Optical character recognition device and method and recording medium

• US 20020012462A1
• Filed: 06/04/2001
• Published: 01/31/2002
• Est. Priority Date: 06/09/2000
• Status: Active Grant

• Current Assignee: Minolta Co., Ltd. (Konica Minolta Inc.)
• Original Assignee: Minolta Co., Ltd. (Konica Minolta Inc.)
• Inventors: Fujiwara, Yoko
• Granted Patent: US 6,788,810 B2
• Time in Patent Office: Days
• US Class Current: 382/165
• CPC Class Codes: G06V 30/413 Classification of content, e.g. text, photographs or tables

Abstract

An image processing method or device invented to reduce the ratio of erroneously recognized non-character elements in optical character recognition (OCR) regarding a color document that includes character images and other types of images, wherein the extracted character image data is checked to determine whether a color change exists in each character image, and wherein if no color change exists, the character image data is converted into character code data, but where a color change does exist, the character image data is not converted into character code data.

Claims

1. An image processor comprising:

an obtaining unit that obtains image data that corresponds to an document image including character images and other types of images;

an extracting unit that extracts the character images from the image data;

an detecting unit that checks whether a color change exists in the extracted character images based on the extracted image data; and

a generating unit that generates character code data based on the image data for the character images as to which there is no color change.

2. An image processing method comprising the steps of:

obtaining image data that corresponds to an document image including character images and other types of images;

extracting the character images from the image data;

checking whether a color change exists in the extracted character images based on the extracted image data; and

generating character code data based on the image data for the character images not having a color change.

3. An optical character recognition device that converts character image data included in image data into character code data, said device comprising:

a character image data extracting unit that extracts the character image data from the image data;

a color change detecting unit that checks whether a color change exists in the character image data extracted by the character image data extracting unit; and

a converting unit that converts the character image data as to which no color change was detected by the color change detecting unit into character code data.

4. An optical character recognition device according to claim 3, wherein said converting unit does not convert character image data including a color change into character code data.

5. An optical character recognition device according to claim 3, wherein said character image data extracting unit extracts character image data on an individual character basis.

6. An optical character recognition device according to claim 3, wherein said character image data extracting unit extracts character image data on an individual word basis.

7. An optical character recognition method that converts the character image data included in image data into character code data, comprising the steps of:

extracting character image data from the image data;

checking whether a color change exists in the extracted character image data; and

converting character image data as to which there is no color change into character code data.

8. A computer-readable recording medium that records an optical character recognition program that converts the character image data included in image data into character code data, said program comprising the steps of:

extracting character image data from the image data;

checking whether there is a color change in the extracted character image data; and

converting character image data as to which there is no color change into character code data.

9. An image processor comprising:

an obtaining unit that obtains image data that corresponds to an document image including character images and other types of images;

an extracting unit that extracts the character images from the image data;

an detecting unit that checks whether a color change exists in the extracted character images based on the extracted image data; and

a control unit that generates character code data based on the image data for the character images not having a color change, and does not generate character code data based on the image data for the character images having a color change.