JP2002218125A - Document processor and document processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a document processor and a document processing method, which can automatically apply different processing to each of documents and images being processing objects. SOLUTION: In the document processor and the document processing method, a character recognition section 11 receives a document image from an image input section 10 and extracts and recognizes information describing contents of processing instructions at a predetermined place of the document image or on a slip. An instruction discrimination section 12 compares the result of recognition by the character recognition section 11 with contents of the processing instructions stored in advance in an instruction database section 12 to discriminate the contents of the processing instructions described in the document image and a processing section 14 executes the processing for each document image according to the discriminated processing instructions.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

The present invention relates to a digital copying machine,
Recognizes a processing instruction written in a predetermined place or a tag etc. of a document image input from a scanner, facsimile, etc., and copies the document image without manual operation according to the recognized processing instruction. , Save,
The present invention relates to a document processing device and a document processing method for performing processing such as transfer.

[0002]

2. Description of the Related Art In recent years, digitization of a document processing process has been advanced, and with the advent of digital multifunction peripherals, various processes can be performed on a personal desktop computer.

However, at present, copying and facsimile
In order to process paper documents such as documents, it is necessary to go to the location of the digital multifunction device that is commonly used in the office and operate the device. It has become a bottleneck.

Therefore, it is conceivable that the document images to be processed are stored in a personal desk and the processing in the digital multi-function peripheral is performed collectively. In this case, however, the control of the digital multi-function peripheral is performed for each document image. Since it is necessary to manually operate the panel and the like, there is a problem that the user is restricted in time until the processing of all the document images is completed.

As a means for enabling continuous processing of paper documents in a digital multifunction peripheral, ADF (Auto Docum
ent Feeder), but the ADF can perform only the same continuous processing, and cannot perform different processing for each document image.

Accordingly, a technique relating to document processing process automation has been proposed. One of the means is disclosed in, for example, JP-A-7-49941. In this document processing process, a cover with a machine identification mark code and a route designation on a computer network was placed before the logical set of all sheets, and during scanning, the presence of the cover and the start of document scanning were checked. Above, read the machine identification mark code, record the identifier and routing information there, and if there is no new cover or the next sheet to be inserted into the scanner, replace all the sheets scanned from the previous cover with one For example, a document image is stored on a computer network.

However, in the technique disclosed in Japanese Patent Application Laid-Open No. 7-49941, it is essential to place a cover including machine identification special information before each logical set of a document image. Since there is no next sheet to enter into the scanner, it is identified as one document image, so it is not possible to automatically process only a part of the stack of document images input from ADF etc. There was a problem that is.

[0008]

That is, in the prior art, when operating a digital copying machine, a scanner, a facsimile, etc., it is necessary to manually operate the equipment.
It is impossible to set only a part of document images as an object of automatic processing, and different cooperative processing and automatic processing cannot be performed for each document image to be processed.

The present invention has been made in order to solve the above-described problem. A processing instruction and an identifier are described in a predetermined portion of a document image or a tag, and the processing is performed by recognizing the processing instruction and the identifier. It is an object of the present invention to provide a document processing apparatus and a document processing method capable of automatically performing different processing for each target document image.

[0010]

In order to achieve the above object, in a document processing apparatus according to the present invention, an input means for inputting a document image, and a document image input by the input means, A recognizing means for extracting and recognizing information in which the content of the processing instruction is described in a predetermined portion or a tag of the document image; a database means for preliminarily storing the content of the processing instruction; and a recognizing means. Determining means for comparing the recognition result with the content of the processing instruction stored in the database means to determine the content of the processing instruction described in the document image input from the input means; Processing means for executing a process for each document image with respect to the document image input from the input means in accordance with the given processing instruction. You.

Further, in the document processing method of the present invention, a document image is input, and the content of the processing instruction is described in a predetermined portion or a tag of the input document image. Extracting and recognizing information, comparing the recognized result with the content of the processing instruction stored in advance in the database, and determining the content of the processing instruction described in the input document image, According to the determined processing instruction, for the input document image,
It is characterized in that processing for each document image is executed.

With the above arrangement, according to the present invention, information serving as a processing instruction is described in a predetermined portion of a document or a tag, and the information is recognized so that each document to be processed can be processed. This makes it possible to automatically perform different processes for each case.

[0013]

Embodiments of the present invention will be described below with reference to the drawings. (First Embodiment) FIG. 1 is a block diagram showing a configuration of a document processing apparatus according to a first embodiment of the present invention.

The document processing apparatus includes an image input unit 10, a document recognition unit 11, an instruction determination unit 12, and an instruction database unit 1.
3 and a processing unit 14.

The image input unit 10 inputs a document image as digital data, and is constituted by a digital copying machine, a scanner, a facsimile or the like. The character recognizing unit 11 extracts and recognizes character information indicating a processing command described in a predetermined portion or a tag of the document image input by the image input unit 10.

The instruction judging section 12 performs matching with the processing instruction / identifier stored in the instruction database section 13 based on the character information (character string) recognized by the document recognizing section 11 to obtain a document image. Is to judge the contents of the processing instruction described in. Instruction database unit 13
Is a database in which the contents of processing instructions and identifiers to be executed by the processing unit 14 are stored in advance.

Further, the processing section 14 executes a predetermined process on the document image input from the image input section 10 based on the processing command recognized by the command determination section 12. The processing unit 14 includes, for example, a copy function in a digital copying machine, an OCR function in a scanner,
The AX has a transmission function and the like.

Next, the flow of processing in the document processing apparatus shown in FIG. 1 will be described with reference to the flowchart shown in FIG.

First, a digital copying machine, a scanner, a facsimile
The document image is input as digital data by the image input unit 10 composed of the above (ST101). Next, from the document image input from the image input unit 10, a predetermined portion in the document or handwritten or printed characters written on a tag or the like is extracted by the character recognition unit 11, and recognition processing is executed (ST102). .

The reason why the recognition area of the command is limited to a predetermined position in the document is to prevent a character string other than the command in the document from being erroneously recognized as a command, and the character recognizing unit 11 uses the character string. This is for limiting the region in which the recognition process is performed.

For detection of a predetermined location in a document, for example, this area is determined in association with the document size and the document type, such as this area in A4 length, or this area in the format A book format. In this way, the character recognition unit 11 can automatically detect an area using the document size detection result of the document processing apparatus.

Further, regarding the detection of the tag area, the character recognition unit 11 can detect the tag area by detecting the paper edge of the document and recognizing the area protruding from the straight line forming the paper as the tag. .

In addition, the character string describing the command, the background color of the command character string, the color of the tag, etc. are determined in advance, and the background color and the color information of the tag can be used. It is also possible to detect a character string recognition area by setting a special rule such as writing a special mark or enclosing it with a dotted line so that the character recognition unit 11 can recognize the command character string.

FIG. 3 shows an example of a character recognition target area (a predetermined location or a tag) in a document image.
Shown in FIG. 3A shows an example in which a region surrounded by a dotted line in the upper right of the document is defined as a character recognition region, and FIG. 3B shows an example in which a tag portion is defined as a recognition region.

In these examples, as shown in FIG. 4, in the character recognition section 11, the character strings "COPY 3", "OC"
The letters "R" and "MAIL SATO" are recognized.
As described above, when the character recognition unit 11 recognizes a character at a predetermined portion or a tag portion in a document image (S
T103), and sends the character recognition result to the command determination unit 12.

The command judging section 12 interprets the character string recognized by the character recognizing section 11 and matches a processing command and an identifier existing in the command database section 13 to recognize a processing command for a document image (ST104).

The instruction database unit 13 stores processing instructions and identifiers to be executed by the document processing apparatus in advance, and specific examples of the stored processing instructions are shown below. (Contents of processing instruction) ・ Copy (take a copy) ・ FAX (send FAX) ・ OCR (recognize text in document image) ・ MAIL (send by e-mail) ・ Save (save to memory) ・ Copy attribute (Example: 2 in 1, enlargement / reduction, stapling, double-sided copy) Image processing (eg, binarization, inclination correction, monochrome, photo removal) Expiration date Folder classification In the instruction database unit 13, for example, processing instructions And the contents of a specific series of processing are stored in association with each other as described below.
When these processing instructions are instructed, it is possible to identify the contents of a series of processing.

"Check" → "Skew correction → Monochrome → Save" ・ "Copy 2" → "2in1 → Copy" ・ "Monochrome" → "Photo removal → Binarization → FAX" ・ "Resume" → "Copy" In the example illustrated in FIGS. 3 and 4, the instruction determining unit 12 determines COPY (takes a copy) as the first instruction based on the processing instruction / identifier stored in the instruction database unit 13. 3 (three copies) as an identifier serving as its argument, OCR (applying the document image content to OCR) as a second command, MAIL (sending mail) as a third command,
"SATO" is recognized as the corresponding identifier.

Further, the instruction determining unit 12 determines whether the recognized processing instruction is appropriate and can be executed (ST105). That is, in the case of the example shown in FIG.
"Copy three copies of the input document image and copy the document image
R, and the details of the recognition are entered in the user name "SA
A processing instruction of “send by mail to TO” is recognized, and it is determined whether this processing instruction can be executed by the document processing apparatus.

When it is determined that these recognition results are executable, the recognized processing instruction is sent to the processing unit 14.
Further, when an OCR command is specified in spite of not having the OCR function in the document processing apparatus, the command determining unit 12 determines that the specified processing command is not executable, A processing instruction is sent to the processing unit 14 so as to notify the user of the warning that execution is impossible by mail or printout.

In the case where no character is detected in the character recognizing section 11 because no character is described in a predetermined place in the document image or a tag is not attached (ST103), The command determining unit 12 sends a processing command to the processing unit 14 to perform default processing predetermined by the image input unit 10 such as a digital copying machine, a scanner, and a facsimile.

The processing section 14 executes the processing instruction determined by the instruction determining section 12 (ST106), or issues a warning that the processing instruction cannot be executed (ST10).
7) or execute the appropriate process of executing the default process specified by the image input unit 10 (ST108). For example, in a document image input from the image input unit 10, if a processing instruction is described in a predetermined location or a tag in the document image as shown in FIG. 3, first, in accordance with the processing instruction, , Image input unit 1
In this process, three copies of the input document image are copied from O, the input document image is subjected to character recognition by OCR, and the recognition result is transmitted to the user name "SATO" by mail.

As described above, by describing a processing instruction and an identifier in a predetermined portion or a tag of the document image input from the image input unit 10, the processing instruction in which the input document image is described is recognized. By letting
It is possible to automatically perform processing (copy, OCR, mail transmission, etc.) specified for each input document image. (Second Embodiment) FIG. 5 is a block diagram showing a configuration of a document processing apparatus according to a second embodiment of the present invention.

This document processing apparatus shows a configuration for recognizing a processing instruction coded and described in a predetermined portion of a document image or a tag.

This document processing apparatus comprises an image input unit 20, a code recognition unit 21, an instruction determination unit 22, an instruction database unit 23, and a processing unit 24.

The image input unit 20 is for inputting a document image as digital data and, like the image input unit 10 shown in FIG. 1, comprises a digital copying machine, a scanner, a facsimile or the like. Code recognition unit 2
Reference numeral 1 is for extracting and recognizing code information indicating a processing instruction described in a predetermined portion or a tag of a document image input by the image input unit 20.

The instruction judging unit 22 performs matching with the processing instruction / identifier stored in the instruction database unit 23 based on the code information recognized by the code recognizing unit 21, and describes the matching in the document image. This is to determine the content of the processing instruction. The instruction database unit 23 is a database in which the contents of processing instructions and identifiers to be executed by the processing unit 24 are stored in advance.

Further, the processing section 24 is for executing a predetermined process on the document image input from the image input section 20 based on the processing command recognized by the command determining section 22. This processing unit 24 includes, for example, a copy function in a digital copying machine, like the processing unit 14 shown in FIG.
It has an OCR function in the scanner, a transmission function in the FAX, and the like.

Next, the flow of processing in this document processing apparatus will be described with reference to the flowchart shown in FIG.

First, a digital copying machine, a scanner, a facsimile
A document image is input as digital data by the image input unit 20 configured as described above (ST201). Next, from the document image input from the image input unit 20, code information written on a predetermined portion in the document image or on a tag or the like is extracted by the code recognition unit 21, and the contents of the code information are recognized ( ST202).

FIG. 7 shows an example of a "predetermined location" or "sticky note" which is a recognition target area of code information in a document image. FIG. 7A is an example in which the area surrounded by the upper right dotted line of the document image is defined as a code information recognition area, and FIG. 7B is an example in which the tag portion is defined as code information recognition area. An example in which a barcode is adopted as code information is shown. In these examples, the bar code area is recognized by the code recognition unit 21 as shown in FIG. Also, this "predetermined location" or "sticky note"
Is detected by the code recognition unit 21 using the same method as that described in the first embodiment.

The instruction judging unit 22 interprets the code recognized by the code recognizing unit 21 and matches the processing instruction / identifier existing in the instruction database unit 23 to recognize the processing instruction for the document image (ST204).

The instruction database unit 23 stores in advance processing instructions and identifiers to be executed by the document processing apparatus, and the details of the stored processing instructions will be described in the first embodiment. The contents are the same as those stored in the instruction database unit 13.

Next, the instruction determining unit 22 determines whether the recognized processing instruction is appropriate and can be executed (ST205), and when it is determined that these recognition results are executable. Sends the recognized command to the processing unit 24.
Further, when a facsimile command is specified in spite of the fact that the document processing apparatus does not have the facsimile function, it is determined by the command determination unit 22 that the specified processing command is not executable. In this case, a processing command is sent to the processing unit 24 so as to notify the user of the warning that execution is impossible by mail or printout.

Further, when code information is not described in a predetermined location in a document image, or when a tag or the like is not attached, the code recognition unit 21
When no code information is detected in (ST203)
In step (2), the command determining unit 22 sends a processing command to the processing unit 24 to perform a default process predetermined by the image input unit 20 such as a digital copying machine, a scanner, and a facsimile.

The processing section 24 executes the processing instruction determined by the instruction determining section 22 (ST206) or issues a warning that the processing instruction cannot be executed (ST20).
7) or execution of a default process specified by the image input unit 20 (ST208).

For example, as shown in FIG. 7, in a document image input from the image input unit 20, when a processing instruction is described as code information in a predetermined location or a tag in the document image, According to the processing instruction, predetermined processing (copy, OCR, mail transmission, etc.) is executed for each document image.

As described above, by describing the processing instruction as code information in a predetermined portion or a tag of the document image input from the image input unit 20, the processing instruction in which the input document image is described is written. Recognition makes it possible to automatically perform the designated process for each input document image. (Third Embodiment) FIG. 9 is a block diagram showing a configuration of a document processing apparatus according to a third embodiment of the present invention.

In this document processing apparatus, for example, by referring to the processing method in the document processing apparatus described in the first embodiment or the second embodiment, for example, a document image on which an approval seal is stamped is used. This is an example of a case where a process of identifying and storing a document image on which an approval seal is stamped and another document image in different folders is executed. For example, if an approval stamp is stamped on a predetermined portion or a sticky note of a document image, the document image is transferred to an approved folder (not shown), and another document image (an approval stamp is not stamped) Document image) to an unapproved folder (not shown).

In this document processing apparatus, the image input unit 30
Seal recognition unit 31, judgment unit 32, seal database unit 33
And a processing unit 34.

The image input section 30 inputs a document image as digital data, and comprises a digital copying machine, a scanner, a facsimile or the like.

The seal recognition unit 31 extracts and recognizes a seal imprint written on a predetermined portion or a tag of the document image input by the image input unit 30.

The judging unit 32 matches the seal imprint recognized by the seal recognition unit 31 with a plurality of seal imprint data corresponding to the approval seal stored in the seal imprint database 33.
This is to determine whether the imprint data described in the document image is an approval seal.

When the determining unit 32 determines that the document image input from the image input unit 31 is stamped with an approval stamp, the processing unit 34 stores the document image in an approval folder (not shown). In addition, if it is determined that the document image input from the image input unit 31 is not stamped with an approval stamp, the document image is transferred to an unapproved folder.

Next, the flow of processing in this document processing apparatus will be described with reference to the flowchart shown in FIG.

First, a digital copying machine, a scanner, a facsimile
A document image is input as digital data by the image input unit 30 configured as described above (ST301). Next, in order to determine whether or not an approval stamp is imprinted on a document image input from the image input unit 30 at a predetermined location in the document image or on a tag or the like, the recognition unit 31 If any mark is imprinted on a predetermined portion or a tag in the document image, the seal image is extracted and recognized by the seal recognition unit 31 (ST302).

FIG. 11 shows an example of a "predetermined location" or "sticky note" which is a recognition target area of a seal image of a document image.
FIG. 11A shows an example in which the area surrounded by the upper right dotted line of the document image is defined as a seal impression recognition area, and FIG. 11B shows an example in which the tag portion is defined as a seal impression recognition area. In the example, the seal imprint area is recognized by the seal recognition section 31 as shown in FIG. As for the method of detecting the “predetermined part” or “sticky” area, the seal recognition unit 31 uses the same method as that described in the first embodiment.
Will be implemented.

The judgment unit 32 matches the imprint data recognized by the seal recognition unit 31 with the imprint data stored in the imprint database unit 33, and the imprint data stamped on the document image is the approval seal. It is determined whether or not this is the case (ST304), and the following processing is executed based on the determination result (ST305).

In this embodiment, when the recognized seal is an approval seal, the image input unit 30 is sent to the processing unit 34.
Is instructed to register the document image data input from the approval folder, and the recognized imprint is registered in the imprint database 3.
If it is determined that the document image is not an approval stamp because it is different from the data of the approval stamp stored in No. 3, the document image data is transferred to the unapproved folder to the processing unit 34, and Instruct the user to notify the user of the warning by e-mail or printout.

If the seal recognition unit 31 does not detect any imprint on a predetermined portion or a tag in the document image (ST303), the instruction determination unit 32 determines whether the digital copying machine, the scanner, the facsimile, or the like. A processing command is sent to the processing unit 34 so as to perform a predetermined default process in the image input unit 20 of the image processing apparatus.

In the processing section 34, based on the processing command of the determination section 32, either execution of registration of the document image data in the approved folder (ST306), warning notice (ST307) or execution of default processing (ST308) is appropriate. Then, the process for the document image is completed.

As described above, in the document processing apparatus according to the third embodiment, the document image with the approval mark is identified, and the document image with the approval mark is separated from the other document images. Can be automatically executed. (Fourth Embodiment) When an area for describing a character, a code, a seal, or the like in a document image or an area in which a character, code, or seal is described in a tag area is directly processed, the area is included in the original document image. Processing such as printing, copying, saving, transferring, and OCR is performed while characters, codes, and imprints that have not been included are included.

Therefore, as a fourth embodiment of the present invention, after deleting designated portions such as characters, codes or imprints provided for automatic processing, printing a document image,
An example of a document processing apparatus having a configuration for performing processing such as copying, saving, transferring, and OCR will be described.

FIG. 13 shows the configuration of a document processing apparatus according to the fourth embodiment of the present invention, and FIG. 14 is a flowchart showing the flow of processing in this document processing apparatus.

In this document processing apparatus, the image input unit 40
The configuration includes a recognition unit 41, a command determination unit 42, an instruction deletion unit 43, and a processing unit 44.

The image input unit 40 inputs a document image as digital data using image input means such as a digital copying machine, a scanner, and a facsimile (ST401).

Recognition section 41 extracts and recognizes a predetermined portion in the document image, characters, code information, or seal imprinted on a tag or the like from the document image input by image input section 40 (ST402).

At this time, when no character, code information, or imprint is detected in the recognition unit 41 (S
In T403), the instruction deciding section 4 performs no default processing in the instruction erasing section 44 and performs default processing predetermined by a digital copying machine, a scanner, a facsimile or the like.
2 to the processing unit 45.

When characters, code information, imprints, and the like are detected by the recognition unit 41 (ST403), the detection result is sent to the instruction determination unit 42.

The instruction determining unit 42 determines whether the character, code information or seal imprint recognized by the recognizing unit 41 is associated with the instruction database 4.
3 is matched with the processing instruction / identifier, code information or imprint information existing in Step 3 to recognize a processing instruction or the like for the document image (ST404). Further, the instruction determining unit 42
Then, it is determined whether the instruction is appropriate and executable (ST405),
If we determine that these recognition results are feasible,
It instructs the processing unit 45 of the recognized processing instruction and the like. Recognition unit 4
In step 1, if it is determined that the recognized processing instruction or the like is not executable, the instruction erasing unit 44 does not perform any special processing, and notifies the user of a warning that execution is not possible by e-mail or printout. To the processing unit 45.

The processing unit 45 executes an appropriate one of the execution of the recognition instruction (ST406), the warning notification (ST407), and the execution of the default processing (ST408) based on the judgment result of the instruction judgment unit 42. . At this time, when one of the instructions recognized by the recognition unit 41 includes the deletion of the instruction added to the document image, or when the setting to delete the instruction added to the document image is included,
When the instruction erasing instruction is recognized, the instruction deciding section 42 issues an instruction to the instruction erasing section 44, and the instruction erasing section 44 executes an operation of erasing the instruction added to the document image.

With this configuration, even if a document image has characters, codes, and seals described in an area for describing characters, codes, seals, and the like, and a tag area, these descriptions are deleted. Print, copy,
This enables processing such as storage, transfer, and OCR.

The present invention is not limited to the above-described embodiment, but can be variously modified without departing from the gist thereof.

[0074]

As described in detail above, in the present invention,
For a document image input from a digital copier, a scanner, a facsimile, or the like, information to be a processing instruction is described in a predetermined portion or a tag of the document image, and the information is extracted and recognized. By recognizing a designated processing instruction for each document image, different processing can be automatically performed for each document image to be processed.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration of a document processing apparatus according to a first embodiment of the present invention.

FIG. 2 is a flowchart illustrating a document processing method in the apparatus.

FIG. 3 is a diagram showing an example of a recognition target area and a character of a document image processed by the apparatus.

FIG. 4 is a diagram showing an extracted character string region of a document image processed by the same device and an example of character recognition.

FIG. 5 is a block diagram illustrating a configuration of a document processing apparatus according to a second embodiment of the present invention.

FIG. 6 is a flowchart showing a document processing method in the apparatus.

FIG. 7 is a diagram showing an example of a recognition target area and code information of a document image processed by the same device.

FIG. 8 is a diagram showing an extracted character string area of a document image processed by the same device and an example of code recognition.

FIG. 9 is a block diagram illustrating a configuration of a document processing apparatus according to a third embodiment of the present invention.

FIG. 10 is a flowchart illustrating a document processing method in the apparatus.

FIG. 11 is a diagram illustrating an example of a recognition target region and a seal imprint of a document image processed by the same device.

FIG. 12 is a diagram showing an example of recognizing an imprint area of a document image processed by the apparatus.

FIG. 13 is a block diagram illustrating a configuration of a document processing apparatus according to a fourth embodiment of the present invention.

FIG. 14 is a flowchart illustrating a document processing method in the apparatus.

FIG. 15 is a diagram illustrating an example in which a recognition target area of a document image processed by the apparatus is deleted.

[Explanation of symbols]

 10, 20, 30, 40 ... Image input unit 11 ... Character recognition unit 12, 22, 42 ... Command determination unit 13, 23, 43 ... Instruction database unit 14, 24, 34, 45 ... Processing unit 21 ... Code recognition unit 31 … Seal recognition unit 32… Judgment unit 33… Stamp database unit 41… Recognition unit 44… Instruction erasure unit

 ──────────────────────────────────────────────────の Continued on the front page F term (reference) 5B047 AA01 CA01 CB09 CB22 5B064 AA01 BA01 CA08 5C062 AA02 AA05 AB02 AB22 AB40 AB42 AB46 AC22 AC35 AE15

Claims (14)

[Claims] 1. An input means for inputting a document image, and, for a document image input by the input means, information in which a content of a processing instruction is described in a predetermined portion or a tag of the document image. Recognizing means for extracting and recognizing; database means preliminarily storing the content of the processing instruction; comparing the recognition result recognized by the recognizing means with the content of the processing instruction stored in the database means Determining means for determining the contents of a processing instruction described in the document image input from the input means, and determining whether the document image has been input from the input means in accordance with the processing instruction determined by the determining means. And a processing unit for executing a process for each document image. 2. The method according to claim 1, wherein the recognizing means recognizes the character information when the content of the processing command is described as character information in a predetermined portion or a tag of the document image input from the input means. 2. The document processing apparatus according to claim 1, further comprising character recognition means. 3. A method according to claim 1, wherein said recognizing means includes a step of: when a content of the processing instruction is described as code information in a predetermined portion or a tag of the document image input from said input means.
2. The document processing apparatus according to claim 1, further comprising code recognition means for recognizing the code information. 4. The apparatus according to claim 1, wherein the determining unit includes an instruction determining unit configured to determine whether the recognized processing instruction is executable. Sending a processing instruction notifying the processing instruction to the processing means when it is determined that the recognized processing instruction is not executable.
Document processing device as described. 5. The determination means sends a processing instruction to the processing means so as to perform a default process predetermined by the input means when the information describing the processing instruction is not detected in the recognition unit. 2. The document processing apparatus according to claim 1, further comprising means. 6. When a content of a processing instruction is described in a predetermined portion or a tag of the document image input by the input means, the processing means outputs the document image for each document image. 2. The document processing apparatus according to claim 1, further comprising an erasing means for erasing the contents of the processing instruction before executing the processing. 7. Inputting a document image, extracting and recognizing, from the input document image, information in which the content of a processing instruction is described in a predetermined portion or a tag of the document image; By comparing the recognized recognition result with the content of the processing instruction stored in the database in advance, the content of the processing instruction described in the input document image is determined, and according to the determined processing instruction, A document processing method characterized by performing a process for each document image on the input document image. 8. When a content of a processing instruction is described as character information in a predetermined portion or a tag of the input document image, the character information is recognized as a character. Document processing method described. 9. The method according to claim 7, wherein when the content of the processing instruction is described as code information in a predetermined portion or a tag of the input document image, the code information is recognized. Document processing method. 10. When judging the content of the processing instruction, it is further judged whether or not the recognized processing instruction is executable,
If it is determined that the recognized processing instruction is executable,
8. The method according to claim 7, wherein the processing of the document image input by the recognized command is executed, and when it is determined that the recognized processing command is not executable, the fact is notified. Document processing method. 11. A method for performing a predetermined default process when information describing a processing instruction is not detected in an input document image when determining the content of the processing instruction. 8. The method according to claim 7, wherein
Document processing method described. 12. When the content of a processing command is described in a predetermined portion or a tag of the input document image, before executing the process for each document image, 8. The document processing method according to claim 7, wherein the contents of the processing instruction are deleted. 13. An input means for inputting a document image, and for a document image input by the input means, a predetermined portion of the document image or imprint data attached to a tag is extracted and recognized. Recognition means, database means storing a plurality of imprint data in advance, by comparing the recognition result of the imprint data recognized by the recognition means with the contents of the imprint data stored in the database means, Determining means for determining the content of the imprint data given to the document image input from the input means; and determining the content of the imprint data determined by the determining means with respect to the document image input from the input means. A document processing apparatus comprising: processing means for executing a predetermined process. 14. A document image is input. Imprint data attached to a predetermined portion of the document image or a tag is extracted and recognized from the input document image. By comparing the contents of the imprint data stored in advance with the database means,
Determining a content of the seal imprint data given to the input document image, and performing a predetermined process on the input document image in accordance with the determined content of the seal imprint data; Processing method.