JPH07200721A - Character recognition electronic mail device - Google Patents

Abstract

PURPOSE:To facilitate moving of distributed processing character recognition system. CONSTITUTION:A character recognition electronic mail device 1 is connected to the computer of a user for exchanging electronic mail through a network. Then, character images are transmitted from the computer of the user to the character recognition electronic mail device 1 by the electronic mail. This electronic mail is received by an electronic mail reception processing part 11 and transformed to any prescribed data format suitable for the device by an image information data format transforming part 13. Then, a character image area for each character is segmented from the character images in the electronic mail by a character image area segmenting part 14. Afterwards, character recognition is performed by a character recognition part 15 and as the character recognized result, a character code is transmitted from an electronic mail transmission processing part 12 as the electronic mail. The computer of the user receives this electronic mail, extracts the character code and processes a document.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a character recognition electronic mail apparatus for character-recognizing image information sent by electronic mail and transmitting the recognition result by electronic mail.

[0002]

2. Description of the Related Art Generally, a character recognition device reads image information as image data, compares it with a character pattern prepared in advance by pattern recognition, and outputs a character code as a result. The hardware of such a character recognition device comprises a computer to which an image scanner is connected. Such a computer was a so-called standalone type in the early days, but in recent years,
It has begun to shift to a distributed processing system by a plurality of computers connected via a communication line such as a network.
That is, when the character recognition device is configured by such a system, the image information is read by the image scanner by one computer and the character recognition process is performed by the other computer connected via the network.

FIG. 2 is a block diagram showing the configuration of a conventional character recognition system. The illustrated system comprises a document processing device 21 and a character recognition device 22, both of which are connected via a communication line. The document processing device 21 includes an image reading unit 23, an image area cutout unit 24, an image transmitting unit 25, a character receiving unit 26, and a document processing unit 27. The character recognition device 22 includes an image receiving unit 28, a character recognition unit 29, and a character recognition unit 29. The character transmission unit 30 is included. The document processing device 21 inputs a character image from an image reading device such as an image scanner,
The image reading unit 23 receives the input character image. Then, the received character image is passed to the image area cutout unit 24. The image area cutout unit 24
A character area for each character is cut out from the passed character image and passed to the image transmitting unit 25. The image transmission unit 25 uses the character recognition device 2 for each line of the passed character area image for each character.
Send to 2.

The character recognition device 22 receives the character area image transmitted from the document processing device 21 by the image reception unit 28 and transfers it to the character recognition unit 29. The character recognition unit 29 compares the passed character area image with the character pattern dictionary data prepared in advance. Then, the character code corresponding to the most approximated character pattern is output as a character recognition result and passed to the character transmitting unit 30. Character transmission unit 3 that received the character code
0 transmits the character code to the document processing device 21 which has transmitted the character area image. Then, the document processing device 21
The character receiving unit 26 receives the character code and passes it to the document processing unit 27. The document processing unit 27 receives the character code as input and performs document processing. This document process is a process of collecting character codes for each word and correcting the word into a correct word by collating it with a word dictionary. As a result, even when the character code of the character recognition result of the character recognition device 22 is somewhat incorrect, a meaningful word can be output.

FIG. 3 is a time chart showing the character recognition processing procedure of the system of FIG. First, the document processing device 2
In 1, the line segmentation for each line and the character segmentation for each character of each segmented line are performed. The time required for this processing is L as shown in FIG.
1, L2 and L3. The cut out character area image is
As shown in FIG. 4A, the data is transmitted line by line. As shown in FIG. 3B, this transmission time is R1,
R2 and R3.

Next, in the character recognition device 22, character recognition is performed for each character of one line received from the document processing device 21. The time required for this processing is L11, L12, etc., as shown in FIG. As shown in FIG. 4B, the character codes K111 to K11 from the first candidate to the fourth candidate for the first character and the second character by the character recognition.
4, K211 to K214, etc. are obtained. Also, FIG.
As shown in (c), along with the character codes K111 to K114 and the like, distance values S111 to S114 representing the degree of approximation between the matching pattern of each candidate character and the character area image may be calculated and output. Such a character recognition result is received by the document processing device 21 via a communication line, as shown in FIG. This reception time is shown in FIG.
As shown in (b), they are T1, T2, and T3 (see JP-A-4-24777 and JP-A-4-24778).

[0007]

However, the above-mentioned conventional technique has the following problems. That is, in the conventional system shown in FIG.
To communicate data from the character recognition device 22 to the character recognition device 22,
The communication protocol shown in (a) is required, and the character recognition device 22
4 to communicate data from the document processing device 21 to the document processing device 21.
The communication protocol shown in (b) or (c) is required. That is, a dedicated communication protocol is required between the document processing device 21 and the character recognition device 22. Therefore, when a user who has performed character recognition using a stand-alone type computer introduces a character recognition dedicated device such as the character recognition device 22, the user uses dedicated communication software for this device. You must also install it on your computer. Therefore, there is a problem that it is difficult to introduce the system shown in FIG.

The present invention has been made in view of the above points, and it is an object of the present invention to provide a character recognition electronic mail device which facilitates introduction of a distributed processing type character recognition device.

[0009]

A character recognition electronic mail apparatus of the present invention receives an electronic mail transmitted from a computer connected via a network, and from the received electronic mail, image information and its transmission side are transmitted. An electronic mail reception processing unit that extracts an electronic mail address, a character image area cutout unit that cuts out a character image area from the image information extracted by the electronic mail reception processing unit, and character image information cut out by the character image area cutout unit A character recognition unit for performing character recognition processing regarding the above, and an electronic mail including the character recognition result recognized by the character recognition unit and the electronic mail address of the transmission side is transmitted to a computer connected via the network. And an electronic mail transmission processing unit for performing the same.

[0010]

The character recognition electronic mail apparatus of the present invention is connected to a computer of a user who can send and receive electronic mail via a network. Then, the character image is sent from the user's computer to the character recognition electronic mail device by electronic mail. This e-mail is received by the e-mail reception processing unit and converted into a predetermined data format. Then, the character image area cutout unit cuts out a character image area for each character from the character image in the electronic mail. Then, the character recognition unit performs character recognition, and the character code that is the character recognition result is transmitted as an electronic mail from the electronic mail transmission processing unit. The user's calculator receives this email and
The character code is extracted and the document is processed.

[0011]

Embodiments of the present invention will now be described in detail with reference to the drawings. FIG. 1 is a block diagram of an embodiment of the character recognition electronic mail apparatus of the present invention. FIG. 5 is a configuration diagram of a computer network including the device of FIG. Figure 5
In, the character recognition electronic mail device 1, computers 2, 4
Are connected to the network 3. The character recognition electronic mail device 1 includes a mailbox for storing messages addressed to the computers 2 and 4. Generally, an electronic mail system communicates by using a computer to store and accumulate information such as documents, images, programs, and voices as electronic messages in a mailbox, and retrieve messages from the mailbox as appropriate. It is a system that does. In the present invention, since such an electronic mail system is used for the character recognition system, the character recognition electronic mail apparatus 1 receives the image information transmitted from the computer 2 as an electronic mail, and after the character recognition, the mail box is received. Accumulate in. Although such a mailbox is not particularly shown, the character recognition electronic mail device 1 and the computer 2 are not shown.
It consists of a part of memory.

The character recognition electronic mail device 1 shown in FIG.
As shown in FIG. 1, it comprises an electronic mail reception processing unit 11, a character image area cutout unit 14, a character recognition unit 15, an electronic mail transmission processing unit 12, and an image information data format conversion unit 13. The e-mail reception processing unit 11 receives the e-mail transmitted from the computer 2 connected via the network 3 shown in FIG. 5, and extracts the image information and the e-mail address of the sender from the received e-mail. . The character image area cutout unit 14 cuts out a character image area from the image information extracted by the electronic mail reception processing unit 11. This is a known one, and there are various configurations. For example, a portion of a group of black pixels of binary image data is taken out, divided into each line, and further divided into each character. Can be done by The character recognition unit 15 performs a character recognition process on the character image information cut out by the character image area cutout unit 14. This is also known, and specifically, it is provided with a collation pattern for collating with image information as dictionary data, and by comparing with this, the character code corresponding to the most similar collation pattern is extracted. Recognize.

The electronic mail transmission processing unit 12 sends an electronic mail including the character recognition result recognized by the character recognition unit 15 and the sender's electronic mail address to the network 3
It is transmitted to the computer 2 connected via. Further, the electronic mail transmission processing unit 12 transmits the image information indicating the character image area cut out by the character image area cutting unit 14 together with the character recognition result. Image information data format conversion unit 13
Converts the data format of the image information extracted by the e-mail reception processing unit 11 into a predetermined data format suitable for the device, and inputs it to the character image area cutout unit 14. By providing the image information data format conversion unit 13, the character recognition electronic mail apparatus 1 can be easily installed even when the data format of the user's computer is different from the data format of the character recognition electronic mail apparatus 1.

FIG. 6 is an explanatory diagram showing the flow of processing in the above system. First, the user sends a fax 3
1. Image information is taken into the user's computer 2 from the image scanner 32, the camera 33, etc. (U1). When the user wants to perform character recognition on the captured image information, the user creates an electronic mail in which the captured image information or the image information obtained by cutting out the portion of the captured image information for which character recognition is performed is written (U2). Here, when the electronic mail is a multimedia electronic mail that can send both image data and code data, the image information is written as it is in the electronic mail using its basic function. If the email is a text email that can send only code data, the image data is encoded as text and written in the email.

Then, the user sends an electronic mail in which the image information is written from the computer 2 via the network 3 to the character recognition electronic mail apparatus 1 (U3). The character recognition electronic mail device 1 receives the electronic mail in which the image information is written (M1). Then, the character recognition electronic mail device 1
Performs character recognition of the image information written in the electronic mail and creates an electronic mail in which the character recognition result is written (M2). After that, the character recognition electronic mail device 1 transmits the electronic mail in which the result of the character recognition is written to the user (M3).

Next, the operation of the character recognition electronic mail apparatus 1 corresponding to step M2 of FIG. 6 will be described with reference to FIGS. 1 and 7. First, the email reception processing unit 11 extracts image information from the received email and sends the image information to the image information data format conversion unit 13 (S1). Further, the electronic mail reception processing unit 11 extracts the electronic mail address of the user from the received electronic mail and sends the electronic mail address of the user to the electronic mail transmission processing unit 12 (S2). The image information data format conversion unit 13 converts the data format of the extracted image information from the data format used by the user in the computer 2 to the data format used in the character recognition electronic mail device 1, and the data format is converted. The image information is sent to the character image area cutout unit 14 (S3).

The character image area cutout unit 14 cuts out the character image area including the character image information from the image information for each character in each line, and sends the cut out character image area to the character recognition unit 15. Further, the coordinates of the frame surrounding the clipped character image area are written in the image information so that the clipped character image area can be seen, and the image information indicating the clipped character image area is sent to the image information data format conversion unit 13 (S4).
The character recognition unit 15 performs character recognition by comparing the character image information with a matching pattern prepared in advance, and sends the result of character recognition to the email transmission processing unit 12 (S).
5).

The image information data format conversion unit 13 converts the data format of the image information indicating the cut-out character image area from the data format used in the character recognition electronic mail apparatus 1 to the data format used in the computer 2 by the user. Then, the image information indicating the converted character image area of the converted data format is sent to the electronic mail transmission processing unit 12 (S6). The electronic mail transmission processing unit 12 creates an electronic mail including the result of character recognition and the image information indicating the cut-out character image area (S7). Then, the email transmission processing unit 12 transmits the created email to the mailbox of the user's email address (S8).

According to the above-described embodiment, when changing the stand-alone type computer to the distributed processing type, the user does not need to install new software, and the original computers 2 and 4 are connected to the network 3
Just connect to. Therefore, the character recognition electronic mail device 1 can be easily introduced. Moreover, since the original data format of the computers 2 and 4 can be converted into the data format of the character recognition electronic mail apparatus 1 by the image information data format conversion unit 13, the data format of the computers 2 and 4 can be converted to that of the character recognition electronic mail apparatus 1. There is no need to match the data format. Furthermore, since the cutout result of the character image area cutout unit 14 is also obtained, the document processing using this can be performed in the computers 2 and 4. In the above-mentioned embodiment, the case where only one character recognition electronic mail device 1 is connected to the network 3 has been described, but the present invention is not limited to this, and a plurality of devices may be connected. Of course.

[0020]

As described above, according to the character recognition electronic mail apparatus of the present invention, the image information and the character code are communicated by electronic mail, so that the stand-alone type computer is changed to the distributed processing type. In this case, the user does not need to install new software, only needs to connect the existing computer to the network, and the character recognition electronic mail device can be easily installed. Also, by providing the image information data format conversion unit, the original data format of the computer can be converted to the data format of the character recognition electronic mail device, so it is necessary to match the data format of the computer with the data format of the character recognition electronic mail device. There can be no. Further, the electronic mail transmission processing unit also transmits the cutout result of the character image area cutout unit, so that the computer can perform the document processing utilizing the cutout result.

[Brief description of drawings]

FIG. 1 is a block diagram of an embodiment of a character recognition electronic mail device of the present invention.

FIG. 2 is a block diagram showing a configuration of a conventional character recognition system.

FIG. 3 is a time chart explaining a character recognition processing procedure of the system of FIG.

FIG. 4 is an explanatory diagram of a data format in a conventional character recognition system.

FIG. 5 is a block diagram showing a configuration of a character recognition system according to the present invention.

6 is a flowchart illustrating a processing procedure of the character recognition system in FIG.

7 is a flowchart illustrating a processing procedure of the character recognition electronic mail device of FIG.

[Explanation of symbols]

 1 Character Recognition E-mail Device 11 E-mail Reception Processing Section 12 E-mail Transmission Processing Section 13 Image Information Data Format Conversion Section 14 Character Image Area Cutting Section 15 Character Recognition Section

Claims (3)

[Claims] 1. An electronic mail reception processing unit that receives an electronic mail sent from a computer connected via a network and extracts image information and an electronic mail address of the sender from the received electronic mail, and the electronic mail. A character image area cutout unit that cuts out a character image area from the image information extracted by the mail reception processing unit, a character recognition unit that performs character recognition processing on the character image information cut out by the character image area cutout unit, and the character An electronic mail transmission processing unit for transmitting an electronic mail including the character recognition result recognized by the recognition unit and the electronic mail address of the transmission side to a computer connected via the network. Character recognition email device. 2. An image information data format conversion section for converting the data format of the image information extracted by the electronic mail reception processing section into a predetermined data format and inputting it to the character image area cutout section. The character recognition electronic mail device according to claim 1. 3. The character recognition electronic mail apparatus according to claim 1, wherein the electronic mail transmission processing unit transmits image information indicating a cut-out character image area together with the character recognition result.