then imitative to write fiduciary level be 1 to this candidate's subdivision, otherwise be 0;
(9) be each subdivision splitting scheme in the step (6), calculate its imitative fiduciary level of writing; If by this scheme, treat that imitative writing of Chinese characters is made of n subdivision, then imitative fiduciary level X=x1A1+x2A2+...+xnAn, the wherein x1 of writing of this scheme, x2, ..., xn is respectively the imitative fiduciary level, A1 write of subdivision of each subdivision under this scheme, A2, ..., An is in the standard regular script word for the treatment of imitative writing of Chinese characters, and each subdivision scope rectangle area occupied is in the ratio of whole word scope rectangle area occupied;
(10) select the imitative one group of the highest imitative result that writes of fiduciary level that writes for each subdivision splitting scheme.
7. the method for a kind of computing machine imitation Chinese character hand-written person's handwriting as claimed in claim 1, it is characterized in that the described interior spatial structure of waiting to imitate Chinese character that imitates according to the personal handwritten font database, each radicals by which characters are arranged in traditional Chinese dictionaries or the stroke that in view of the above imitation are obtained are spliced into complete Chinese character, as imitation writing result; If a plurality of alternativess are arranged, then choose one as imitation writing result step:
(11) in advance in standard regular script font, according to textural classification, classification comprises with all Chinese characters: independent body structure, left and right sides structure, up-down structure, external and internal compositions, left, center, right structure, upper, middle and lower structure;
(12) treat the imitation Chinese character, in the word that this individual had write, search this Chinese character and whether write by it; Then the interior spatial structure parameter matrix of this Chinese character handwriting that all these people were write is as the candidate;
(13) if this Chinese character was not write by this people, then in the word that this individual had write, find out all and belong to the Chinese character of same textural classification with Chinese character to be imitated;
(14) Chinese character that step (13) has been found out calculates the corresponding font similarity on each font commonly used with it of each Chinese character; Font similarity between two fonts is defined as: when the scaling font made the scope rectangular area of two fonts the same, the coincidence area of the writing part of two fonts accounted for the ratio of scope rectangular area; To each font commonly used, get ask the font similarity to some extent mean value as should font commonly used with treat the imitative overall similarity of writing people's writing;
(15) get the font commonly used of overall similarity maximum, according to waiting to imitate the inner structure parameter matrix of Chinese character in this font commonly used, the imitative result combinations of writing of each radicals by which characters are arranged in traditional Chinese dictionaries as claimed in claim 6 or stroke is become whole word, write output as this word imitative.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008101214905A CN101377854B (en) | 2008-10-07 | 2008-10-07 | Method for simulating Chinese characters hand-written handwriting by a computer |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008101214905A CN101377854B (en) | 2008-10-07 | 2008-10-07 | Method for simulating Chinese characters hand-written handwriting by a computer |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101377854A true CN101377854A (en) | 2009-03-04 |
| CN101377854B CN101377854B (en) | 2012-01-04 |
Family
ID=40421382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2008101214905A Expired - Fee Related CN101377854B (en) | 2008-10-07 | 2008-10-07 | Method for simulating Chinese characters hand-written handwriting by a computer |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101377854B (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101599180B (en) * | 2009-03-05 | 2012-06-13 | 浙江大学 | Automatic generation method of imitative computer calligraphy based on handwriting style |
| CN102637078A (en) * | 2012-02-27 | 2012-08-15 | 厦门大学 | Method for generating structurally optimized Chinese character patterns |
| CN102646023A (en) * | 2012-04-11 | 2012-08-22 | 广东欧珀移动通信有限公司 | Method for generating original user handwriting fonts |
| CN103136769A (en) * | 2011-12-02 | 2013-06-05 | 北京三星通信技术研究有限公司 | Method and device of generation of writing style font of user |
| CN103885699A (en) * | 2012-12-20 | 2014-06-25 | 中山大学深圳研究院 | Automatic handwriting copying method based on mobile terminals |
| CN103914503A (en) * | 2012-12-28 | 2014-07-09 | 叶青湖 | System and method for generating personalized handwriting font |
| CN104281859A (en) * | 2013-07-08 | 2015-01-14 | 株式会社日立制作所 | Handwriting overlap processing device and method and electronic book equipment |
| CN105956601A (en) * | 2016-04-15 | 2016-09-21 | 北京工业大学 | Robot Chinese character writing learning method based on track imitation |
| CN106611172A (en) * | 2015-10-23 | 2017-05-03 | 北京大学 | Style learning-based Chinese character synthesis method |
| CN110766997A (en) * | 2018-07-26 | 2020-02-07 | 腾讯数码（天津）有限公司 | Copy display method, device and storage medium |
| CN111079503A (en) * | 2019-08-02 | 2020-04-28 | 广东小天才科技有限公司 | Character recognition method and electronic equipment |
| CN112805674A (en) * | 2018-12-19 | 2021-05-14 | 深圳市欢太科技有限公司 | Font setting method and device |
| CN112840312A (en) * | 2018-12-19 | 2021-05-25 | 深圳市欢太科技有限公司 | Font setting method and device |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB9305495D0 (en) * | 1993-03-17 | 1993-05-05 | Eden Group Ltd | Handwriting recognition device and method |
| CN100354860C (en) * | 2004-09-17 | 2007-12-12 | 华南理工大学 | Treating method and its use for dynamic Chinese character word library containing writing time sequence information |
| CN100338612C (en) * | 2005-07-08 | 2007-09-19 | 天津大学 | Water ink transmission model based on Chinese brush and xuan paper and emulation algorithm |
-
2008
- 2008-10-07 CN CN2008101214905A patent/CN101377854B/en not_active Expired - Fee Related
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101599180B (en) * | 2009-03-05 | 2012-06-13 | 浙江大学 | Automatic generation method of imitative computer calligraphy based on handwriting style |
| CN103136769A (en) * | 2011-12-02 | 2013-06-05 | 北京三星通信技术研究有限公司 | Method and device of generation of writing style font of user |
| CN103136769B (en) * | 2011-12-02 | 2016-02-03 | 北京三星通信技术研究有限公司 | The method and apparatus that user writing style font generates |
| CN102637078B (en) * | 2012-02-27 | 2015-09-09 | 厦门大学 | A kind of Chinese character pattern generation method of structure optimization |
| CN102637078A (en) * | 2012-02-27 | 2012-08-15 | 厦门大学 | Method for generating structurally optimized Chinese character patterns |
| CN102646023A (en) * | 2012-04-11 | 2012-08-22 | 广东欧珀移动通信有限公司 | Method for generating original user handwriting fonts |
| CN103885699A (en) * | 2012-12-20 | 2014-06-25 | 中山大学深圳研究院 | Automatic handwriting copying method based on mobile terminals |
| CN103914503A (en) * | 2012-12-28 | 2014-07-09 | 叶青湖 | System and method for generating personalized handwriting font |
| CN104281859A (en) * | 2013-07-08 | 2015-01-14 | 株式会社日立制作所 | Handwriting overlap processing device and method and electronic book equipment |
| CN106611172A (en) * | 2015-10-23 | 2017-05-03 | 北京大学 | Style learning-based Chinese character synthesis method |
| CN106611172B (en) * | 2015-10-23 | 2019-11-08 | 北京大学 | A kind of Chinese character synthetic method based on style study |
| CN105956601A (en) * | 2016-04-15 | 2016-09-21 | 北京工业大学 | Robot Chinese character writing learning method based on track imitation |
| CN105956601B (en) * | 2016-04-15 | 2019-01-29 | 北京工业大学 | A kind of robot Chinese writing and learning method based on Track Imitation |
| CN110766997A (en) * | 2018-07-26 | 2020-02-07 | 腾讯数码（天津）有限公司 | Copy display method, device and storage medium |
| CN112805674A (en) * | 2018-12-19 | 2021-05-14 | 深圳市欢太科技有限公司 | Font setting method and device |
| CN112840312A (en) * | 2018-12-19 | 2021-05-25 | 深圳市欢太科技有限公司 | Font setting method and device |
| CN112805674B (en) * | 2018-12-19 | 2024-04-02 | 深圳市欢太科技有限公司 | Font setting method and device |
| CN111079503A (en) * | 2019-08-02 | 2020-04-28 | 广东小天才科技有限公司 | Character recognition method and electronic equipment |
| CN111079503B (en) * | 2019-08-02 | 2023-08-25 | 广东小天才科技有限公司 | Character recognition method and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101377854B (en) | 2012-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101377854B (en) | Method for simulating Chinese characters hand-written handwriting by a computer | |
| CN101599180B (en) | Automatic generation method of imitative computer calligraphy based on handwriting style | |
| CN100583135C (en) | Computer estimation method of Chinese character writing shape beauty degree | |
| CN101393645A (en) | Hand-writing Chinese character computer generation and beautification method | |
| Lian et al. | EasyFont: a style learning-based system to easily build your large-scale handwriting fonts | |
| CN101393693B (en) | Computer educating method for Chinese character writing | |
| Xu et al. | Automatic generation of artistic Chinese calligraphy | |
| CN109871851B (en) | Chinese character writing normalization judging method based on convolutional neural network algorithm | |
| Yang et al. | Layered object models for image segmentation | |
| CN110378985A (en) | A kind of animation drawing auxiliary creative method based on GAN | |
| Razzak et al. | HMM and fuzzy logic: a hybrid approach for online Urdu script-based languages’ character recognition | |
| CN106203395A (en) | Face character recognition methods based on the study of the multitask degree of depth | |
| CN106611172B (en) | A kind of Chinese character synthetic method based on style study | |
| CN104123550A (en) | Cloud computing-based text scanning identification method | |
| Wang et al. | Evaluation of Chinese calligraphy by using DBSC vectorization and ICP algorithm | |
| CN112069900A (en) | Bill character recognition method and system based on convolutional neural network | |
| Liang et al. | A robot calligraphy writing method based on style transferring algorithm and similarity evaluation | |
| CN112784531A (en) | Chinese font and word stock generation method based on deep learning and part splicing | |
| CN101604451A (en) | A kind of automatic imitative writing method for personal Chinese character handwritten font based on shape grammar | |
| Xu et al. | An intelligent system for Chinese calligraphy | |
| CN101819683A (en) | Method for reconstructing Chinese character font | |
| Zand et al. | Recognition-based segmentation in Persian character recognition | |
| Gordienko et al. | Capsule deep neural network for recognition of historical Graffiti handwriting | |
| Hiremani et al. | Human and Machine Vision Based Indian Race Classification Using Modified-Convolutional Neural Network. | |
| Jung et al. | On-line recognition of cursive Korean characters using graph representation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20120104 Termination date: 20161007 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |