CN102541347A - Automatic identification system and method of handwriting Chinese character - Google Patents
Automatic identification system and method of handwriting Chinese character Download PDFInfo
- Publication number
- CN102541347A CN102541347A CN2011103604419A CN201110360441A CN102541347A CN 102541347 A CN102541347 A CN 102541347A CN 2011103604419 A CN2011103604419 A CN 2011103604419A CN 201110360441 A CN201110360441 A CN 201110360441A CN 102541347 A CN102541347 A CN 102541347A
- Authority
- CN
- China
- Prior art keywords
- image
- data
- handwriting
- gradient
- degree
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 230000005484 gravity Effects 0.000 claims description 14
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 230000002411 adverse Effects 0.000 claims description 3
- 238000003707 image sharpening Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000008014 freezing Effects 0.000 claims description 2
- 238000007710 freezing Methods 0.000 claims description 2
- 230000007704 transition Effects 0.000 claims description 2
- 238000000638 solvent extraction Methods 0.000 claims 1
- 230000005540 biological transmission Effects 0.000 abstract description 3
- 230000002452 interceptive effect Effects 0.000 abstract 1
- 238000010295 mobile communication Methods 0.000 abstract 1
- 230000011664 signaling Effects 0.000 abstract 1
- 238000011160 research Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 8
- 239000004973 liquid crystal related substance Substances 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 239000011800 void material Substances 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000010897 surface acoustic wave method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Character Discrimination (AREA)
Abstract
The invention relates to an automatic identification system and a method of a handwriting Chinese character. The system comprises an EMB-4650 main board, wherein expanded sub-interfaces of the EMB-4650 main board are a low voltage differential signaling (LVDS) interface, a digital video interactive (DVI) interface, a universal serial bus (USB) interface and a computer-output microfilm (COM) interface which are respectively connected with an AUO display screen, a DVI-LVDS signal converting board, a USB controller and a global system for mobile communication (GSM) module. The DVI-LVDS signal converting board is connected with another AUO display screen, and the USB controller is connected with a touch screen. The identification method comprises the steps of (1) inputting handwriting Chinese character data, (2) preprocessing the handwriting Chinese character data, (3) extracting shape features of the handwriting Chinese character data, and (4) identifying the handwriting Chinese character data. By means of the automatic identification system and the method of the handwriting Chinese character, a novel polar coordinate feature recognition method with font centroid as a reference point. Users can record, store and send important information in real time by utilizing a handwriting mode, thereby achieving the matching between handwriting Chinese characters and handwriting Chinese characters. The system integrates high confidentiality and high-speed transmission and is suitable for intelligence agents to collect and screen the important information.
Description
Technical Field
The invention relates to a method for automatically extracting note features by using a computer, in particular to a handwriting automatic identification system and a handwriting automatic identification method.
Background
Handwriting is a fairly stable behavior characteristic, different people have different handwriting, and the handwriting is easy to obtain. With the rapid development of information digitization, handwriting authentication becomes an active research topic in the field of computer vision and pattern recognition. As is well known, the literature experts can identify the authenticity of the handwriting, but the computer automatically extracts the handwriting characteristics and identifies the authenticity of the handwriting, and particularly, the computer still has certain difficulty on a small amount of handwriting.
The research of computer handwriting authentication began in the last 60 th century. In recent years, as computer handwriting identification technology is widely applied in the fields of public security, finance, education evaluation and the like, the technology is gradually becoming an active but difficult research subject in the fields of computer vision and pattern recognition, Chinese and foreign scholars make extensive research on the technology, but a satisfactory solution is not obtained so far.
Since the information communication technology in developed countries starts early and develops rapidly, its popularity and usage degree have reached a higher level, and their computer management and automation technologies also have a considerable popularity and a higher modernization degree, the computer identity authentication technology has gradually received extensive attention and research. At present, a plurality of related products for signature identification appear in foreign markets, but due to the particularity of Chinese character construction, the research work for identifying the handwriting of the Chinese characters is slow. Due to differences in cultural backgrounds and the like, western countries have few researches on the problem of identifying oriental characters, so that research institutions related to the problems are mostly distributed in asia, and currently, main research institutions include korea cauldron mountain university, mode identification laboratories of the institute of automation of the chinese academy of sciences, and the institute of calculation of the chinese academy of sciences. In addition, at present, many companies in China are dedicated to the development of handwriting identification systems and achieve some results, but the real investment is not available at present.
Disclosure of Invention
The invention aims to provide a handwriting pen body automatic identification system and a handwriting pen body automatic identification method aiming at the defects in the prior art, which take a diary in daily life and work as a design prototype, combine personal double-page note writing habits, and realize information search aiming at a personal handwriting pen body by utilizing a computer technology and an innovative search algorithm. The system starts from a plurality of structural characteristics of the Chinese characters, comprehensively analyzes the characteristics of handwriting, abandons a huge standard word stock, and directly searches from handwriting to handwriting conveniently, thereby not only paying attention to extracting commonalities from personalities, but also emphasizing the grasp of the personalities.
In order to achieve the above object, the idea of the present invention is as follows: the invention realizes the searching function based on the handwritten font recognition of the image. The technology belongs to the category of offline character recognition, and the system searching function only needs to find the same or similar characters in a library written by a user without judging which character in Chinese characters the characters written by the user specifically correspond to. The system is used for processing two-dimensional images, separating the written Chinese characters from the background, and searching the positions of picture files of the same or similar characters as the written Chinese characters through a series of preprocessing and displaying the picture files. The whole searching process can be divided into the following parts: information acquisition (handwritten character input), preprocessing (including background removal, character segmentation and the like), single character feature extraction, and comparison selection.
According to the inventive concept, the invention adopts the following technical scheme:
an automatic handwriting pen body recognition system comprises an EMB-4650 mainboard which is made by controlling Intel Atom Z510P chips, and is characterized in that the extended sub-interfaces of the mainboard comprise an LVDS interface, a DVI interface, a USB interface and a COM interface; the interfaces are respectively connected with the AUO display screen, the DVI-LVDS signal conversion board, the USB controller and the GSM module; therefore, the DVI-LVDS signal conversion board is connected with another AUO display screen, and the USB controller is connected with the touch screen. When a user writes data in the touch screen, the data are transmitted to the EMB-4650 mainboard through the USB controller, and meanwhile, the EMB-4650 mainboard transmits the data to the display screen to realize real-time display; meanwhile, the EMB-4650 mainboard performs recognition algorithm processing on the data, and then sends the processed result to a display screen for displaying, so that a simple human-computer interaction real-time operation effect is achieved. If necessary, the edited font data can be sent to the GSM module through the COM port, so that the real-time sending of the data is realized.
The font is written on the touch screen by a user, font data are input into a storage device and are preprocessed by a processor, then the shape characteristics of a single character are extracted by using a polar coordinate method claimed by the text application, and the input character is selected and determined. Meanwhile, the character result after the user's input and processing is displayed on the liquid crystal display. If necessary, the GSM module can be used for carrying out wireless transmission on the input information, so that the information can be transmitted more conveniently and timely.
In the system, the power supply of the system adopts an external power supply mode to supply power. The 18V alternating current power supply is obtained from a commercial power 220V50Hz through a power supply filter and a transformer and is connected into the voltage conversion circuit, and the voltage conversion circuit converts the 18V alternating current into power supplies of 12V, 5V, 3.3V and 1.8V and provides working power supply for each module of the system.
In the system, the touch screen is connected to the USB interface of the motherboard through the conversion board. The conversion board converts the input signal into a USB signal to be connected with a system host, and controls the performance of the touch screen through corresponding software.
In the above system, B089AW 01V 1 is a color dot matrix liquid crystal display panel composed of a TFT LCD panel, a set of driving circuits, and an LED backlight system. The screen display supports the WSVGA (1024(H) x 600(V)) format and 262k color data drive equipped with an LED backlight driving circuit. All input signals are compatible with the LVDS interface. One of the two display screens is connected to the LVDS interface of the mainboard, and the other display screen is connected to the DVI interface of the mainboard through a DVI-LVDS conversion board. DVI-LVDS completes the conversion of an input DVI signal into an LVDS signal suitable for a liquid crystal display.
In the system, the two GSM modules are GSM/GPRS wireless transceivers of the Zealand T-1008 series. The module mainly comprises a Modem main body part (comprising a chip, a peripheral circuit and the like), a voltage-stabilized power supply and an antenna. The GPRS module is connected to the mainboard through a chip COM port.
An automatic identification method of a handwriting body adopts the system for identification, and is characterized by comprising the following specific operation steps: step 1: inputting data of the pen body; step 1: preprocessing the data of the pen body; and step 3: extracting shape features of the pen body data; and 4, step 4: and recognizing the data of the pen body.
Compared with the prior art, the invention has the following obvious prominent substantive characteristics and obvious advantages:
the handwriting automatic identification method is characterized in that the identification method is handwriting searching, a new polar coordinate feature identification method which takes the handwriting font mass center as a datum point is established, and the identification accuracy rate is extremely high; and writing information is conveniently searched, a complicated paper searching process is omitted, the note picture form is stored in real time, and the storage time is long.
The invention is different from the prior single-screen display, adopts a double-screen display mode, performs related setting in software, and can be set into a double-screen independent display mode and a combined display mode, wherein a main display can be set as a digital display and a secondary display is set as an MID in the double-screen independent display mode, and meanwhile, the setting of screen rotation can also be performed. The changeable display mode can meet the requirements of various occasions, and is convenient to carry without losing visual effect.
The font shape feature extraction algorithm is advanced, is different from the traditional X-Y axis coordinate identification method, innovatively provides a polar coordinate identification method taking the centroid of the font as the center of a circle, solves the problem that the setting of a segmentation algorithm threshold and the individual writing habit are a pair of contradictions which are difficult to solve for Chinese characters with left and right structures or left, middle and right structures, and improves the font identification rate.
Drawings
FIG. 1 is a block diagram of an automatic handwriting recognition system according to the present invention.
FIG. 2 is a flow chart of the automatic handwriting recognition method of the invention.
FIG. 3 is a flow chart of the pen body data preprocessing in FIG. 2.
Fig. 4 is a flow chart of the image binarization in fig. 3.
Fig. 5 is a flow chart of font identification in fig. 1.
The specific implementation mode is as follows:
the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings:
the first embodiment is as follows: referring to FIG. 1, the automatic handwriting pen body recognition system comprises an EMB-4650 motherboard made of Intel Atom Z510P chips by master control, and the extended subinterfaces thereof comprise LVDS interfaces, DVI interfaces, USB interfaces and COM interfaces; the interfaces are respectively connected with the AUO display screen, the DVI-LVDS signal conversion board, the USB controller and the GSM module; therefore, the DVI-LVDS signal conversion board is connected with another AUO display screen, and the USB controller is connected with the touch screen. When a user writes data in the touch screen, the data are transmitted to the EMB-4650 mainboard through the USB controller, and meanwhile, the EMB-4650 mainboard transmits the data to the display screen to realize real-time display; meanwhile, the EMB-4650 mainboard performs recognition algorithm processing on the data, and then sends the processed result to a display screen for displaying, so that a simple human-computer interaction real-time operation effect is achieved. If necessary, the edited font data can be sent to the GSM module through the COM port, so that the real-time sending of the data is realized. The present invention will be described in further detail below with reference to preferred embodiments thereof and the accompanying drawings.
Example two: referring to fig. 2, the implementation method of the automatic handwriting pen body identification system adopts the system for identification, and the specific operation comprises the following steps:
step 1: inputting the data of the pen body: according to the different working principles of touch screens, the touch screens are divided into surface acoustic wave touch screens, resistive touch screens, capacitive touch screens, infrared touch screens and the like. The touch screen used in the invention is a resistance type touch screen. The resistive touch screen is arranged on the surface of the display and mainly comprises two transparent conductive layers, and the two conductive layers are insulated. From the electrical characteristics, each conductive layer is equivalent to a resistor element, and a voltage is applied to two ends of each conductive layer, so that a corresponding relation between the plane position and the voltage drop can be established. When touched, the two conductive layers are contacted at a contact point, the voltage quantity reflecting the plane position is led out by the contact point, and the contact point position is obtained after measurement. The touch screen stores the touch point data in the form of image data for a host to read.
Step 2: preprocessing of the pen volume data, see fig. 3. The flow chart of the data preprocessing of the invention is shown in fig. 4. The main board (1) reads in the stored image data from the touch screen (7) and inputs the image data into the main board (1) register.
Step 2-1: the 256-color bitmap is converted into a gray scale map.
a) Calculating a gray mapping table
From the relation Y =0.299R +0.587G +0.114B between the luminance signal Y and the three primary colors R, G, B, bMap [ i ] = (BYTE) (0.299 lpbmi- > bmicors [ i ]. rgbRed
+0.587 * lpbmi->bmiColors[i].rgbGreen
+0.114 * lpbmi->bmiColors[i].rgbBlue + 0.5);
Where lpbmi is a pointer to the BITMAP INFO structure
b) Updating DIB palette tri-primary components
lpbmi->bmiColors[i].rgbRed = i;
lpbmi->bmiColors[i].rgbGreen = i;
lpbmi->bmiColors[i].rgbBlue = i;
c) Changing the color index of each pixel (i.e., changing to gray values according to a gray mapping table)
for(i = 0; i < lHeight; i++)
{ for(j = 0; j < lWidth; j++)
{ lpSrc = (unsigned char*)lpDIBBits + lLineBytes * (lHeight - 1 - i) + j;
*lpSrc = bMap[*lpSrc];
}
}
(in the above program section lHeight and lWidth are the height and width of the whole image, respectively)
Step 2-2: binarization: in the invention, the gray level image is binarized by adopting a hard threshold value mode, and the program flow chart of the image binarization flow chart is shown in fig. 4. A Threshold value Threshold is set, and the data of the gray image is divided into two parts, namely a pixel group which is greater than or equal to the Threshold value and a pixel group which is smaller than the Threshold value. For example, if the input grayscale image function is f (x, y) and the output binary image function is g (x, y), then
The black and white distribution of the whole image is determined by determining a Threshold value Threshold. It is emphasized that as far as the goal of separating features from the background is to write a special background-removing function to fundamentally separate the colored background and text into two "independent" bitmaps, rather than simplyThe two regions are divided into two regions, which is different from the traditional binarization thought in the processing mode.
Step 2-3: and (3) removing discrete noise: in the writing process, especially when a good article needs a word pouring, people often have the habit of touching a pen on paper from time to time, so that a certain amount of noise is mixed in information stored in real time, additional adverse factors are brought to the accurate handwriting searching later, and therefore denoising processing must be performed firstly.
The basic idea is to scan the whole image and set the pixel points determined as discrete points to be white. Nesting of two functions is used in the operation of removing discrete noise, one function is void removeScatterNoise (HDIB), the function is an outer layer function, the main function is to judge whether a pixel point is a discrete point, if so, the pixel point is set to be white, and a DeleteScatterJudge () function is called when the discreteness is judged; another function is a pool DeleteScaterJudge (), the function adopts the recursion idea, examines eight directions of upper, lower, left, upper, right, left, lower, right, if the color point is black, the function calls itself to recur, the return value is TRUE or FALSE because the function is of the pool type, the return value is obtained in void removeScatterNoise (HDIB hdI, B), if the return value is FALSE, the pixel point is a discrete point, the pixel point is set to be white, thereby realizing the effect of removing discrete noise.
Step 2-4: gradient sharpening: the purpose of the image sharpening process is to make a blurred image clearer, and there are two general methods for image sharpening: one is a differential method and the other is a high-pass filter method. The gradient sharpening adopted by the invention is a common method in a differential method.
Let the image be
Definition of
At the point of
Gradient vector of (2)Comprises the following steps:
from this equation, the conclusion can be drawn: the value of the gradient is
The amount by which the unit distance in the direction of its maximum rate of change increases.
For discrete digital images, the above equation can be rewritten as:
for convenience of calculation, the following approximate calculation formula (1) may also be employed:
if gradient values are directly adopted
To represent an image, i.e. order
=
Then, the above formula (1) shows that: where the image transitions slowly its value is small (corresponding to the image being darker); and where the transformation is fast, such as line profiles, the values are large. The image becomes clear after gradient operation, thereby achieving the purpose of sharpening.
For the adverse factor that the image is dark due to small gradient at the place where the image transformation is slow, the adopted solution is to give a threshold value
If less than the threshold value
Keeping the original gray value unchanged; if greater than or equal to the threshold valueThen assign a value of：
Step 2-5: thinning: the thinning is a process of finding a central skeleton part of an image, wherein the central skeleton part is one of important characteristics for describing geometric and topological properties of the image, and the thinning of the processed image is helpful for highlighting shape characteristics and reducing redundant information.
The refinement algorithm adopted by the invention has the characteristics that: one of an image
Areas, for each point, are labeled the names P1, P2, … P8, where P1 is located at the center. If P1=1 (i.e., black dot), the following 4 conditions if satisfied simultaneously delete P1 (P1 = 0). (ii) 2
NZ(P1)
6；②
= 1; ③ P2P 4P 8=0 or 
1; (iv) P2 × P4 × P6=0 or
1; this is repeated for each point in the image until all points are undeletable.
And step 3: shape feature extraction of the pen body data: the shape characteristics of the handwritten Chinese characters comprise gradient, gravity center shift, character extension and the like, and the characteristics have definite physical meanings and reflect a part of writing styles of writers. In general, such features may be described in terms of moments.
For a frame
Character image of
The p + q order moment is defined as:
wherein,
the physical meaning of each order moment is explained as follows:
representing the degree of extension of the image in the horizontal direction;
representing the degree of extension of the image in the vertical direction;
represents the gradient of the image (>0 means that the image is tilted up to the left,
<0 represents the image tilting up to the right);
representing the degree of shift of the center of gravity of the image in the horizontal direction (
>0 indicates that the center of gravity is to the left,<0 indicates the center of gravity is to the right);
representing the degree of shift of the center of gravity of the image in the vertical direction (>0 means that the center of gravity is on the upper side,<0 represents a center of gravity off);
indicating the degree of equalization of the horizontal stretching of the image (
>0 means that the horizontal extension in the lower part of the image is larger than in the upper part of the image,
<0 indicates that the horizontal stretch in the lower part of the image is smaller than in the upper part of the image);
indicating the degree of equalization of the vertical stretching of the image (
>0 means that the vertical extension of the right part of the image is greater than the left part of the image,
<0 indicates that the vertical extension of the right part of the image is smaller than the left part of the image).
From the central moments calculated above, some of the following normalized shape features can be derived:
a) aspect ratio:
b) font gradient:
(ii) a Wherein
c) Drawing length:
(ii) a Wherein
Is calculated as follows:
d) the stretching degree:
(ii) a Wherein size represents the size of the character lattice, i.e.
The central moments of the third order, since their values may be positive or negative, are in fact composed of two parts, the basis functions of which are positive and negative.
The normalized features extracted by the third-order central moment are as follows:
horizontal offset degree:
vertical offset degree:
③ degree of horizontal stretching and balancing:
vertical stretching equilibrium degree:
for corresponding feature words, a feature vector is obtained
The defined distances are as follows:
and 4, step 4: and (3) identifying pen body data: and establishing a polar coordinate system by taking the mass center of the character as an origin and taking a half of the normalized character height as a radius, and performing sector average block division on the whole circumference, wherein the number n of blocks is variable. Finally, whether the two bitmaps are similar or not is judged, namely whether the current written Chinese character and the character appearing in the past stored notes have certain similarity or not follows the same criterion: and only when the difference value of every two pixel points of each block region in the n block regions corresponding to the two bitmaps is smaller than a preset threshold value, the two regions are considered to be similar. While freezing n to be variable is equivalent to setting the precision of the lookup to be adjustable. Obviously, we consider a search to be a fuzzy search when n =12, and an exact search when n = 360. FIG. 5 is a flow chart of font data recognition. After the font data recognition is completed, the computer displays the recognized font on the screen. After the font edition is finished, the font data can be sent to a receiving station through a wireless GSM network through software control, so that real-time transmission is realized.
Claims (2)
1. An automatic handwriting pen body recognition system comprises an EMB-4650 mainboard (1) which is made by controlling Intel Atom Z510P chips, and is characterized in that the expanded subinterfaces of the mainboard (1) comprise an LVDS interface, a DVI interface, a USB interface and a COM interface; the interfaces are respectively connected with an AUO display screen (2), a DVI-LVDS signal conversion board (3), a USB controller (4) and a GSM module (5); the DVI-LVDS signal conversion board (3) is connected with another AUO display screen (6), and the USB controller (4) is connected with the touch screen (7); when a user writes data in the touch screen, the data are transmitted to the EMB-4650 mainboard through the USB controller, and meanwhile, the EMB-4650 mainboard transmits the data to the display screen to realize real-time display; meanwhile, the EMB-4650 mainboard performs recognition algorithm processing on the data, and then sends the processed result to a display screen for displaying, so that a simple human-computer interaction real-time operation effect is achieved; the edited font data can be sent to the GSM module through the COM port, and real-time data sending is achieved.
2. An automatic handwriting recognition method, which is recognized by the automatic handwriting recognition system of claim 1, and is characterized by comprising the following specific operation steps:
step 1: inputting the data of the pen body: when the touch screen is touched, the touch screen stores the data in the form of image data for a host to read;
step 2: preprocessing the pen body data: the main board 1 reads in stored image data from the touch screen (7) and inputs the image data into a register of the main board (1);
2-1, converting the 256-color bitmap of the data input by the touch screen (7) into a gray scale map according to a gray scale mapping table method;
step 2-2: binarization: realizing binarization on the gray level image by adopting a hard threshold value mode;
step 2-3: and (3) removing discrete noise: denoising noise mixed by touch;
step 2-4: gradient sharpening: carrying out image sharpening by adopting a differential method:
let the image be
Definition of
At the point of
Gradient vector of (2)
Comprises the following steps:
the following results are obtained: the value of the gradient is
The amount by which the unit distance in the direction of its maximum rate of change increases;
for discrete digital images, the above equation is rewritten as:
for convenience of calculation, the following approximate calculation formula (1) may also be employed:
if gradient values are directly adoptedTo represent an image, i.e. order
=
Then, the above formula (1) shows that: where the image transitions slowly its value is small (corresponding to the image being darker); and the values are large at places where the transformation is fast, such as line profiles; the image becomes clear after gradient operation so as to achieve the aim of sharpening;
for the adverse factor that the image is dark due to small gradient at the place where the image transformation is slow, the solution is to give a threshold value
If less than the threshold value
Keeping the original gray value unchanged; if greater than or equal to the threshold valueThen assign a value of
：
Step 2-5: thinning: the process of finding the central skeleton part of one image is specified, the central skeleton part is one of important features for describing the geometric and topological properties of the image, and the thinning of the processed image is helpful for highlighting the shape characteristics and reducing the redundant information content;
the adopted refinement algorithm has the characteristics that: one of an image
Areas, for each point, are labeled the names P1, P2, … P8, where P1 is located at the center; if P1=1, i.e., a black dot, the following 4 conditions, if satisfied simultaneously, delete P1 (P1 = 0); (ii) 2NZ(P1)
6；②= 1; ③ P2P 4P 8=0 or
1; (iv) P2 × P4 × P6=0 or
1; this step is repeated for each point in the image until all points are undeletable;
and step 3: shape feature extraction of the pen body data: the shape characteristics of the handwritten Chinese characters comprise inclination, gravity center offset and character extension, and the characteristics are described by moments;
for a frame
Character image ofThe p + q order moment is defined as:
wherein,each ofThe physical meaning of the order moments is explained below:
representing the degree of extension of the image in the horizontal direction;
representing the degree of extension of the image in the vertical direction;representing the inclination of an image
>0 means that the image is tilted up to the left,
<0 represents the image tilting up to the right;
representing the degree of shift of the center of gravity of an image in the horizontal direction
>0 indicates that the center of gravity is to the left,<0 indicates the center of gravity is to the right;
representing the degree of shift of the center of gravity of an image in the vertical direction
>0 means that the center of gravity is on the upper side,
<0 represents a center of gravity off;
indicating the degree of equalization of the horizontal stretching of the image,
>0 means that the horizontal extension in the lower part of the image is larger than in the upper part of the image,
<0 indicates that the horizontal stretch in the lower part of the image is smaller than in the upper part of the image;
indicating the degree of equalization of the vertical stretching of the image,>0 means that the vertical extension of the right part of the image is greater than the left part of the image,
<0 indicates that the vertical extension of the right part of the image is smaller than the left part of the image;
from the central moments calculated above, some normalized shape features are derived:
aspect ratio:
font gradient:
(ii) a Wherein
Drawing length:(ii) a Wherein
Is calculated as follows:
the stretching degree:
(ii) a Wherein size represents the size of the character lattice, i.e.
The central moments of the third order, since their values may be positive or negative, are in fact composed of two parts, the basis functions of which are positive and negative;
horizontal offset degree:
vertical offset degree:
③ degree of horizontal stretching and balancing:
vertical stretching equilibrium degree:
for corresponding feature words, a feature vector is obtained
The defined distances are as follows:
and 4, step 4: and (3) identifying pen body data: establishing a polar coordinate system by taking the centroid of the character as an origin and half of the normalized height of the character as a radius, and performing sector average partitioning on the whole circumference, wherein the number n of blocks is variable;
finally, whether the two bitmaps are similar or not is judged, namely whether the current written Chinese character and the character appearing in the past stored notes have certain similarity or not follows the same criterion: only when the difference value of every two pixel points of each block area in n block areas corresponding to the two bitmaps is smaller than a preset threshold value, the two bitmaps are regarded as similar; freezing n to be variable is equivalent to setting the search precision to be adjustable;
obviously, we consider a search to be a fuzzy search when n =12, and a precise search when n = 360; after the font data recognition is completed, the computer displays the recognized font on the screen.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011103604419A CN102541347A (en) | 2011-11-15 | 2011-11-15 | Automatic identification system and method of handwriting Chinese character |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011103604419A CN102541347A (en) | 2011-11-15 | 2011-11-15 | Automatic identification system and method of handwriting Chinese character |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102541347A true CN102541347A (en) | 2012-07-04 |
Family
ID=46348375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011103604419A Pending CN102541347A (en) | 2011-11-15 | 2011-11-15 | Automatic identification system and method of handwriting Chinese character |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102541347A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105094383A (en) * | 2014-05-13 | 2015-11-25 | 联想（新加坡）私人有限公司 | Smart pen pairing and connection |
| CN107918935A (en) * | 2017-12-05 | 2018-04-17 | 深圳市北电仪表有限公司 | The images match cutter device and cutting method of embedded system |
| WO2018103226A1 (en) * | 2016-12-07 | 2018-06-14 | 广州视源电子科技股份有限公司 | Method and device for generating handwriting format document on the basis of picture |
| CN110737364A (en) * | 2019-11-06 | 2020-01-31 | 广州炫视智能科技有限公司 | Control method for touch writing acceleration under android systems |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN85100085A (en) * | 1985-04-01 | 1986-07-16 | 清华大学 | Recognition method of printed Chinese character recognition device |
| CN1128423C (en) * | 1999-04-21 | 2003-11-19 | 中国科学院自动化研究所 | Handwriting identifying method based on grain analysis |
-
2011
- 2011-11-15 CN CN2011103604419A patent/CN102541347A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN85100085A (en) * | 1985-04-01 | 1986-07-16 | 清华大学 | Recognition method of printed Chinese character recognition device |
| CN1128423C (en) * | 1999-04-21 | 2003-11-19 | 中国科学院自动化研究所 | Handwriting identifying method based on grain analysis |
Non-Patent Citations (8)
| Title |
|---|
| MILAN SONKA等: "《图像处理、分析与机器视觉》", 31 January 2011, 清华大学出版社 * |
| 何斌等: "《Visual C++ 数字图像处理》", 30 April 2001, 人民邮电出版社 * |
| 唐伟成: "手写英文字符识别系统", 《中国优秀硕士学位论文全文数据库（信息科技辑）》 * |
| 李小泉: "自动检测系统关键技术研究", 《武汉理工大学硕士学位论文》 * |
| 杨阳等: "基于图像分析的滚动轴承表面缺陷识别技术研究", 《华东交通大学学报》 * |
| 陈维克等: "印鉴识别方法和技术研究", 《中国水运》 * |
| 黄佳森: "实现个人手写笔体检索的全新算法——质心圆周分块算法", 《信息系统工程》 * |
| 黄佳森等: "基于Intel Menlow平台EMB－4650开发板的即写即发、个人双屏触控PDA实现", 《信息与电脑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105094383A (en) * | 2014-05-13 | 2015-11-25 | 联想（新加坡）私人有限公司 | Smart pen pairing and connection |
| CN105094383B (en) * | 2014-05-13 | 2021-05-11 | 联想（新加坡）私人有限公司 | Smart pen pairing and connection |
| WO2018103226A1 (en) * | 2016-12-07 | 2018-06-14 | 广州视源电子科技股份有限公司 | Method and device for generating handwriting format document on the basis of picture |
| CN107918935A (en) * | 2017-12-05 | 2018-04-17 | 深圳市北电仪表有限公司 | The images match cutter device and cutting method of embedded system |
| CN107918935B (en) * | 2017-12-05 | 2022-03-08 | 深圳市北电仪表有限公司 | Image matching cutting device and cutting method of embedded system |
| CN110737364A (en) * | 2019-11-06 | 2020-01-31 | 广州炫视智能科技有限公司 | Control method for touch writing acceleration under android systems |
| CN110737364B (en) * | 2019-11-06 | 2023-12-12 | 广州炫视智能科技有限公司 | Control method for touch writing acceleration under android system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104408449B (en) | Intelligent mobile terminal scene literal processing method | |
| CN108647681A (en) | A kind of English text detection method with text orientation correction | |
| CN103916647B (en) | Gesture pre-processing of video stream with hold-off period to reduce platform power | |
| CN101706875B (en) | Hand-held laser code-jetting character recognizer under complex background | |
| CN104751187A (en) | Automatic meter-reading image recognition method | |
| CN107346420A (en) | Text detection localization method under a kind of natural scene based on deep learning | |
| CN113486828B (en) | Image processing method, device, equipment and storage medium | |
| CN103778250A (en) | Implement method for Chinese wubi cursive script dictionary query system | |
| CN101976114B (en) | System and method for realizing information interaction between computer and pen and paper based on camera | |
| CN108958636B (en) | Intelligent copybook device and copybook writing detection method | |
| CN109033954A (en) | A kind of aerial hand-written discrimination system and method based on machine vision | |
| CN106339707A (en) | Instrument pointer image recognition method based on symmetrical characteristics | |
| Tian et al. | Natural scene text detection with MC–MR candidate extraction and coarse-to-fine filtering | |
| CN103065146A (en) | Character recognition method for power communication machine room dumb equipment signboards | |
| CN110866900A (en) | Water body color identification method and device | |
| CN102541347A (en) | Automatic identification system and method of handwriting Chinese character | |
| CN107122775A (en) | A kind of Android mobile phone identity card character identifying method of feature based matching | |
| CN105930497A (en) | Image edge and line feature based three-dimensional model retrieval method | |
| CN104636309B (en) | Matrix recognition methods based on machine vision | |
| CN109543525B (en) | Table extraction method for general table image | |
| CN109241962A (en) | A kind of character identifying method and device | |
| CN201654804U (en) | Character recognizer | |
| CN104809721B (en) | A kind of caricature dividing method and device | |
| CN114596214A (en) | Face whitening image processing method, device, medium and equipment | |
| CN106547891A (en) | For the quick visualization method of the pictured text message of palm display device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20120704 |