JPH103516A - Method and device for processing information - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve the efficiency of checking and modifying work for character recognition processing by specifying a required area and changing a language mode attribute displayed in accordance with a language mode attribute instruction. SOLUTION: A document picture is inputted by a scanner 4 or the like. A preprocessing part 7 analyzes the input picture, divides the picture into a plurality of areas, judges the attributes (texts, graphics, table, ruled lines, the sorts of the texts, etc.) of respective areas and stores the positional information and attribute information of respective areas (blocks) in a memory 3. A recognition part 8 recognizes characters included in the inputted picture and stores information related to the input document such as the texts (character code strings) of a recognized result and area information in the memory 3 or a storage device 5 as a file. An attribute changing part 6 changes an attribute and a block symbol following the attribute by the operation of a pointing device or the like. A display part 9 displays an image obtained by each processing.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an information processing method and apparatus for recognizing characters in an input image.

[0002] The present invention relates to an information processing method and apparatus capable of processing a document image in which different languages can exist.

[0003] The present invention relates to an information processing method and apparatus for controlling activation of an application running on a general-purpose computer.

[0004]

2. Description of the Related Art In the case of performing character recognition on a document written in two or more languages, a plurality of recognition processing systems for performing optimal proper processing for each language are prepared, and characters for each input document or characters in the input document are prepared. By performing the operation of specifying the language for each area and performing recognition processing specialized for each language,
A character recognition device having a high recognition rate for characters in any language can be obtained. In such a character recognition device, the operator causes the character recognition device to perform a character recognition process after designating a correct language mode for each document or each character region in the document.

It is necessary to confirm and correct the output result of the character recognition process. In the conventional character recognition application, for the recognition result: We have a simple text editor in the character recognition application program, and use it to check and correct. 2. Save the output results to a file. The operator activates another application such as a text editor or a document editor, opens the file, checks and corrects the file. Two types of methods were provided.

[0006]

However, in the conventional device, the set language mode exists only as a variable value in the program. This variable value can be confirmed by specifying the area and opening the area information dialog.
In order to know the language mode for each area in the image, it was necessary to specify each area and open an area information dialog to check the value.

For this reason, in a case where a plurality of documents having different languages are continuously processed, or after specifying a different language mode for a large number of character areas in the document, it is determined whether or not the language mode for the attention area is correctly set. The task of checking is very complicated and burdens the operator.

[0008] Of the methods provided as a method for correcting the recognition result, etc., 1. The method is mainly intended to individually correct misrecognized characters. An effective misrecognized character correction environment is provided, for example, by presenting the lower candidate derived by the character recognition processing to the operator.

However, when the recognition result includes information that cannot be processed by a simple text editor, the above method is insufficient. For example, there are cases where the recognition result includes not only characters but also image information and document structure information, such as a recognition result for a complex format document in which tables and photographs are also mixed.

In that regard, 2. In the method of (1), the recognition result of a complicated format can be confirmed and corrected by appropriately selecting an application. For example, when displaying a recognition result including the above-described structure information, a document editor corresponding to the structure information may be used.

In this case, however, it is necessary to start the desired application after waiting for the output of the character recognition result file, and to open the output result file saved on the application. It took time to confirm.

[0012]

In order to solve the above problems, the present invention displays an input image, a frame representing a plurality of regions constituting the image, and a language mode attribute of the region. An information processing method and apparatus for designating a desired area in an existing area, indicating a language mode attribute of the specified area, and changing the displayed language mode attribute in accordance with the instruction.

In order to solve the above problems, the present invention preferably performs different character recognition processing according to the language mode attribute.

In order to solve the above problem, the present invention preferably displays different symbol patterns according to the language mode attribute.

[0015] In order to solve the above problem, the present invention preferably performs different processing for each language on the image according to the language mode attribute.

In order to solve the above problem, the present invention preferably displays a symbol pattern of a different color according to the language mode attribute.

In order to solve the above problem, the present invention preferably displays a symbol pattern having a different shape according to the language mode attribute.

In order to solve the above problems, the present invention preferably inputs the image by a scanner.

In order to solve the above-mentioned problem, the present invention is an information processing method in a character recognition application operating on a general-purpose computer.
Provided is an information processing method and apparatus for storing a result of the character recognition and automatically starting another application after storing the character recognition result.

In order to solve the above problems, the present invention preferably has the character recognition having a plurality of output formats as a recognition result.

In order to solve the above-mentioned problem, the present invention preferably provides that the application to be automatically started selects and starts an application corresponding to the output format.

In order to solve the above problem, the present invention preferably designates the application to be automatically started to a desired one.

In order to solve the above problems, the present invention specifies an application, instructs execution of a specified process, executes the specified process in response to the instruction, and then executes the specified process. To provide an information processing method and apparatus for starting an application.

[0024] In order to solve the above-mentioned problem, the present invention preferably includes the step of specifying the application on a screen for instructing execution of the processing, by specifying the application.
So do it.

In order to solve the above-mentioned problem, the present invention preferably stores the specified application in an execution instruction screen of the processing, and stores the identified application every time the execution instruction screen of the processing is displayed. The application that is being displayed is displayed and can be edited.

In order to solve the above-mentioned problem, the present invention preferably starts the application after ending the specified processing.

[0027] In order to solve the above-mentioned problem, the present invention preferably specifies the application by inputting an application name.

[0028]

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

[Configuration of Apparatus] FIG. 1 is a block diagram showing the configuration of an apparatus according to an embodiment of the present invention. In FIG. 1, reference numeral 1 denotes a device, 2 denotes a central processing unit (hereinafter referred to as a CPU) for arithmetic processing for controlling the entire device 1, and C
The PU 2 executes various processes described in the present embodiment, for example, as shown in a flowchart described later, according to a control program stored in the memory 3. Reference numeral 3 denotes a memory including a ROM or a RAM, which stores a control program to be executed by the CPU 3 and various data, and also stores a work area of the CPU 3 and document image data input from the input unit 4. It is also used to store the area, and also the block frame coordinates indicating the area to be recognized in the image and the attribute information thereof.

Reference numeral 4 denotes an input unit for reading and inputting a document image, which is constituted by, for example, a scanner or the like, and inputs document image data as digital data. Reference numeral 4 'denotes an interface unit to which the scanner 4 is connected, for exchanging data and controlling. Note that input of an image is not limited to input from the scanner 4 directly connected to the apparatus 1,
Digital data of an image input by another information processing apparatus may be input via a communication line or the like, or digital data of an image stored in an external storage device may be input from the interface unit 4 '.

5 is a storage device (hard disk, FD, C
D-ROM, magnetic tape, ROM, etc.), and data is exchanged and controlled between the main units 1 through the interface 5 '. The control program stored in the memory 3 may also be provided from this storage device.

Reference numeral 6 denotes an attribute changing unit for changing an attribute and a corresponding block symbol (to be described later in detail) by an operation using a later-described pointing device or the like.
In response to the change instruction, the attribute change unit 6 also updates the storage of the attribute information stored in the memory 3. Reference numeral 7 denotes a character recognition preprocessing unit that analyzes image characteristics of the document image stored in the memory 3 and performs block pre-recognition, such as block extraction and further pattern extraction for each character included in the block. Perform processing. Reference numeral 8 denotes a recognition unit. In the Japanese recognition unit 8-1, the pattern preprocessed by the preprocessing unit 7 extracts a geometric feature from an image and is stored in advance in the Japanese recognition dictionary 8-2. The character recognition of the document image is performed by collating with the standard pattern. Similarly, an English recognition unit 8-3 performs character recognition by using patterns stored in the English dictionary 8-4. Which of the two recognition units is used for the recognition process depends on the language mode attribute specified for each block. This language mode attribute follows information stored in the memory 3. The Japanese-language recognition dictionary 8-2 and the English-language recognition dictionary 8-4 include standard pattern data of characters used in each language and grammatical information for each language for post-recognition processing for language analysis of the character recognition results. Etc. are stored. By switching the dictionary for recognition to a dictionary of another language, any language such as French, Italian, etc. can be supported, in addition to Japanese and English.

Reference numeral 9 denotes a display unit, which is an image display unit 9-1 for displaying an input document image, a recognition result display unit 9-2 for displaying a text as a result of recognizing the document image, and a pre-processing unit based on the document image. 7 includes a block frame display section 9-3 for displaying block boundaries so that the blocks cut out by the block 7 can be identified, and an attribute display section 9-4 for identifying attributes determined from each block. Reference numeral 10 denotes a display such as an LCD or a CRT, which can display images, graphics, characters, and the like with various attributes added thereto under the control of the display unit 9.

Reference numeral 11 denotes an external output device, for example, a printer such as an LBP or an ink jet printer, which prints various data under the control of the interface unit 11 '.
Reference numeral 12 denotes a keyboard and a mouse for the user to input and give various data, and gives instructions under the control of the interface unit 12 '. Reference numeral 13 denotes a system bus, which includes a data bus, an address bus, a control signal bus, and the like of the CPU 2.

In the above configuration, a document image is input from the input unit 4 and stored in the memory 3. Then, a reduced image is generated separately from the stored original image and stored in the memory 3.
To be stored. In this reduced image, an n × n pixel block of the original image is used as one reduced pixel. When at least one black pixel exists in the n × n pixel block, the reduced pixel is determined as a black pixel. Things. When you do this,
Eventually, this is the same as when the original image is vertically and horizontally multiplied by 1 / n, and the connected character images (dot images of the character pattern) are connected to each other. A rectangle circumscribing the connected dot distribution is sequentially defined, and the area is divided.

In the following description, it is assumed that the area division processing has been performed as described above, but the area division processing is not limited to this and may be any processing.

FIG. 2 shows an embodiment of the present invention.
3 is a block diagram of software operating on the device (computer) 1 of FIG. Operation system 2 of device 1
01 manages the use of the CPU 2, the memory 3, and various external devices for each application. Under the control of the operation system 201, the character recognition application 202 and the text editor 20 according to the present invention are used.
3. The document editor 204 and the image display application 205 are selectively or simultaneously executed.

FIG. 3 is a flowchart showing the overall processing in the embodiment of the present invention. A document image is input by the scanner 4 or the like (S301), and the input image is converted by the character recognition application 202 into the pre-processing unit 7. Analyzes and divides the area, determines the attributes (text, figure, table, ruled line, text type, etc.) of each area, and determines each area (block)
Is stored in the memory 3 (S30).
2). Characters included in the image input in S301 are recognized by the character recognition application 202 (S30).
3) Information about the input document, such as the text (character code string) of the recognition result and area information, is stored as one file (S304). Display of an image (for example, S502 or the like) performed in each process may be executed by the image display application 205.

FIG. 4 is an example of a window for displaying the result of the area division in the area division processing performed in S302.

The input document image (stored in the memory 3), the area division result and the attribute of the area are combined and displayed on the display 10 by the processing of the image display unit 9-1 as an image window.

In FIG. 4, reference numeral 41 denotes an image window showing that a document image read by the input unit 4 is displayed. Reference numeral 42 denotes a frame (frame specifying the size of one region) as a result of the region division, which indicates the position of the paragraph in the text portion. 43, 44 and 45 are block symbols indicating the attributes of the block. Block attributes indicate the character of the characters in the block frame.
Block order, content (title, sentence), composition direction (horizontal,
Vertical), language mode (Japanese, English ...).

Here, depending on the color of the block symbol,
The language mode among the attributes described above is displayed. In FIG. 4, reference numerals 43 and 44 denote block symbols on a white background indicating that the language mode attribute in the frame is Japanese, and reference numeral 45 denotes a block symbol on a black background indicating that the language mode attribute in the frame is English.

[Display of Block Attribute] Hereinafter, in the example in which the attribute of each block is displayed in the image window, and the attribute correction is accepted, and the recognition process corresponding to each attribute is performed, the processing steps of S301 to S303 are further performed. The detailed processing is shown in the flowchart of FIG. 5 and will be described below. The control program for executing this process is stored in the memory 3
Is stored in

First, in step S 301, the document image set by the operator is read and input by the input unit 4 (scanner) and stored in the memory 3.

Next, the process proceeds to step S501, where the preprocessing unit 7
To divide the area. In the region division, attributes of each block such as a paragraph, a figure, a table, and a ruled line of a text are also extracted.

In step S502, as shown in FIG. 4, the attribute of the area is displayed in the form of a block symbol in accordance with the attribute information stored in the memory 3 and stored in the memory 3, and the image read by the image display unit is displayed. indicate. In the initial state, the attributes of all blocks are set to default values.

In step S503, the operator checks the attribute information shown on the display unit, and inputs correction information of the attribute of the area using the mouse or the keyboard 12 if necessary. If it is determined in step S503 that there is a region whose attribute has been corrected, the attribute information stored in the memory 3 is changed in accordance with the instruction, and step S502 is executed again to display the corrected block symbol again. . After it is determined in S503 that the attribute has not been modified, the process proceeds to character recognition processing.

In step S505, the attribute specified for each block is referred to from the memory 3. If the language mode attribute is Japanese, the Japanese recognition unit 8-1 executes step S50.
In step S507, English character recognition is performed by the English recognition unit 8-3 when the language mode attribute is English.

Finally, in step S508, the recognition result is output. The recognition result is displayed not only on the display screen of the display 10 according to the designation of the operator but also on the storage device 5.
Or to the printer 11.

Finally, in step S508, the recognition result is output. The recognition result is displayed not only on the display screen of the display 10 according to the designation of the operator but also on the storage device 5.
Or to the printer 11.

FIG. 6 is a flowchart showing the processing of the block symbol display unit in step S502. S
At 61, the attribute of each block is read from the memory 3, and if the language mode attribute of the block is Japanese, S62
The process proceeds to step S63 to display a block symbol on a white background and a block symbol on a black background when the language mode attribute of the block is English.

FIG. 7 is a view showing an example of a display enabling the attribute correction processing in the embodiment of the present invention. An operation panel 72 and an image window 71 are displayed. What is shown in the image window 7 is S after the area division processing.
In the state of 502, the language mode attribute of all blocks is set to a default value, and here all are in Japanese. Therefore, the block symbols 73 and 74 in FIG.
And 75 are all displayed on a white background indicating that the text in the frame is in Japanese.

Here, since the area indicated by the block symbol 75 is actually an English sentence area, it is necessary to change the language mode attribute of the block to English before recognition. This can be easily confirmed by the operator comparing the color of the block symbol overwritten with the image in the image window.

The operator changes the language mode attribute value of the block 78 to English by designating the block symbol 75 with the mouse 12 and clicking the button 76 for changing the block attribute to English on the operation panel 72. To update the memory 3. By this operation, the block symbol is changed to a black block symbol indicating that the text in the frame is in English, and the image window is in the same state as 41 in FIG. The attribute change operation is not limited to the above, and may be performed by another operation.

As described above, in the present invention, by comparing the displayed image with the colors of the block symbols by the display as shown in FIG. 7, the language mode to be designated for each area and the currently set language mode are set. Inconsistency with the current language mode can be easily found, and the complexity of the language mode confirmation operation during multilingual character recognition processing can be reduced.

In FIG. 4, the color of the block symbol is white in Japanese and black in English, depending on the type of language mode used for recognition. However, various other easily distinguishable colors are used. Is also possible.

In FIG. 7, the default language mode is set equally for all blocks immediately after the area division. However, a language discriminating means for discriminating the language mode based on the image in the frame is used. Alternatively, the result of performing the language determination for each block may be used as the default language mode value for each block. Also at this time, the operator can easily confirm the correctness of the language discrimination by comparing the color of the block symbol with the image by the attribute display means of the present invention, so that the operation burden is reduced.

In FIG. 4, the colors are used to distinguish the block symbols, but the shape of the block symbols may be changed according to the language mode attribute so that the symbols can be visually distinguished easily. For example, as shown in FIG.
The shape may be changed, the size may be changed, or the presence or absence of blinking may be distinguished as shown in FIG.

In FIG. 7, there are two language modes, Japanese and English. However, in a character recognition apparatus for various languages, a different language mode is used for each block symbol indicating each language mode. Colors or shapes may be assigned.

[Application Activation Control] Next, the processing of the character recognition application 202 will be described with reference to the flowchart of FIG. However, here, the saving process S304 will be described in detail in S901 to S906. Steps S301 to S303 are the same as the processes shown in the flowcharts of FIGS.

First, in step S301, the operator uses the scanner 4 to input document image data to a character recognition program. Instead of the scanner, a document image file in the external storage device 5 or received via a network (not shown) may be designated as an input image. The input image data is stored in the memory 3.

Next, in step S302, the CPU 2 performs region division on the document image. Each area such as a text, a table, a ruled line, a figure, and a photograph in the document is extracted by the area division, and the structure information including the coordinates and the size in the document is stored in the memory 3. Image data is stored in the memory 3 for an area where character recognition cannot be performed, such as a figure or a photograph.

FIG. 10 shows an example of an input document, and FIG. 11 shows an example of the result of area division for the document image of FIG.
Displayed as 0. 1101, 1102, 1103 are text areas, 1104 is a table area, 1105 is a figure area, 1
106 is a ruled line.

Here, the region division is performed by a method of estimating a set of characters from the distribution of connected components obtained by reducing the size of a document image, but the present invention is not limited to this method and may be performed by any process.

In step S303, the CPU 2 recognizes a character in a region whose attribute is given as text. In character recognition, a geometric feature is extracted from a character pattern, collated with a standard pattern in a recognition dictionary in a recognition unit 8, and converted into a character code.

In step S 901, the operator selects whether or not to save the recognition result, and instructs using the keyboard / mouse 12. The stored recognition result is S303
This is a recognition result of the entire document obtained by synthesizing the character code which is the character recognition result in the text region obtained in step S301, the figure / photograph image stored in step S301, and their structural information.

When an instruction to select save is given in S901, the operator inputs a save file name using the keyboard 12 in S902. Further, in step S903, after saving the recognition result, the user selects whether to start another application for checking and correcting the result, and instructs using the keyboard or the mouse 12.

If it is instructed to start the application after storing the recognition result, the process proceeds to S904, where the recognition result is stored as a file in the memory 3 or the storage device 5, and then in S905, another application is started according to the instruction. I do. At this time, the saved recognition result file is designated for the other application so that the content of the recognition result is immediately displayed on the started other application.

If the application is not started, S
In step 906, the recognition result is stored in a file in the memory 3 or the storage device 5, and the process ends.

FIG. 12 shows an example of the window displayed in S901 to S903 in FIG. 9, and the operation will be described.

The operator uses the keyboard and mouse 12 to enter a file name for storing the recognition result in a text box 1203 in the dialog 1202.

A check box 1203 is used to select whether to automatically start the application. The state of the check box 1203 is determined by
When the user clicks on the button 208, the state changes from on to off to on each time the click is made.

Further, by inputting the name of the application to be started into the keyboard 1205 through the keyboard 12, an arbitrary application desired by the operator is started.
This input value can be stored in the storage window 1202, and if there is no change, it is not necessary to input the value every time the recognition operation is performed.

When the save button 1206 is clicked with the mouse 12 after instructing the save file name and whether or not to start the application, the operation proceeds to step S904 or S906. If saving is not desired, the cancel button 1207 may be clicked with the mouse 12.

In FIG. 13, reference numeral 1302 denotes a step S90 in which a document editor is designated as an application to start the save window 1202 in step S902.
5 is an example of an application started in FIG. This application is a document editor that can reproduce complicated document structures and can also capture figures and pictures in documents as images.

As described above, according to the present invention, since the user can specify an arbitrary application conforming to the format of the recognition result, the desired application can be used for checking and correcting the recognition result each time. In addition, since those applications are automatically started when the recognition result is stored, the recognition contents can be immediately confirmed. Therefore, the efficiency of the work after recognition is improved.

When a plurality of output formats of the character recognition result can be selected, such as text only, text with structure information, or image images, different applications may be activated depending on the selection of the output format. For this purpose, a window 1402 for selecting a character recognition result output format as shown in FIG. 14 may be displayed. Recognition result output setting dialog box 1402
The output format can be selected by designating the output format selection menu 1403 in the mouse with the mouse 12. Also, 1404,
Reference numerals 1405 and 1406 denote applications used to display the output in each format, the contents of which can be changed by inputting a character string from the keyboard 12 by the operator.

If the above selection is made before the recognition or before the storage of the recognition result, an application suitable for the output format is automatically started when the recognition result is stored. Therefore, the operator can immediately confirm the content regardless of the format of the recognition result.

It is to be noted that an erroneously recognized character correcting process may be added immediately after the character recognizing process of the text area. FIG. 15 is a diagram showing a flowchart of the process. In step S1500 added to the flowchart of FIG. 9, an erroneously recognized character correction process is performed.

FIG. 16 shows an example in which a character correction editor is used as the erroneously recognized character correction processing. The character correction editor window 1603 is an editor provided as a part of the character recognition application program window 1601, and presents a candidate 1604 for each target character by using information in the program to effectively prevent the operator from erroneous recognition. Provide an environment for modification.

As described above, an editor excellent in correcting erroneously recognized characters is used for checking and correcting characters, and thereafter, a part which cannot be checked and corrected by the character correcting editor is checked and corrected using another application. I can do it.

For example, a document editor capable of reproducing a document structure can be started as another application to further confirm and correct the recognition result of the document. At this time, the application is automatically started when the recognition result is saved, and the recognition content can be checked immediately.
The efficiency of the work after recognition is improved.

[0083]

As described above, according to the present invention,
An input image, a frame representing a plurality of regions constituting the image,
Displaying a language mode attribute of the area, specifying a desired area in the displayed area, indicating a language mode attribute of the specified area, and displaying the language mode attribute according to the instruction; , The efficiency of the character recognition processing confirmation and correction work can be improved.

As described above, according to the present invention, the accuracy of character recognition processing can be improved by performing different character recognition processing according to the language mode attribute.

As described above, according to the present invention, it is possible to easily identify a language mode attribute by displaying different symbol patterns according to the language mode attribute.

As described above, according to the present invention, by performing processing different for each language on the image in accordance with the language mode attribute, it is possible to perform appropriate processing according to the language.

As described above, according to the present invention, by displaying symbol patterns of different colors according to the language mode attribute, the language mode attribute can be easily identified.

As described above, according to the present invention, by displaying a symbol pattern having a different shape according to the language mode attribute, the language mode attribute can be easily identified.

As described above, according to the present invention, any document image can be processed by inputting the image with a scanner.

As described above, according to the present invention, there is provided an information processing method for a character recognition application operating on a general-purpose computer, comprising the steps of recognizing a character in an input image, storing the result of the character recognition, After the recognition result is saved, by automatically starting another application, correction work after the character recognition processing can be performed efficiently, and work efficiency for starting the application for that purpose can be improved.

As described above, according to the present invention, the character recognition has a plurality of output formats as recognition results, so that necessary data can be obtained as needed.

As described above, according to the present invention, the application to be automatically started can select an application suitable for the output format by selecting and starting an application corresponding to the output format.

As described above, according to the present invention, an application desired by a user can be designated by designating a desired application as the application to be automatically started.

As described above, according to the present invention, an application is specified, an instruction to execute a specified process is issued, and after executing the specified process in response to the instruction, the specified application is executed. By activating the application, the operability at the time of activating the application can be improved.

As described above, according to the present invention, the specification of the application is provided on the execution instruction screen of the processing by means for specifying the application, and the application is easily specified. .

As described above, according to the present invention, the specified application is stored in the processing execution instruction screen, and is stored each time the processing execution instruction screen is displayed. Display the applications that are
By allowing editing, the previously specified application is provided as a default, thereby facilitating the specifying operation.

As described above, according to the present invention, the activation of the application is performed after the termination of the designated process, so that the designated process is started in order to indicate the application to be activated next. There is no need to wait for termination, and operability is improved.

As described above, according to the present invention, by specifying the application by inputting the application name, the operation of specifying the application is simplified.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of an apparatus according to an embodiment of the present invention.

FIG. 2 is a software configuration diagram according to the embodiment of the invention;

FIG. 3 is a flowchart of an overall process;

FIG. 4 is an exemplary view of an image window.

FIG. 5 is a flowchart of an attribute correction and recognition process.

FIG. 6 is a flowchart of an attribute display process.

FIG. 7 is an exemplary display at the time of attribute correction processing.

FIG. 8 shows a second example of attribute display.

FIG. 9 is a flowchart of a recognition result storing process.

FIG. 10 is a view showing an example of an input document image;

FIG. 11 is a view showing a result of dividing the image of FIG. 10 into regions;

FIG. 12 is an exemplary diagram of a save window.

FIG. 13 is a diagram showing an example of display when another application is activated.

FIG. 14 is a view showing an example of a setting window of a recognition result output.

FIG. 15 is a flowchart of processing in which an erroneously recognized character correction step is added.

FIG. 16 is a view showing an example of display when correcting a misrecognized character.

Claims (18)

[Claims] 1. An input image, a frame representing a plurality of areas constituting the image, and a language mode attribute of the area are displayed, a desired area in the displayed area is specified, and the specified area is displayed. An information processing method comprising: instructing a language mode attribute of an area; and changing the displayed language mode attribute in accordance with the instruction. 2. The information processing method according to claim 1, wherein different character recognition processing is performed according to the language mode attribute. 3. The information processing method according to claim 1, wherein different symbol patterns are displayed according to the language mode attribute. 4. The information processing method according to claim 1, wherein processing different for each language is performed on the image according to the language mode attribute. 5. The information processing method according to claim 1, wherein a symbol pattern of a different color is displayed according to the language mode attribute. 6. The information processing method according to claim 1, wherein a symbol pattern having a different shape is displayed according to the language mode attribute. 7. The information processing method according to claim 1, wherein the image is input by a scanner. 8. An input image, frames representing a plurality of regions constituting the image, display means for displaying a language mode attribute of the region, and region designation for designating a desired region in the displayed region Information processing apparatus, comprising: means for specifying a language mode attribute of the designated area. 9. An information processing method for a character recognition application operating on a general-purpose computer, wherein the input image is subjected to character recognition, the result of the character recognition is stored, and after storing the character recognition result, another application is executed. An information processing method characterized by automatically starting. 10. The information processing method according to claim 9, wherein the character recognition has a plurality of output formats as a recognition result. 11. The information processing method according to claim 10, wherein the automatically started application selects and starts an application corresponding to the output format. 12. The information processing method according to claim 9, wherein the application to be automatically started is designated as a desired one. 13. The method according to claim 1, wherein an application is specified, execution of a specified process is instructed, and after executing said specified process in response to said instruction, said specified application is started. Information processing method. 14. The information processing method according to claim 13, wherein a means for specifying the application is provided on the execution instruction screen of the processing, and the specification of the application is performed there. 15. The specified application,
15. The information according to claim 14, wherein the stored application is stored with respect to the processing execution instruction screen, and the stored application is displayed and edited each time the processing execution instruction screen is displayed. Processing method. 16. The information processing method according to claim 1, wherein the activation of the application is performed after the specified processing is completed. 17. The information processing method according to claim 13, wherein the specification of the application is performed by inputting an application name. 18. An application specifying unit for specifying an application, an execution instructing unit for instructing execution of a specified process, and executing the specified process in response to the instruction, and then executing the specified application. An information processing apparatus, comprising: an application activating unit for activating the application.