JPH07234917A - Image processor - Google Patents

Abstract

PURPOSE:To provide an image processor capable of easily switching the image processing of a specific area. CONSTITUTION:A character part is sampled from a document image inputted from a scanner 1 and stored in memory 3 by an area dividing part 4, and it is identified whether a character is a type or a hand-written character by a character identifying part 6, and the character is outputted by, for example, applying masking processing to a hand-written character area, or by separating a type character area from the hand-written character area corresponding to an identified result. Also, a type character is converted to a different kind of type character by recognizing the character sampled at the area dividing part 4, and for example, converting the character area to the type character corresponding to a recognized result, and outputting by separating the hand- written character area converted to the type character.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus for switching image processing for each specified area in a document image.

[0002]

2. Description of the Related Art Conventionally, in an image processing apparatus which switches image processing for each specified area, an area to be specified is input and designated by an external operation or the like according to the content of image processing, or a document is identified by using an identification marker or the like. It is generally performed by manual designation such as designation by filling in a closed loop in the image, and various image processing such as masking processing is performed on the document image according to the designated area information. Was configured to do.

[0003]

By the way, there is a document in which a personal memo is added to an arbitrary area for the purpose of supplementing the content of the document image in the document image. You may want to delete the writing and reproduce the original document image.

However, in the above conventional method, the area of the memo writing portion is manually input in advance,
It is necessary to perform the masking process, and when there are a large number of document images to be processed, it is necessary to specify the area one by one, and there is a drawback that a troublesome operation must be repeated.

It is an object of the present invention to provide an image processing device which can easily switch the image processing of a specific area.

[0006]

According to the present invention, an input means for inputting a document image, a storage means for storing the document image, an extracting means for extracting a character portion from the stored document image, and the extracted character. Has a character identifying means for identifying whether it is a printed character or handwriting, and a control means for switching image processing according to the identification result, and according to the identification result, for example, a masking process is performed on a handwritten character area. In this case, the printed character area and the handwritten character area are separately output.

The present invention further comprises an input means for inputting a document image, a storage means for storing the document image, an extracting means for extracting a character portion from the stored document image, and a character recognizing means for recognizing characters. , And a control means for switching the image processing according to the recognition result, according to the recognition result, for example, to convert a handwritten character area into print characters, or separate the handwritten character area converted into print characters. It is used to output or convert print characters into different kinds of print characters.

[0008]

1 is a block diagram showing the configuration of a first embodiment of the present invention.

The image processing apparatus of this embodiment includes a scanner circuit 1 for capturing a document image, a memory circuit 3 for storing the captured document image, a memory control circuit 2 for controlling the memory circuit 3, and a document image An area division circuit 4 for dividing an area such as a character, a figure, or a photograph according to the characteristics, and an area memory circuit 5 for storing the area division result
A character information identification circuit 6 for identifying whether a character is a printed character or a handwritten character based on the character area division result, a character information memory circuit 7 for storing the character information identification result, and for each divided area of the document image. An image processing circuit 8 capable of adaptive processing and a system control circuit 9 for controlling the entire system of the image input / output device are provided.

FIG. 2 is an explanatory diagram showing an example of a document image for explaining the operating principle of the present invention. 2A shows the original document image, and FIG. 2B shows the output result. Further, in each image, the document image 20 is composed of a print character 21 representing a title, a print character 22, a handwritten character 23 added as a private memo, and a plurality of pie charts 24.

Next, the operation of this embodiment will be described.

First, the document image shown in FIG. 2A is scanned by the scanner circuit 1 and fetched, and stored in the memory circuit 3 via the memory control circuit 2 controlled by the system control circuit 9.

Next, the document image data read from the memory circuit 3 via the memory control circuit 2 is supplied to the area dividing circuit 4, and here, according to the characteristics of the document image data, FIG. As shown in FIG. 5, after dividing into areas such as characters and figures, the area memory circuit 5 stores the information such as the image content and the position of the area which is the result of the division for each area.

Next, referring to the division result stored in the area memory circuit 5, the system control circuit 9 reads the document image data of the character area portion from the memory circuit 3 and supplies it to the character information identification circuit 6. Control the system. The character information identification circuit 6 extracts the characteristics of the character, identifies whether the character is printed or handwritten according to the characteristics, and stores the identification result in the character information memory circuit 7.

Next, the document image data read from the memory circuit 3 is supplied to the image processing circuit 8 via the memory control circuit 2. On the other hand, in the image processing circuit 8,
The area division result read out from the area memory circuit 5 and the character information identification result read out from the character information memory circuit 7 are also supplied. The image processing in which the processing content can be adaptively switched is performed and output.

As shown in FIG. 2B, here,
The handwritten character area 23 indicated by the shaded area is deleted, or the handwritten character area 23 is separated and output separately.

As described above, it is possible to reproduce a document image with a personal memo or the like added.

FIG. 3 is a block diagram showing the configuration of the second embodiment of the present invention. In FIG. 3, those having the same functions as those in FIG. 1 are designated by the same reference numerals and the description thereof will be omitted.

The image processing apparatus according to the second embodiment is provided with a character information recognition circuit 10 and a dictionary memory circuit 11 instead of the character information identification circuit 6.

Since the operation of this embodiment is partly common to that of the first embodiment, common parts will be omitted and different parts will be described.

In FIG. 3, referring to the area division result stored in the area memory circuit 5, the character image data of the character area portion is read from the memory circuit 3 and supplied to the character information recognition circuit 10. The control circuit 9 controls the system.

In the character information recognition circuit 10, character characteristics are extracted, and the character recognition is performed by referring to and compared with the character characteristics of a typed character or handwritten character registered in the dictionary memory circuit 11 in advance. Information memory circuit 7
Memorized in.

Next, the document image data read from the memory circuit 3 is supplied to the image processing circuit 8 via the memory control circuit 2. On the other hand, in the image processing circuit 8,
The area division result read out from the area memory circuit 5 and the character information recognition result read out from the character information memory circuit 7 are also supplied. The image processing in which the processing content can be adaptively switched is performed and output.

As shown in FIG. 2B, here,
The handwritten character area 23 indicated by the shaded area is deleted, or the handwritten character area is separated and output separately, as in the case of the first embodiment. It is possible to convert to another type of print characters, or to convert the handwritten character area into print characters.

As described above, it is possible to reproduce a document image with a private memo added.

[0026]

As described above, according to the present invention,
By effectively utilizing the area division result extracted from the document image and the character information identification result or the character information recognition result, it is possible to easily switch the image processing of the specific area with a relatively simple configuration, and to have an excellent function. There is an effect that it is possible to provide the image processing device that has.

[Brief description of drawings]

FIG. 1 is a block diagram showing a first embodiment of the present invention.

FIG. 2 is an explanatory diagram showing an example of a document image for explaining the operation principle of the present invention.

FIG. 3 is a block diagram showing a second embodiment of the present invention.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... Scanner circuit, 2 ... Memory control circuit, 3 ... Memory circuit, 4 ... Area division circuit, 5 ... Area memory circuit, 6 ... Character information identification circuit, 7 ... Character information memory circuit, 8 ... Image processing circuit, 9 ... System control circuit, 10 ... Character information recognition circuit, 11 ... Dictionary memory circuit.

 ─────────────────────────────────────────────────── ─── Continuation of front page (72) Inventor Akihiko Sakai 3-30-2 Shimomaruko, Ota-ku, Tokyo Canon Inc. (72) Inventor Michiko Hirayu 3-30-2 Shimomaruko, Ota-ku, Tokyo Canon Within the corporation

Claims (7)

[Claims] 1. An input unit for inputting a document image, a storage unit for storing the document image, an extracting unit for extracting a character portion from the stored document image, and whether or not the extracted character is a printed character or handwritten. Character identification means for identifying whether there is,
An image processing apparatus comprising: a control unit that switches image processing according to the identification result. 2. The image processing apparatus according to claim 1, wherein the image processing is to perform masking processing on a handwritten character area according to the identification result and output the masked character area. 3. The image processing apparatus according to claim 1, wherein the image processing is to separate and output a print character area and a handwritten character area according to the identification result. 4. An input unit for inputting a document image, a storage unit for storing the document image, an extraction unit for extracting a character portion from the stored document image, a character recognition unit for recognizing characters, and the recognition result. An image processing apparatus, comprising: a control unit that switches image processing according to the above. 5. The image processing apparatus according to claim 4, wherein the image processing is to convert a handwritten character area into a printed character according to the recognition result. 6. The image processing apparatus according to claim 5, wherein the image processing separates and outputs a handwritten character area converted into a print character according to the recognition result. 7. The image processing apparatus according to claim 6, wherein the image processing is to convert a print character into a different type of print character according to the recognition result.