CN105096356A - Handwritten character emboldening method and handwritten character emboldening device - Google Patents
Handwritten character emboldening method and handwritten character emboldening device Download PDFInfo
- Publication number
- CN105096356A CN105096356A CN201410200641.1A CN201410200641A CN105096356A CN 105096356 A CN105096356 A CN 105096356A CN 201410200641 A CN201410200641 A CN 201410200641A CN 105096356 A CN105096356 A CN 105096356A
- Authority
- CN
- China
- Prior art keywords
- hand
- written character
- pixel
- character
- base picture
- 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
Landscapes
- Controls And Circuits For Display Device (AREA)
Abstract
The invention provides a handwritten character emboldening method and a handwritten character emboldening device. The handwritten character emboldening method includes the steps: obtaining a character draft image of handwritten characters; identifying the outlines of the handwritten characters in the character draft image; and changing pixel values of pixel points that are outside the outlines of the handwritten characters and are a certain distance away from pixel points on the outlines of the handwritten characters so that the edges of the handwritten characters are retouched. The character draft image is a binary image. According to the technical scheme, the edges of the handwritten characters are retouched, the handwritten character quality is guaranteed, the production cost is not increased, and emboldening of the handwritten characters is easy and feasible.
Description
Technical field
The present invention relates to character library manufacture technology field, in particular to a kind of hand-written character overstriking method and a kind of hand-written character overstriking device.
Background technology
In recent years, personal character library is subject to liking of more and more people, and personal character library is the demand according to individual calligraphist and fan thereof, and personal handwritten font is transformed into computer library to use as personal character library.
The manufacturing process of traditional computer character library, is roughly divided into the next stage: design word original text; Scanning input computer; Identify design word, carry out digitizing matching; Repair word; Quality inspection; Be integrated into storehouse etc.But because personal character library is different from traditional computer library, first personal character library needs author's written word original text, by author's written word original text scanning input computer, through digitizing matching, directly be integrated into storehouse, then test etc., if hand-written character stroke is partially thin, traditional way is: after generation profile character library, existing instrument (such as: FontLab) is used to carry out overstriking to character outline, then go to intersect, hand inspection is also revised, this is by man power and materials a large amount of for cost, if each classifying hand-written characters that needs of personal character library carries out adding bulk processing, the production cost of personal character library will inevitably be improved, for cost consideration, most font manufacturer takes to retain original effect, classifying hand-written characters does not carry out overstriking, but the display effect of personal character library can be affected like this, in character library, the stroke of font is general partially thin.
Therefore, how in guarantee hand-written character quality, while not improving manufacturing cost, classifying hand-written characters carries out the technical matters that overstriking becomes urgently to be resolved hurrily effectively.
Summary of the invention
Consider the technical matters occurred in correlation technique, the invention provides a kind of new hand-written character overstriking technology, by technical scheme of the present invention, limit is retouched to the hand-written character profile in word manuscript base picture, in guarantee hand-written character quality, while not improving production cost, simple classifying hand-written characters carries out overstriking.
According to an aspect of the present invention, provide a kind of hand-written character overstriking method, comprising: the word manuscript base picture obtaining hand-written character; Identify the profile of hand-written character described in described word manuscript base picture; The pixel value of the pixel of the pixel preset distance on the outline line of hand-written character described in the outer distance of profile changing described hand-written character, to retouch limit to described hand-written character, wherein, described word manuscript base picture is bianry image.
In this technical scheme, owing to comprising hand-written character in word manuscript base picture, and word manuscript base picture is bianry image, namely black and white two kinds of colors are only had, wherein, hand-written character is black, remainder is white, therefore after the profile by the hand-written character in identifier word manuscript base picture, change the pixel value of the pixel of the pixel preset distance on the outline line of the outer distance hand-written character of profile of hand-written character, realize the overstriking of classifying hand-written characters, carry out compared with overstriking with needing the profile manually using instrument classifying hand-written characters in prior art, limit is retouched to the hand-written character in word manuscript base picture, simple, and can automatic business processing, do not increase cost, simultaneously can by regulating the size of preset distance, regulate the overstriking ratio of hand-written character, thus ensure that hand-written character can not adhesion between stroke after overstriking, ensure the quality after hand-written character overstriking.
Specifically: in bianry image (word manuscript base picture), because hand-written character is black, remainder is white, therefore the pixel value of the pixel of the pixel preset distance on the outline line of the outer distance hand-written character of profile of hand-written character is changed, the pixel of the pixel preset distance on the outline line of outer for the profile of hand-written character distance hand-written character can be become black from white, the point in the profile of hand-written character is become by the point outside the profile of hand-written character, what realize classifying hand-written characters retouches limit, and classifying hand-written characters carries out overstriking.
Certainly, it should be noted that, by retouching limit to word manuscript base picture, realize the method for classifying hand-written characters overstriking, also can be used in the process of making computd character library, use the method can reduce in computer library manufacturing process and carry out overstriking to character outline, go the operations such as intersection, improves the generating period of character library, reduces cost of labor.
In technique scheme, preferably, the word manuscript base picture of described acquisition hand-written character is specially: with hand-written character described in default resolution scan, generates bianry image as described word manuscript base picture.
In this technical scheme, owing to retouching limit to character, be actually the pixel value of the pixel changed in word manuscript base picture, the resolution of scan word manuscript base picture is higher, in the word manuscript base picture of scanning, pixel is more, the overstriking operation of classifying hand-written characters is more accurate, and the hand-written character quality after overstriking is better, but the scanning process of classifying hand-written characters is consuming time longer; On the contrary, the resolution of scan word manuscript base picture is lower, pixel in the word manuscript base picture then scanned is fewer, the overstriking operation of classifying hand-written characters is fuzzyyer, and the hand-written character quality after overstriking will be poorer, but the scanning process of hand-written character is consuming time shorter, therefore, the size of the default resolution of scanning hand-written character can be chosen according to the overstriking effect of classifying hand-written characters and the length of sweep time, and as comparatively preferred technical scheme, default resolution is more high better.
In technique scheme, preferably, the profile of the described hand-written character in described identification described word manuscript base picture is specially: word manuscript base picture described in raster scanning; Judge whether there is the pixel different from described arbitrary pixel pixel value in multiple neighbor pixels of arbitrary pixel in described word manuscript base picture; When there is at least one pixel different from described arbitrary pixel pixel value in the multiple neighbor pixels judging arbitrary pixel in described word manuscript base picture, determine that described arbitrary pixel is the pixel on the outline line of described hand-written character; Pixel on all described outline lines forms the profile of described hand-written character.
In this technical scheme, because word manuscript base picture is bianry image, wherein, hand-written character is black, remainder is white, each pixel in raster scanning (lining by line scan) word manuscript base picture, judge whether there is the pixel different from the pixel value of this pixel in the neighbor pixel of arbitrary pixel, due to be in the point on hand-written character outline line neighbor pixel in always there is at least one pixel not identical with its pixel value, therefore, in word manuscript base picture arbitrary pixel neighbor pixel in when there is at least one pixel different from the pixel value of this pixel, can judge that this pixel is as the point on the outline line of hand-written character, point on all outline lines can form hand-written characters all in word manuscript base picture.
In technique scheme, preferably, described preset distance is relevant with the size of described hand-written character and the stroke weight of described hand-written character.
In this technical scheme, classifying hand-written characters carries out adding bulk processing, but need the quality ensureing hand-written character, namely can not adhesion between the stroke in hand-written character, when retouching limit to word manuscript base picture, the size of hand-written character and the thickness of hand-written character all will affect the size of preset distance, specifically, hand-written character is larger, spacing between the stroke of hand-written character is larger, then the value of preset distance also should be larger, and hand-written character is less, spacing between the stroke of hand-written character is less, then the value of preset distance also should be less; Hand-written character is thinner, and the spacing between the stroke of hand-written character is larger, then the value of preset distance should be larger, and hand-written character is thicker, and the spacing between the stroke of hand-written character is less, then the value of preset distance should be less.
In technique scheme, preferably, also comprise: digitizing matching is carried out to the described hand-written character after overstriking, generate character library.
In this technical scheme, after word manuscript base picture being retouched to limit process, after also namely adding bulk processing to the hand-written character in word manuscript base picture, by bianry image (word manuscript base picture) digitizing matching, generate character library with easy to use.As comparatively preferred technical scheme, when bianry image is carried out digitizing matching, can fit to as far as possible close to the curved profile of hand-written character original copy, namely ensure the quality after hand-written character overstriking as much as possible.
According to a further aspect in the invention, propose a kind of hand-written character overstriking device, comprising: acquiring unit, for obtaining the word manuscript base picture of hand-written character; Recognition unit, is connected to described acquiring unit, for identifying the profile of hand-written character described in described word manuscript base picture; Processing unit, be connected to described recognition unit, the pixel value of the pixel of the pixel preset distance on the outline line of hand-written character described in the outer distance of the profile for changing described hand-written character, to retouch limit to described hand-written character, wherein, described word manuscript base picture is bianry image.
In this technical scheme, owing to comprising hand-written character in word manuscript base picture, and word manuscript base picture is bianry image, namely black and white two kinds of colors are only had, wherein, hand-written character is black, remainder is white, therefore after the profile by the hand-written character in identifier word manuscript base picture, change the pixel value of the pixel of the pixel preset distance on the outline line of the outer distance hand-written character of profile of hand-written character, realize the overstriking of classifying hand-written characters, carry out compared with overstriking with needing the profile manually using instrument classifying hand-written characters in prior art, limit is retouched to the hand-written character in word manuscript base picture, simple, and can automatic business processing, do not increase cost, simultaneously can by regulating the size of preset distance, regulate the overstriking ratio of hand-written character, thus ensure that hand-written character can not adhesion between stroke after overstriking, ensure the quality after hand-written character overstriking.
Specifically: in bianry image (word manuscript base picture), because hand-written character is black, remainder is white, therefore the pixel value of the pixel of the pixel preset distance on the outline line of the outer distance hand-written character of profile of hand-written character is changed, the pixel of the pixel preset distance on the outline line of outer for the profile of hand-written character distance hand-written character can be become black from white, the point in the profile of hand-written character is become by the point outside the profile of hand-written character, what realize classifying hand-written characters retouches limit, and classifying hand-written characters carries out overstriking.
Certainly, it should be noted that, by retouching limit to word manuscript base picture, realize the method for classifying hand-written characters overstriking, also can be used in the process of making computd character library, use the method can reduce in computer library manufacturing process and carry out overstriking to character outline, go the operations such as intersection, improves the generating period of character library, reduces cost of labor.
In technique scheme, preferably, described acquiring unit, specifically for hand-written character described in default resolution scan, generates bianry image as described word manuscript base picture.
In this technical scheme, owing to retouching limit to character, be actually the pixel value of the pixel changed in word manuscript base picture, the resolution of scan word manuscript base picture is higher, in the word manuscript base picture of scanning, pixel is more, the overstriking operation of classifying hand-written characters is more accurate, and the hand-written character quality after overstriking is better, but the scanning process of classifying hand-written characters is consuming time longer; On the contrary, the resolution of scan word manuscript base picture is lower, pixel in the word manuscript base picture then scanned is fewer, the overstriking operation of classifying hand-written characters is fuzzyyer, and the hand-written character quality after overstriking will be poorer, but the scanning process of hand-written character is consuming time shorter, therefore, the size of the default resolution of scanning hand-written character can be chosen according to the overstriking effect of classifying hand-written characters and the length of sweep time, and as comparatively preferred technical scheme, default resolution is more high better.
In technique scheme, preferably, described recognition unit comprises: scanning element, is connected to described acquiring unit, for word manuscript base picture described in raster scanning; Judging unit, is connected to described scanning element, for judge arbitrary pixel in described word manuscript base picture multiple neighbor pixels in whether there is the pixel different from described arbitrary pixel pixel value; Outline specifying unit, be connected to described judging unit, during for there is at least one pixel different from described arbitrary pixel pixel value in the multiple neighbor pixels judging arbitrary pixel in described word manuscript base picture, determine that described arbitrary pixel is the pixel on the outline line of described hand-written character; Outline generating unit, is connected to described outline specifying unit, forms the profile of described hand-written character with the pixel on all described outline lines.
In this technical scheme, because word manuscript base picture is bianry image, wherein, hand-written character is black, remainder is white, each pixel in raster scanning (lining by line scan) word manuscript base picture, judge whether there is the pixel different from the pixel value of this pixel in the neighbor pixel of arbitrary pixel, due to be in the point on hand-written character outline line neighbor pixel in always there is at least one pixel not identical with its pixel value, therefore, in word manuscript base picture arbitrary pixel neighbor pixel in when there is at least one pixel different from the pixel value of this pixel, can judge that this pixel is as the point on the outline line of hand-written character, point on all outline lines can form hand-written characters all in word manuscript base picture.
In technique scheme, preferably, described processing unit is also for adjusting described preset distance according to the size of described hand-written character and the stroke weight of described hand-written character.
In this technical scheme, classifying hand-written characters carries out adding bulk processing, but need the quality ensureing hand-written character, namely can not adhesion between the stroke in hand-written character, when retouching limit to word manuscript base picture, the size of hand-written character and the thickness of hand-written character all will affect the size of preset distance, specifically, hand-written character is larger, spacing between the stroke of hand-written character is larger, then the value of preset distance also should be larger, and hand-written character is less, spacing between the stroke of hand-written character is less, then the value of preset distance also should be less; Hand-written character is thinner, and the spacing between the stroke of hand-written character is larger, then the value of preset distance should be larger, and hand-written character is thicker, and the spacing between the stroke of hand-written character is less, then the value of preset distance should be less.
In technique scheme, preferably, also comprising: character library generation unit, be connected to described processing unit, for carrying out digitizing matching to the described hand-written character after overstriking, generating character library.
In this technical scheme, after word manuscript base picture being retouched to limit process, after also namely adding bulk processing to the hand-written character in word manuscript base picture, by bianry image (word manuscript base picture) digitizing matching, generate character library with easy to use.As comparatively preferred technical scheme, when bianry image is carried out digitizing matching, can fit to as far as possible close to the curved profile of hand-written character original copy, namely ensure the quality after hand-written character overstriking as much as possible.
Accompanying drawing explanation
Fig. 1 shows the schematic flow diagram of hand-written character overstriking method according to an embodiment of the invention;
Fig. 2 shows the schematic diagram contrasted before and after hand-written character overstriking according to an embodiment of the invention;
Fig. 3 shows the structural representation of hand-written character overstriking device according to an embodiment of the invention.
Embodiment
In order to more clearly understand above-mentioned purpose of the present invention, feature and advantage, below in conjunction with the drawings and specific embodiments, the present invention is further described in detail.It should be noted that, when not conflicting, the feature in the embodiment of the application and embodiment can combine mutually.
Set forth a lot of detail in the following description so that fully understand the present invention, but the present invention can also adopt other to be different from other modes described here and implement, and therefore, the present invention is not limited to the restriction of following public specific embodiment.
Fig. 1 shows the schematic flow diagram of hand-written character overstriking method according to an embodiment of the invention.
As shown in Figure 1, hand-written character overstriking method, comprising: step 102 according to an embodiment of the invention, obtains the word manuscript base picture of hand-written character; Step 104, identifies the profile of hand-written character described in described word manuscript base picture; Step 106, the pixel value of the pixel of the pixel preset distance on the outline line of hand-written character described in the outer distance of profile changing described hand-written character, to retouch limit to described hand-written character, wherein, described word manuscript base picture is bianry image.
In this technical scheme, owing to comprising hand-written character in word manuscript base picture, and word manuscript base picture is bianry image, namely black and white two kinds of colors are only had, wherein, hand-written character is black, remainder is white, therefore after the profile by the hand-written character in identifier word manuscript base picture, change the pixel value of the pixel of the pixel preset distance on the outline line of the outer distance hand-written character of profile of hand-written character, realize the overstriking of classifying hand-written characters, carry out compared with overstriking with needing the profile manually using instrument classifying hand-written characters in prior art, limit is retouched to the hand-written character in word manuscript base picture, simple, and can automatic business processing, do not increase cost, simultaneously can by regulating the size of preset distance, regulate the overstriking ratio of hand-written character, thus ensure that hand-written character can not adhesion between stroke after overstriking, ensure the quality after hand-written character overstriking.
Specifically: in bianry image (word manuscript base picture), because hand-written character is black, remainder is white, therefore the pixel value of the pixel of the pixel preset distance on the outline line of the outer distance hand-written character of profile of hand-written character is changed, the pixel of the pixel preset distance on the outline line of outer for the profile of hand-written character distance hand-written character can be become black from white, the point in the profile of hand-written character is become by the point outside the profile of hand-written character, what realize classifying hand-written characters retouches limit, and classifying hand-written characters carries out overstriking.
Certainly, it should be noted that, by retouching limit to word manuscript base picture, realize the method for classifying hand-written characters overstriking, also can be used in the process of making computd character library, use the method can reduce in computer library manufacturing process and carry out overstriking to character outline, go the operations such as intersection, improves the generating period of character library, reduces cost of labor.
Fig. 2 shows the schematic diagram contrasted before and after hand-written character overstriking according to an embodiment of the invention.
As shown in Figure 2, " upright character library " four hand-written characters obtain overstriking when ensureing hand-written character quality, and wherein 202 is the character before overstriking, and 204 is the character after overstriking.
In technique scheme, preferably, the word manuscript base picture of described acquisition hand-written character is specially: with hand-written character described in default resolution scan, generates bianry image as described word manuscript base picture.
In this technical scheme, owing to retouching limit to character, be actually the pixel value of the pixel changed in word manuscript base picture, the resolution of scan word manuscript base picture is higher, in the word manuscript base picture of scanning, pixel is more, the overstriking operation of classifying hand-written characters is more accurate, and the hand-written character quality after overstriking is better, but the scanning process of classifying hand-written characters is consuming time longer; On the contrary, the resolution of scan word manuscript base picture is lower, pixel in the word manuscript base picture then scanned is fewer, the overstriking operation of classifying hand-written characters is fuzzyyer, and the hand-written character quality after overstriking will be poorer, but the scanning process of hand-written character is consuming time shorter, therefore, the size of the default resolution of scanning hand-written character can be chosen according to the overstriking effect of classifying hand-written characters and the length of sweep time, and as comparatively preferred technical scheme, default resolution is more high better.
In technique scheme, preferably, the profile of the described hand-written character in described identification described word manuscript base picture is specially: word manuscript base picture described in raster scanning; Judge whether there is the pixel different from described arbitrary pixel pixel value in multiple neighbor pixels of arbitrary pixel in described word manuscript base picture; When there is at least one pixel different from described arbitrary pixel pixel value in the multiple neighbor pixels judging arbitrary pixel in described word manuscript base picture, determine that described arbitrary pixel is the pixel on the outline line of described hand-written character; Pixel on all described outline lines forms the profile of described hand-written character.
In this technical scheme, because word manuscript base picture is bianry image, wherein, hand-written character is black, remainder is white, each pixel in raster scanning (lining by line scan) word manuscript base picture, judge whether there is the pixel different from the pixel value of this pixel in the neighbor pixel of arbitrary pixel, due to be in the point on hand-written character outline line neighbor pixel in always there is at least one pixel not identical with its pixel value, therefore, in word manuscript base picture arbitrary pixel neighbor pixel in when there is at least one pixel different from the pixel value of this pixel, can judge that this pixel is as the point on the outline line of hand-written character, point on all outline lines can form hand-written characters all in word manuscript base picture.
In technique scheme, preferably, described preset distance is relevant with the size of described hand-written character and the stroke weight of described hand-written character.
In this technical scheme, classifying hand-written characters carries out adding bulk processing, but need the quality ensureing hand-written character, namely can not adhesion between the stroke in hand-written character, when retouching limit to word manuscript base picture, the size of hand-written character and the thickness of hand-written character all will affect the size of preset distance, specifically, hand-written character is larger, spacing between the stroke of hand-written character is larger, then the value of preset distance also should be larger, and hand-written character is less, spacing between the stroke of hand-written character is less, then the value of preset distance also should be less; Hand-written character is thinner, and the spacing between the stroke of hand-written character is larger, then the value of preset distance should be larger, and hand-written character is thicker, and the spacing between the stroke of hand-written character is less, then the value of preset distance should be less.Wherein, the width of preset distance can be 1-5 pixel, and preferably the width of preset distance can be 2 pixels, certainly, herein and be not used in concrete restriction.
In technique scheme, preferably, also comprise: digitizing matching is carried out to the described hand-written character after overstriking, generate character library.
In this technical scheme, after word manuscript base picture being retouched to limit process, after also namely adding bulk processing to the hand-written character in word manuscript base picture, by bianry image (word manuscript base picture) digitizing matching, generate character library with easy to use.As comparatively preferred technical scheme, when bianry image is carried out digitizing matching, can fit to as far as possible close to the curved profile of hand-written character original copy, namely ensure the quality after hand-written character overstriking as much as possible.
Fig. 3 shows the structural representation of hand-written character overstriking device according to an embodiment of the invention.
As shown in Figure 3, hand-written character overstriking device 300 according to an embodiment of the invention, comprising: acquiring unit 302, for obtaining the word manuscript base picture of hand-written character; Recognition unit 304, is connected to described acquiring unit 302, for identifying the profile of hand-written character described in described word manuscript base picture; Processing unit 306, be connected to described recognition unit 304, the pixel value of the pixel of the pixel preset distance on the outline line of hand-written character described in the outer distance of the profile for changing described hand-written character, to retouch limit to described hand-written character, wherein, described word manuscript base picture is bianry image.
In this technical scheme, owing to comprising hand-written character in word manuscript base picture, and word manuscript base picture is bianry image, namely black and white two kinds of colors are only had, wherein, hand-written character is black, remainder is white, therefore after the profile by the hand-written character in identifier word manuscript base picture, change the pixel value of the pixel of the pixel preset distance on the outline line of the outer distance hand-written character of profile of hand-written character, realize the overstriking of classifying hand-written characters, carry out compared with overstriking with needing the profile manually using instrument classifying hand-written characters in prior art, limit is retouched to the hand-written character in word manuscript base picture, simple, and can automatic business processing, do not increase cost, simultaneously can by regulating the size of preset distance, regulate the overstriking ratio of hand-written character, thus ensure that hand-written character can not adhesion between stroke after overstriking, ensure the quality after hand-written character overstriking.
Specifically: in bianry image (word manuscript base picture), because hand-written character is black, remainder is white, therefore the pixel value of the pixel of the pixel preset distance on the outline line of the outer distance hand-written character of profile of hand-written character is changed, the pixel of the pixel preset distance on the outline line of outer for the profile of hand-written character distance hand-written character can be become black from white, the point in the profile of hand-written character is become by the point outside the profile of hand-written character, what realize classifying hand-written characters retouches limit, and classifying hand-written characters carries out overstriking.
Certainly, it should be noted that, by retouching limit to word manuscript base picture, realize the method for classifying hand-written characters overstriking, also can be used in the process of making computd character library, use the method can reduce in computer library manufacturing process and carry out overstriking to character outline, go the operations such as intersection, improves the generating period of character library, reduces cost of labor.
In technique scheme, preferably, described acquiring unit 302, specifically for hand-written character described in default resolution scan, generates bianry image as described word manuscript base picture.
In this technical scheme, owing to retouching limit to character, be actually the pixel value of the pixel changed in word manuscript base picture, the resolution of scan word manuscript base picture is higher, in the word manuscript base picture of scanning, pixel is more, the overstriking operation of classifying hand-written characters is more accurate, and the hand-written character quality after overstriking is better, but the scanning process of classifying hand-written characters is consuming time longer; On the contrary, the resolution of scan word manuscript base picture is lower, pixel in the word manuscript base picture then scanned is fewer, the overstriking operation of classifying hand-written characters is fuzzyyer, and the hand-written character quality after overstriking will be poorer, but the scanning process of hand-written character is consuming time shorter, therefore, the size of the default resolution of scanning hand-written character can be chosen according to the overstriking effect of classifying hand-written characters and the length of sweep time, and as comparatively preferred technical scheme, default resolution is more high better.
In technique scheme, preferably, described recognition unit comprises 304: scanning element 3042, is connected to described acquiring unit 302, for word manuscript base picture described in raster scanning; Judging unit 3044, is connected to described scanning element 3042, for judge arbitrary pixel in described word manuscript base picture multiple neighbor pixels in whether there is the pixel different from described arbitrary pixel pixel value; Outline specifying unit 3046, be connected to described judging unit 3044, during for there is at least one pixel different from described arbitrary pixel pixel value in the multiple neighbor pixels judging arbitrary pixel in described word manuscript base picture, determine that described arbitrary pixel is the pixel on the outline line of described hand-written character; Outline generating unit 3048, is connected to described outline specifying unit 3046, forms the profile of described hand-written character with the pixel on all described outline lines.
In this technical scheme, because word manuscript base picture is bianry image, wherein, hand-written character is black, remainder is white, each pixel in raster scanning (lining by line scan) word manuscript base picture, judge whether there is the pixel different from the pixel value of this pixel in the neighbor pixel of arbitrary pixel, due to be in the point on hand-written character outline line neighbor pixel in always there is at least one pixel not identical with its pixel value, therefore, in word manuscript base picture arbitrary pixel neighbor pixel in when there is at least one pixel different from the pixel value of this pixel, can judge that this pixel is as the point on the outline line of hand-written character, point on all outline lines can form hand-written characters all in word manuscript base picture.
In technique scheme, preferably, described processing unit 306 is also for adjusting described preset distance according to the size of described hand-written character and the stroke weight of described hand-written character.
In this technical scheme, classifying hand-written characters carries out adding bulk processing, but need the quality ensureing hand-written character, namely can not adhesion between the stroke in hand-written character, when retouching limit to word manuscript base picture, the size of hand-written character and the thickness of hand-written character all will affect the size of preset distance, specifically, hand-written character is larger, spacing between the stroke of hand-written character is larger, then the value of preset distance also should be larger, and hand-written character is less, spacing between the stroke of hand-written character is less, then the value of preset distance also should be less; Hand-written character is thinner, and the spacing between the stroke of hand-written character is larger, then the value of preset distance should be larger, and hand-written character is thicker, and the spacing between the stroke of hand-written character is less, then the value of preset distance should be less.
In technique scheme, preferably, also comprising: character library generation unit 308, be connected to described processing unit 306, for carrying out digitizing matching to the described hand-written character after overstriking, generating character library.
In this technical scheme, after word manuscript base picture being retouched to limit process, after also namely adding bulk processing to the hand-written character in word manuscript base picture, by bianry image (word manuscript base picture) digitizing matching, generate character library with easy to use.As comparatively preferred technical scheme, when bianry image is carried out digitizing matching, can fit to as far as possible close to the curved profile of hand-written character original copy, namely ensure the quality after hand-written character overstriking as much as possible.
More than be described with reference to the accompanying drawings technical scheme of the present invention, consider in the prior art, when classifying hand-written characters carries out overstriking, need after generation profile character library, existing instrument is used to carry out overstriking to character outline, then go to intersect, hand inspection is also revised, by man power and materials a large amount of for cost, by technical scheme of the present invention, limit is retouched to the hand-written character profile in word manuscript base picture, in guarantee hand-written character quality, while not improving production cost, simple classifying hand-written characters carries out overstriking.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. a hand-written character overstriking method, is characterized in that, comprising:
Obtain the word manuscript base picture of hand-written character;
Identify the profile of hand-written character described in described word manuscript base picture;
The pixel value of the pixel of the pixel preset distance on the outline line of hand-written character described in the outer distance of profile changing described hand-written character, to retouch limit to described hand-written character, wherein, described word manuscript base picture is bianry image.
2. hand-written character overstriking method according to claim 1, is characterized in that, the word manuscript base picture of described acquisition hand-written character is specially: with hand-written character described in default resolution scan, generates bianry image as described word manuscript base picture.
3. hand-written character overstriking method according to claim 1, is characterized in that, the profile of the described hand-written character in described identification described word manuscript base picture is specially:
Word manuscript base picture described in raster scanning;
Judge whether there is the pixel different from described arbitrary pixel pixel value in multiple neighbor pixels of arbitrary pixel in described word manuscript base picture;
When there is at least one pixel different from described arbitrary pixel pixel value in the multiple neighbor pixels judging arbitrary pixel in described word manuscript base picture, determine that described arbitrary pixel is the pixel on the outline line of described hand-written character;
Pixel on all described outline lines forms the profile of described hand-written character.
4. hand-written character overstriking method according to claim 1, is characterized in that, described preset distance is relevant with the size of described hand-written character and the stroke weight of described hand-written character.
5. hand-written character overstriking method according to claim 1, is characterized in that, also comprise: carry out digitizing matching to the described hand-written character after overstriking, generates character library.
6. a hand-written character overstriking device, is characterized in that, comprising:
Acquiring unit, for obtaining the word manuscript base picture of hand-written character;
Recognition unit, is connected to described acquiring unit, for identifying the profile of hand-written character described in described word manuscript base picture;
Processing unit, be connected to described recognition unit, the pixel value of the pixel of the pixel preset distance on the outline line of hand-written character described in the outer distance of the profile for changing described hand-written character, to retouch limit to described hand-written character, wherein, described word manuscript base picture is bianry image.
7. hand-written character overstriking device according to claim 6, is characterized in that, described acquiring unit, specifically for hand-written character described in default resolution scan, generates bianry image as described word manuscript base picture.
8. hand-written character overstriking device according to claim 6, it is characterized in that, described recognition unit comprises:
Scanning element, is connected to described acquiring unit, for word manuscript base picture described in raster scanning;
Judging unit, is connected to described scanning element, for judge arbitrary pixel in described word manuscript base picture multiple neighbor pixels in whether there is the pixel different from described arbitrary pixel pixel value;
Outline specifying unit, be connected to described judging unit, during for there is at least one pixel different from described arbitrary pixel pixel value in the multiple neighbor pixels judging arbitrary pixel in described word manuscript base picture, determine that described arbitrary pixel is the pixel on the outline line of described hand-written character;
Outline generating unit, is connected to described outline specifying unit, forms the profile of described hand-written character with the pixel on all described outline lines.
9. hand-written character overstriking device according to claim 6, is characterized in that, described processing unit is also for adjusting described preset distance according to the size of described hand-written character and the stroke weight of described hand-written character.
10. hand-written character overstriking device according to claim 6, is characterized in that, also comprise:
Character library generation unit, is connected to described processing unit, for carrying out digitizing matching to the described hand-written character after overstriking, generates character library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410200641.1A CN105096356A (en) | 2014-05-13 | 2014-05-13 | Handwritten character emboldening method and handwritten character emboldening device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410200641.1A CN105096356A (en) | 2014-05-13 | 2014-05-13 | Handwritten character emboldening method and handwritten character emboldening device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105096356A true CN105096356A (en) | 2015-11-25 |
Family
ID=54576692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410200641.1A Pending CN105096356A (en) | 2014-05-13 | 2014-05-13 | Handwritten character emboldening method and handwritten character emboldening device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105096356A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110766771A (en) * | 2019-10-18 | 2020-02-07 | 天津津航计算技术研究所 | Character edge tracing method based on FPGA |
| CN113326009A (en) * | 2021-03-05 | 2021-08-31 | 临沂大学 | Paper calligraphy work copying method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060146054A1 (en) * | 2004-12-30 | 2006-07-06 | Microsoft Corporation | Use of an input overscaled bitmap to generate emboldened overscaled bitmap |
| CN101916318A (en) * | 2010-08-27 | 2010-12-15 | 镇江科大船苑计算机网络工程有限公司 | Scale value outline overstriking drawing method of sign plate |
| CN101930587A (en) * | 2009-06-19 | 2010-12-29 | 株式会社理光 | Watermark information extended coding, embedding, evaluating and detection extracting method and device thereof |
| CN103177709A (en) * | 2011-12-20 | 2013-06-26 | 北大方正集团有限公司 | Method and device for displaying characters |
-
2014
- 2014-05-13 CN CN201410200641.1A patent/CN105096356A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060146054A1 (en) * | 2004-12-30 | 2006-07-06 | Microsoft Corporation | Use of an input overscaled bitmap to generate emboldened overscaled bitmap |
| CN101930587A (en) * | 2009-06-19 | 2010-12-29 | 株式会社理光 | Watermark information extended coding, embedding, evaluating and detection extracting method and device thereof |
| CN101916318A (en) * | 2010-08-27 | 2010-12-15 | 镇江科大船苑计算机网络工程有限公司 | Scale value outline overstriking drawing method of sign plate |
| CN103177709A (en) * | 2011-12-20 | 2013-06-26 | 北大方正集团有限公司 | Method and device for displaying characters |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110766771A (en) * | 2019-10-18 | 2020-02-07 | 天津津航计算技术研究所 | Character edge tracing method based on FPGA |
| CN110766771B (en) * | 2019-10-18 | 2023-07-28 | 天津津航计算技术研究所 | Character edge tracing method based on FPGA |
| CN113326009A (en) * | 2021-03-05 | 2021-08-31 | 临沂大学 | Paper calligraphy work copying method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8711372B2 (en) | Techniques for image segment accumulation in document rendering | |
| JP2016201126A (en) | Detection of label from image | |
| US9965871B1 (en) | Multi-binarization image processing | |
| US10878461B2 (en) | Multimedia information processing method, apparatus, and device, and storage medium | |
| CN109697414B (en) | Text positioning method and device | |
| CN106202086B (en) | Picture processing and obtaining method, device and system | |
| US10083218B1 (en) | Repairing tables | |
| CN103530625A (en) | Optical character recognition method based on digital image processing | |
| CN104943421A (en) | Method for automatically selecting test parameters of an image inspection system | |
| CN105159627A (en) | Method for automatically correcting digital printing chromatic aberration | |
| CN102890826A (en) | Method for resetting scan edition document | |
| CN112347288A (en) | Character and picture vectorization method | |
| CN105096356A (en) | Handwritten character emboldening method and handwritten character emboldening device | |
| US20110187721A1 (en) | Line drawing processing apparatus, storage medium storing a computer-readable program, and line drawing processing method | |
| CN1674634A (en) | Method and apparatus for color transformation (conversion) | |
| JP2009134410A (en) | Coloring device, coloring method and program | |
| CN107861931B (en) | Template file processing method and device, computer equipment and storage medium | |
| CN105704347A (en) | Image processing apparatus and image processing method | |
| JP5885956B2 (en) | Font matching | |
| CN102096903B (en) | Page rasterized character smooth processing method and system | |
| US11074392B2 (en) | Information processing apparatus and non-transitory computer readable medium for switching between an attribute information mode and an image information mode | |
| JP2004086436A (en) | Image processor, image processing method, program, and storage medium | |
| CN109933262B (en) | GIF screen capturing method and device | |
| CN109086481B (en) | Method for improving DRC examination efficiency of integrated circuit design layout | |
| US20150055864A1 (en) | Image Processing Apparatus and Sheet |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151125 |