JP2002279351A - Character recognition device, method, and program, and recording medium computer-readable the program recorded - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a character recognition device for simultaneously recognizing character codes and fonts, which is easily adapted to utilization environment, and highly precisely recognizing characters. SOLUTION: This character recognition device 1 detects the font incorporated in a personal computer 3 and a printer 4, obtains character image data of respective characters of the font detected from the personal computer 3 and the printer 4, prepares a reference pattern of the respective characters of the font detected, by using the character image data, and prepares an identification dictionary for each font detected by registering the reference pattern. The character code and the font of the character pattern recognized from a document image data obtained from a scanner 2 are determined using the identification dictionary for every font.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

[0001] The present invention relates to a character recognition device. More specifically, the present invention is a character recognition device capable of recognizing a font simultaneously with a character code, and performing highly accurate character recognition easily adapted to a use environment.

[0002]

2. Description of the Related Art In a conventional character recognition apparatus, an identification dictionary used for character pattern identification includes a plurality of character dictionaries in order to perform stable character recognition in response to differences in character patterns due to fonts, fluctuations such as blurring and crushing. Of the typical fonts (usually, serif, sans-serif, and monospace-based fonts).

On the other hand, there has been proposed a character recognition apparatus that uses an identification dictionary for each font created based on the feature amount of a single font (Japanese Patent Laid-Open No. 11-85908). In such a device, the font can be recognized simultaneously with the character code, and a higher recognition rate can be obtained for fonts belonging to the identification dictionary than in the case of using the identification dictionary in which the characteristic amounts of a plurality of fonts are averaged. There is an advantage that it can be obtained.

[0004] On the other hand, however, there is a disadvantage that the identification rate is reduced for fonts other than those relating to the identification dictionary owned by the user. Therefore, in order to cope with various use environments, it is necessary to prepare a large number of font-specific dictionaries, which is expensive, and if the user specifies a font to be recognized in advance, the operation becomes complicated, If the font is automatically recognized, the processing becomes extremely complicated. Furthermore, since there are many types of fonts, it is actually difficult to prepare all identification dictionaries, and there is a problem that it is not possible to cope with an environment using a special font.

[0005]

SUMMARY OF THE INVENTION The present invention has been made in consideration of the above-mentioned problems of the prior art, and has as its object to recognize fonts simultaneously with character codes, and to simplify the use environment. It is an object of the present invention to provide a character recognition device capable of adaptively performing highly accurate character recognition.

[0006]

The above object of the present invention is achieved by the following means.

(1) Font detecting means for detecting a font incorporated in a connected device, and character image data obtaining means for obtaining character image data for each character of the font detected by the font detecting device from the connected device. Registering and identifying the standard pattern created by the standard pattern creating unit, which creates a standard pattern for each character of the font detected using the character image data acquired by the character image data acquiring unit; A character recognition apparatus comprising: an identification dictionary creation unit that creates a dictionary; and a character identification unit that determines a character pattern character code and a font using the identification dictionary created by the identification dictionary creation unit.

(2) Font detecting means for detecting a font incorporated in the connected equipment, and character image data obtaining means for obtaining character image data for each character of the font detected by the font detecting means from the connected equipment. A standard pattern creating unit that creates a standard pattern for each character of the font detected using the character image data acquired by the character image data acquiring unit; and a standard pattern created by the standard pattern creating unit. Identification dictionary creating means for creating the identified dictionary for each font, and character identification means for determining the character code and font of the character pattern using the identification dictionary for each font created by the identification dictionary creating means. Character recognition device characterized by the above-mentioned.

(3) The character recognition device according to (2), wherein the character identification means sets a character code of a standard pattern whose similarity is equal to or more than a predetermined threshold value as a character code of the character pattern. apparatus.

(4) The character recognition device according to (2) or (3), wherein the character identification unit determines the priority of the identification dictionary in the order of the identification frequency.

(5) The character identification means determines a font for each of the character blocks by using a font of an identification dictionary having the highest identification frequency as a font of a character block. Character recognition device.

(6) detecting a font incorporated in the connected device, obtaining character image data for each character of the font detected from the connected device, and detecting the character image data; Creating a standard pattern for each character of the font; registering the standard pattern to create an identification dictionary; and determining the character code and font of the character pattern using the identification dictionary. Character recognition method characterized by the following.

(7) A step of detecting a font incorporated in the connected device, a step of acquiring character image data for each character of the font detected from the connected device, and a step of detecting using the character image data Creating a standard pattern for each character of the font; registering the standard pattern to create an identification dictionary for each detected font; and character code and font for the character pattern using the identification dictionary for each font. Determining a character recognition method.

(8) A procedure for detecting a font incorporated in the connected device, a process for acquiring character image data for each character of the font detected from the connected device, and a process for detecting using the character image data A procedure for creating a standard pattern of each character of a font, a procedure for registering the standard pattern and creating an identification dictionary, and a procedure for determining a character code and a font of the character pattern using the identification dictionary, The program to be executed.

(9) A procedure for detecting a font incorporated in the connected device, a process for acquiring character image data for each character of the font detected from the connected device, and a process for detecting the character image data. A procedure for creating a standard pattern for each character of the font, a procedure for registering the standard pattern and creating an identification dictionary for each detected font, and a character code and font for the character pattern using the identification dictionary for each font And a program for causing a computer to execute the procedure.

(10) A procedure for detecting a font incorporated in the connected device, a procedure for acquiring character image data for each character of the font detected from the connected device, and a process for detecting the character image data. A procedure for creating a standard pattern of each character of a font, a procedure for registering the standard pattern and creating an identification dictionary, and a procedure for determining a character code and a font of the character pattern using the identification dictionary, A computer-readable recording medium on which a program to be executed is recorded.

(11) A procedure for detecting a font incorporated in the connected device, a procedure for acquiring character image data for each character of the font detected from the connected device, and a process for detecting using the character image data A procedure for creating a standard pattern for each character of the font, a procedure for registering the standard pattern and creating an identification dictionary for each detected font, and a character code and font for the character pattern using the identification dictionary for each font And a computer-readable recording medium on which a program for causing a computer to execute is determined.

[0018]

Embodiments of the present invention will be described below in detail with reference to the drawings.

FIG. 1 is a block diagram showing the overall configuration of a character recognition system including a character recognition device according to an embodiment of the present invention. The character recognition system includes a character recognition device 1
, A scanner 2 as an image reading device, a personal computer 3 as an image processing device, and a printer 4 as an image forming device, which are communicably connected via a network 5. The type and number of devices connected to the network 5 are not limited to the example shown in FIG.

Next, a description will be given of the configuration of each of the above-described devices. For the portions having the same functions in each of the devices, the description will be given only for the first time in order to avoid duplication of description, and the description will be omitted for the second and subsequent times. .

FIG. 2 is a block diagram showing an example of the configuration of the character recognition device 1 according to the present embodiment. The character recognition device 1 is a computer, and as shown in FIG.
1, a ROM 12, a RAM 13, a hard disk 14, a display 15, an input device 16, a network interface 17, and a bus 18.

The CPU 11 performs various processes of control and calculation. The ROM 12 stores various programs and data.
The RAM 13 temporarily stores programs and data as a work area. The hard disk 14 stores various programs and data. The display 15 performs various displays. The input device 16 is a keyboard, a mouse, or the like,
Used to make various inputs. The network interface 17 is an interface for connecting to a network and communicating with other devices on the network.
The above components are interconnected by a bus 18 for exchanging signals. In the present embodiment, the computer 1 performs a predetermined operation described later. A program for controlling the operation of the computer 1 for this purpose is stored in the ROM 12 or the hard disk 14.

The scanner 2 has a function of reading a document set at a predetermined position, obtaining image data (bitmap data), and outputting the image data to another device via a network.

The personal computer 3 has the same configuration as the character recognition device 1 as shown in FIG. In the personal computer 3, a font for causing a character image to be formed by an image forming apparatus such as a printer or a display as an image processing apparatus is incorporated.

The printer 4 prints out a print image (image data) based on a print job. Printer 4
When a print job includes a control language, it has a function of interpreting the rasterization and performing rasterization to create a print image, and fonts necessary for this are incorporated in the printer 4.

The network 5 includes a LAN connecting computers and network devices according to standards such as Ethernet (registered trademark), Token Ring, and FDDI, and an L
It is composed of a WAN or the like in which ANs are connected by a dedicated line.

Next, an outline of the operation of the character recognition device 1 in this embodiment will be described. FIG. 3 is a flowchart illustrating the overall procedure of the character recognition process of the character recognition device 1 according to the present embodiment. First, the character recognition device 1 displays an input screen for a new identification dictionary creation command on the display 15 and waits for a user to input a new identification dictionary creation command (NO in S101). The user operates the input device 1
6 to input a new creation command of the identification dictionary to the character recognition device 1. When the character recognition device 1 receives an input of a command to newly create an identification dictionary from the user (S10)
(1) (YES), an identification dictionary creation process is performed (S10).
2).

FIG. 4 is a flowchart showing the procedure of the identification dictionary creating process of the character recognition device 1 according to the present embodiment. In the process of creating the identification dictionary, the character recognition device 1
First, the device connected to the character recognition device 1 is detected via the network interface 17 and the network 5 (S201). When a connected device is detected on the network 5 (YES in S202), it is detected whether or not there is a font incorporated in the detected device (S203). For example, in the case of a personal computer, an installed font is owned by an OS (operating system), and font data is held in a specific directory used by the OS on a hard disk. In the case of a printer that supports a page description language such as PostScript (Adobe Systems Incorporated), the printer has a font. The printer interprets the page description language and converts the font based on font data stored on a hard disk or the like. Rasterize. The character recognition device 1 detects a font incorporated in the device by searching a specific directory such as a hard disk of these devices and detecting such font data. When a font incorporated in the detected device is detected, and the detected font is a character for which an identification dictionary has not been created yet (S2).
04, YES), transmits a character image data transfer request to transfer the character image data (bitmap data) for all the characters of the detected font to the device via the network interface 17 and the network 5. (S205).

FIG. 5 shows that the character recognition device 1
The case where the PC 3 on the PC 3 is detected, the font data is detected by searching a predetermined directory on the hard disk of the PC 3 and a transfer request of the character image data of the font related to the detected font data is transmitted to the PC 3 4 is a flowchart showing the operation of the personal computer 3. The personal computer 3 waits until a character image data transfer request is received from the character recognition device 1 (N in S301).
O), upon receiving a character image data transfer request from the character recognition device 1 (YES in S301), prepares character image data for all characters of the font corresponding to the transfer request. Here, there are two types of fonts, a bitmap font that expresses the shape of a character by a set of dots, and an outline font in which the outline (outline) of the character is converted into data. Bitmap fonts consist of font image data themselves, whereas outline fonts contain font data.
It has font metric data describing information on the width and height of the character, and outline data describing information for calculating the outline of the character, and rasterizes to the required character size based on these data. This is for obtaining character image data. Therefore, when the font related to the transfer request is a bitmap font (S30)
2), the character image data, which is the font data for each character, is transmitted to the character recognition device 1 as it is, and if the font requested for the transfer request is an outline font (YES in S302), the font data is converted to the font data for each character. Rasterized to a certain size based on (S
303), and transmits the obtained character image data to the character recognition device 1.

When the printer 4 is the device that requests the transfer of the character image data, the font incorporated in the printer is an outline font.
Operate sequentially in accordance with the procedure for receiving a transfer request for character image data (S301), the procedure for rasterizing processing (S303), and the procedure for character image data transfer (S304) in FIG. If the character recognition device 1 itself incorporates a font as an image processing device, it treats itself as one of the connected devices, and performs the above-described font detection procedure (S203) and rasterization processing procedure (S30).
It operates sequentially according to 3).

In FIG. 4, the character recognition device 1 waits until the character image data is received from the device via the network 5 and the network interface 17 (NO in S206), and receives the character image data from the device. Then (S206: YES), the received character image data is stored in a predetermined directory of the hard disk 14. Next, a standard pattern is created for all characters of the font using the received character image data (S207), and an identification dictionary of the font is created by registering the created standard pattern in a dictionary (S20).
8). Here, the method of creating the identification dictionary differs depending on the method of character recognition. In the case of the method based on feature amount extraction, a feature amount is calculated by a predetermined method from the received character image data of each character, and this is registered as a standard pattern of each character. As a specific method of feature amount extraction, there is a method of extracting the inclination of a character line, the number of loops, the line width, the character area, and the like as the extraction amount. In the case of the method based on pattern matching, the received character image data of each character is registered as it is as a standard pattern of each character. However, in order to cope with misregistration, inclination, minute size differences, etc. of the character pattern to be identified, character image data in which characters are blurred to some extent from the received character image data is created and registered as a standard pattern. There may be. The created identification dictionary of the font is stored in a predetermined directory of the hard disk 14.

The character recognition device 1 continues to detect other fonts incorporated in the device (S203), and if any of them has not created an identification dictionary (YE in S204).
S), the procedure for creating the identification dictionary of the detected font (S2)
05 to S208) are repeated to create an identification dictionary for each detected font. On the other hand, if there is no font incorporated in the device or if all of the incorporated fonts have already created the identification dictionary (S2
04 (NO in step S2), another connected device is detected (S2).
01), if another connected device is detected (YES in S202), the above-described font detection procedure and the procedure for creating the identification dictionary of the detected font (S203 to S208) are repeated, and the identification dictionary for each detected font is determined. Create
If no other connected device is detected (N in S202)
O), the identification dictionary creation process ends.

In FIG. 3, when the above-described identification dictionary creation processing is completed, the character recognition apparatus 1 displays an input screen for a document reading command on the display 15 and waits until a user inputs a document reading command (S103). N
O). The user inputs a document reading command to the character recognition device 1 by operating the input device 16. When a document reading command is input by the user (YES in S103), the character recognition device 1
A document reading command is transmitted to the scanner 2 via the network 7 and the network 5 (S104). When the scanner 2 receives the document reading command from the character recognition device 1, the scanner 2 reads the document document set at a predetermined reading position and transmits the obtained image data to the character recognition device 1. The character recognition device 1 waits until image data is received from the scanner 2 (NO in S105), and receives image data from the scanner 2 via the network 5 and the network interface 17 (YES in S105). Is stored in a predetermined directory on the hard disk 14.

Next, a character area and a non-character area included in the received image data are determined, and the image data is separated into a character area and a non-character area (S106). In this processing, a character area in the original image data and a non-character area such as a photograph or a figure are distinguished from each other by using a brightness histogram of a minute area of the image data or a characteristic of a spectrum obtained by frequency decomposition. Cut out the character area. The cut-out image data of the non-character area is temporarily stored in a predetermined directory of the hard disk 14 for output together with the character code data recognized later. At this time, if necessary, the image data of the non-character area may be subjected to processing such as image correction such as a smoothing filter, change in resolution, and compression. Further, the image data of only the generated character area may be subjected to an image correction by a filtering process as necessary so that a collapsed character or a blurred character does not occur.

Further, a pre-character recognition process is performed on the image data of only the character area (S107). That is,
Since character recognition is performed using monochrome binary image data, in this process, color image data displayed in RGB, Lab, or the like is converted into monochrome binary image data in which characters have a black background on white. Further, if necessary, the generated monochrome binary image data is subjected to processes such as noise removal of isolated points and the like and image tilt correction.

Next, layout analysis is performed on the monochrome binary image data obtained by the character recognition preprocessing (S108). In the processing, the character line configuration and the column are detected using the histogram of the projected image for the character region in the image, and the character region is recognized as a plurality of character blocks. Here, a character block refers to a character area that is divided into paragraphs, separated by columns, blank lines, line feeds, and the like. One character block is also formed when the character sizes are different.

Further, lines and characters are sequentially cut out from the character blocks recognized by the layout analysis (S109), and character recognition processing is performed on the cut-out character image data (S110). The circumscribed rectangle data of each cut-out character image is stored in a predetermined directory of the hard disk 14 as position data of each character.

FIG. 6 is a flowchart showing the procedure of the character recognition process of the character recognition device 1 according to the present embodiment.
In the procedure of the character recognition process, the character recognition device 1
First, one of the character blocks recognized by the layout analysis is selected (S401), a line is cut out from the character block, and a character is cut out from the line (S402).

Next, the feature amount is extracted from the character pattern relating to the cut-out character (S403). The extraction of the feature amount is performed by the same method as that used when creating the standard pattern of each character registered in the identification dictionary in the procedure for creating the standard pattern of the identification dictionary creation process (S207). Also, in the standard pattern creation procedure (S207) of the identification dictionary creation processing, when a method based on pattern matching is used as a method for character recognition instead of a method based on feature amount extraction, a character pattern pertaining to a cut character is used as a standard. Since the comparison is made with the pattern, the procedure of extracting the characteristic amount of the character pattern (S403) is omitted.

Further, an identification dictionary to be used for the identification processing is selected according to the priority (S404), and the hard disk 14
From the RAM 13. The priority order is determined according to a procedure (S408) for determining the priority order of the identification dictionary, which will be described later. However, only the first time, a default priority or a random priority is used.

Then, an identification process is performed in which the feature amount extracted from the character pattern is compared with a standard pattern of each character registered in the selected identification dictionary (S405). That is, in the identification processing, the similarity between the feature amount extracted from the character pattern and the standard pattern of each character registered in the selected identification dictionary is sequentially calculated, and when the similarity is equal to or greater than a predetermined threshold value. (S4)
(YES of 06), the character code of the standard pattern is determined as the character code of the character pattern, and the character code data is stored in a predetermined directory of the hard disk 14 (S407). As a method of calculating the similarity used in the identification processing, a method using a city block distance, a method using a Euclidean distance, a method using a linear identification function,
A subspace method, a Bayes identification method, and the like can be given. If there is no standard pattern in which the similarity is equal to or greater than the threshold value in the selected identification dictionary (NO in S406), the identification dictionaries are sequentially arranged in order of priority until a standard pattern in which the similarity is equal to or greater than the threshold value is found. The selection is performed again, and the above-described procedure of the identification processing is repeated (S404 to S406), and the character code of the character pattern is determined.

Next, the font of the identification dictionary used for determining the character code is set as a font candidate of the character pattern, and the font candidate data is stored in a predetermined directory of the hard disk 14 (S408). Further, the font candidate data stored in the hard disk 14 is analyzed, and the priorities of the identification dictionaries corresponding to the respective fonts are determined and updated according to the frequency of the font candidates (S409). Further, the font size is calculated from the character pattern, and the font size data is stored in a predetermined directory of the hard disk 14 (S410).

After repeating the above-described series of character recognition processing (S402 to S411) for the character patterns of all the characters cut out from the selected character block (S411).
YES), the font related to the identification dictionary having the first priority is determined as the font of the character block, and the font type data is stored in a predetermined directory of the hard disk 14 (S408). Then, the above-described series of character recognition processing (S401 to S412) is repeated for all the character blocks recognized by the layout analysis, and the character recognition processing ends (YES in S413).

In the above-described identification processing procedure (S405 and S406), the similarity is calculated when a standard pattern whose similarity with the feature quantity extracted from the character pattern is equal to or larger than a predetermined threshold value is found. Although the processing is ended, the similarity between all the identification dictionaries and all the standard patterns is calculated, and the procedure for updating the priority of the identification dictionaries (S
In 409), the priorities of the identification dictionaries for the standard pattern may be determined in descending order of similarity. Further, in such a method of calculating the similarity with all the standard patterns of all the identification dictionaries, if two or more standard patterns having a similarity of not less than a predetermined threshold value are found, the spelling of the preceding and following characters is performed. A check may be made and the character code that forms the word in the word dictionary may be adopted. Further, in the procedure for determining the font of the character block (S408), the font of the most frequently used identification dictionary is used as the font of the character block regardless of the character code. A code may be weighted to determine the font of the character block.

In FIG. 3, when the character recognition process is completed, the character recognition device 1 performs color recognition of the character cut out in the character recognition process, and stores the obtained character color data in a predetermined directory on the hard disk 14. (S110). The character color recognition process is performed by reading color data such as RGB and Lab of a pixel corresponding to the character in the original image data, and calculating an average value of all pixels corresponding to the character. The distinction between text and background pixels is
Using the monochrome binary image data created in the character recognition preprocessing, black pixels in a circumscribed rectangle of each character are set as character pixels, and white pixels are set as background pixels.

Then, the procedure of the character recognition processing (S10)
An output file is created from the character code data obtained in 9) and the image data of the non-character area obtained in the character / non-character area separation procedure (S106) (S11).
1). That is, the character code data and the image data in the non-character area are read out from the hard disk 14 onto the RAM 13 and converted into a predetermined output file format. Further, the font type data and the font type data obtained in the character recognition processing procedure (S109) are obtained. The font size and the character color data obtained in the character color recognition procedure (S110) are read from the hard disk 14, added to the character code data as character attribute data, and obtained in the character recognition processing procedure (S109). Based on the character position data, the image data is arranged together with the image data of the non-character area. The created output file is stored on the hard disk 14
In a predetermined directory, or output to another device such as the personal computer 3 or the printer 4 via the network interface 17 and the network 5.

In the above embodiment, in the character recognition processing, the identification dictionary creation processing (S102, S201 to S208) is performed each time.
However, apart from the character recognition processing, the identification dictionary creation processing may be performed only for the first time, or at regular intervals, or only when there is a change in the connection environment. Good.

In the above-described embodiment, an identification dictionary is created for each detected font, and character recognition is performed using the identification dictionary. However, by default, a normal identification dictionary, that is, a feature amount of a plurality of fonts is used. When character recognition is performed using the identification dictionary created by averaging and the recognition rate is low,
That is, when the average value of the similarities is equal to or less than a predetermined value in the identification processing, the above-described identification dictionary for each detected font may be used. Thereby, when a special font that cannot be recognized by the default identification dictionary is used in the environment of the character recognition system, the identification dictionary of the detected font is used only for input data related to the font, and other input data is used. By using the default identification dictionary, the recognition rate as a whole can be improved.

Further, in the above embodiment, a separate identification dictionary is created for each detected font.
A standard pattern obtained from character image data of all characters of all detected fonts may be registered in one identification dictionary to create an identification dictionary.

In the above embodiment, the character recognition device 1, the scanner 2, the computer 3, and the printer 4
Although the configuration was connected to each other via the network 5, the character recognition device 1 and the scanner 2 or the character recognition device 1 and the printer 4 are connected to the RS-232C, USB, or IEEE.
Serial interface such as E1394, SCSI, I
Parallel interface such as EEE1284, Blue
Bluetooth (Bluetooth), IEEE802.1
1. The configuration may be a local connection using a wireless communication interface such as HomeRF, IrDA, or the like.

The character recognizing device 1 according to the present invention has, in addition to the configuration described in the above embodiment, a configuration having a document reading means or a printing means, such as a scanner having a character recognizing function, a digital copier, a facsimile machine, or the like. It can be a functional peripheral device (MFP).

The character recognizing device and the character recognizing method according to the present invention can be realized not only by a dedicated hardware circuit for executing the above-mentioned procedures but also by a CPU executing a predetermined program describing the above-mentioned procedures. Can be realized. When the present invention is realized by the latter, the above-mentioned predetermined program for operating the character recognition device can be provided by a computer-readable recording medium such as a floppy (registered trademark) disk or a CD-ROM. In this case, the program recorded on the computer-readable recording medium is usually transferred to a ROM or a hard disk and stored. This program may be provided, for example, as independent application software, or may be incorporated in the software of the character recognition device as a function of the device.

[0053]

As described above, according to the present invention, the font used in the environment in which the character recognition device is used is automatically detected, and an identification dictionary is created for each font to perform character recognition. Compared with the case of using an identification dictionary in which the characteristic amounts of a plurality of fonts are averaged, font recognition can be performed simultaneously with character codes, and a higher recognition rate can be achieved.

Further, since an identification dictionary is created only for fonts existing in the environment of use, highly accurate character recognition can be performed even if identification dictionaries are not prepared for many fonts in advance.

Furthermore, even in an environment where a special font is used, an identification dictionary for the font is automatically created, so that highly accurate character recognition can be easily performed and adapted to the environment.

[Brief description of the drawings]

FIG. 1 is a block diagram showing an overall configuration of a character recognition system including a character recognition device according to an embodiment of the present invention.

FIG. 2 is a block diagram illustrating an example of a configuration of the character recognition device 1 according to the embodiment.

FIG. 3 is a flowchart illustrating an overall procedure of a character recognition process of the character recognition device 1 according to the embodiment.

FIG. 4 is a flowchart illustrating a procedure of an identification dictionary creation process of the character recognition device 1 according to the embodiment.

FIG. 5 is a flowchart illustrating a procedure of a character image data transfer process of the personal computer 3 according to the present embodiment.

FIG. 6 is a flowchart illustrating a procedure of a character recognition process of the character recognition device 1 according to the embodiment.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... Character recognition device, 11 ... CPU 12 ... ROM 13 ... RAM 14 ... Hard disk 15 ... Display 16 ... Input device 17 ... Network interface 18 ... Bus 2 ... Scanner, 3 ... Personal computer, 4 ... Printer, 5 ... Network.

Claims (11)

[Claims] 1. Font detecting means for detecting a font incorporated in a connected device; character image data obtaining means for obtaining character image data for each character of a font detected by the font detecting means from the connected device; A standard pattern creating means for creating a standard pattern of each character of a font detected using the character image data acquired by the character image data acquiring means; and an identification dictionary for registering the standard pattern created by the standard pattern creating means. A character recognition device comprising: an identification dictionary creating unit that creates a character string; and a character identification unit that determines a character code and a font of a character pattern using the identification dictionary created by the identification dictionary creating unit. 2. Font detecting means for detecting a font incorporated in a connected device; character image data obtaining means for obtaining character image data for each character of the font detected by the font detecting means from the connected device; A standard pattern creating unit that creates a standard pattern for each character of the font detected using the character image data acquired by the character image data acquiring unit; and a standard pattern created by the standard pattern creating unit registered and detected. Identification dictionary creating means for creating an identification dictionary for each font, and character identification means for determining a character pattern character code and a font using the identification dictionary for each font created by the identification dictionary creating means. Character recognition device. 3. The character code of a standard pattern whose similarity is equal to or greater than a predetermined threshold value as the character code of the character pattern.
The character recognition device according to 1. 4. The apparatus according to claim 2, wherein the character identification means determines the priority of the identification dictionary in the order of the identification frequency.
Or the character recognition device according to 3. 5. The character recognition apparatus according to claim 2, wherein said character identification means determines a font for each character block using a font of an identification dictionary having the highest identification frequency as a font of a character block. apparatus. 6. A step of detecting a font incorporated in the connected device; a step of obtaining character image data for each character of the font detected from the connected device; and a font detected using the character image data. Creating a standard pattern of each character, registering the standard pattern to create an identification dictionary, and determining a character code and a font of the character pattern using the identification dictionary. Character recognition method to be characterized. 7. A step of detecting a font incorporated in the connected device; a step of obtaining character image data for each character of the font detected from the connected device; and a font detected using the character image data. Creating a standard pattern of each character, creating an identification dictionary for each detected font by registering the standard pattern, and using the identification dictionary for each font to determine a character pattern character code and a font. Determining a character. 8. A procedure for detecting a font incorporated in a connected device, a procedure for acquiring character image data for each character of the font detected from the connected device, and a font detected using the character image data Executing a procedure of creating a standard pattern of each character of the above, a procedure of registering the standard pattern and creating an identification dictionary, and a procedure of determining a character code and a font of the character pattern using the identification dictionary. Program to let you. 9. A procedure for detecting a font embedded in a connected device, a procedure for acquiring character image data for each character of the font detected from the connected device, and a font detected using the character image data A procedure for creating a standard pattern of each character, a procedure for registering the standard pattern and creating an identification dictionary for each detected font, and using the identification dictionary for each font to determine a character pattern character code and a font. A program for causing a computer to execute a procedure for determining. 10. A procedure for detecting a font incorporated in a connected device, a procedure for acquiring character image data for each character of the font detected from the connected device, and a font detected using the character image data Executing a procedure of creating a standard pattern of each character of the above, a procedure of registering the standard pattern and creating an identification dictionary, and a procedure of determining a character code and a font of the character pattern using the identification dictionary. A computer-readable recording medium on which a program for causing a computer to record is recorded. 11. A procedure for detecting a font incorporated in a connected device, a procedure for acquiring character image data for each character of the font detected from the connected device, and a font detected using the character image data A procedure for creating a standard pattern of each character, a procedure for registering the standard pattern and creating an identification dictionary for each detected font, and using the identification dictionary for each font to determine a character pattern character code and a font. A computer-readable recording medium on which a program for causing a computer to execute the determining procedure is recorded.