Image processing apparatus for discriminating image field of original document plural times and method therefor

• US 6,424,742 B2
• Filed: 08/20/1998
• Issued: 07/23/2002
• Est. Priority Date: 08/20/1997
• Status: Expired due to Term

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Kawakami, Haruko, Yamamoto, Naofumi, Rao, Gururaj
• Primary Examiner(s): Tran, Phuoc
• Application Number:
  US09/136,929
• Publication Number:
  US 20010016065A1
• Time in Patent Office: 1,433 Days
• Field of Search: 382/173, 382/176, 382/162, 382/237, 382/260, 382/205, 382/172, 382/164, 382/165, 382/274, 358/515, 358/538, 358/540, 358/462, 358/465, 358/1.9, 395/109
• US Class Current: 382/173
• CPC Class Codes: G06T 2207/10008 from scanner, fax or copier
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/162 Quantising the image signal
• CPC Class Codes: G06V 30/18105 related to colour
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text

Abstract

An image processing apparatus incorporating a field separating section for separating an original image into plural types of fields in response to a first image signal obtained at a rough density of the supplied original image, a characteristic value calculating section for calculating a characteristic value of the original image in response to a second image signal of the original image obtained at a density which is higher than the rough density, and a discrimination section for discriminating an image field of the original image in accordance with the characteristic value to correspond to the type of the field.

Claims

1. An image processing apparatus comprising:

first discrimination means for discriminating an original image into one of plural types of fields in response to a first image signal obtained at a first density of the original image;

characteristic value calculating means for calculating a characteristic change value in density, an average density and chroma of the original image in response to a second image signal of the original image obtained at a second density which is higher than the first density;

second discrimination means for selecting one of plural threshold values according to the type of field discriminated by the first discrimination means, and comparing the characteristic change value calculated by the characteristic value calculating means with the selected threshold value, so as to output a result of second discrimination; and

image processing means for processing predetermined image processes corresponding to the result of second discrimination of the image field performed by the second discrimination means, on the second image signal.

2. An image processing apparatus according to claim 1, wherein each of the first discrimination means and the characteristic value calculating means further includes scanning means for scanning the original image at the first density and then scanning the same at the second density, respectively.

3. An image processing apparatus according to claim 1, wherein the first discrimination means includes

means for separating the original image into at least a usual character field, characters on a background, a continuous gradation field and a dot gradation field.

4. An image processing apparatus according to claim 1, further including means for deleting a gradation image existing in a field which has not been discriminated by the first discrimination means as a gradation field and a gradation image existing in a field discriminated as a continuous gradation field.

5. An image processing apparatus according to claim 1, wherein the characteristic value calculating means includes means for calculating a characteristic value of the original image in each of unit regions having different lengths in a main scanning direction and a sub-scanning direction in response to the second image signal of the original image obtained at the second density which is higher than the first density.

6. An image processing apparatus according to claim 1, wherein the characteristic value calculating means includes means for calculating a segment component of the original image in a main scanning direction and a sub-scanning direction as the characteristic coverage value in response to the second image signal of the original image obtained at the second density which is higher than the first density.

7. An image processing method comprising the steps of:

a first discrimination step for discriminating an original image into one of plural types of fields in response to a first image signal obtained at a first density of the supplied original image;

a characteristic value calculating step for calculating a characteristic change value in density, average density, and chroma of the original image in response to a second image signal of the original image obtained at a second density which is higher than the first density;

a second discrimination step for selecting one of plural threshold values according to the one of the plural types of fields discriminated by the first discrimination step, and comparing the characteristic change value calculated by the characteristic value calculating step with the selected threshold value, so as to output a result of second discrimination step; and

an image processing step for processing predetermined image processes corresponding to the result of second discrimination step of the image field, on the second image signal.

8. An image processing method according to claim 7, wherein the first discrimination step includes scanning the original image at the first density and the characteristic value calculating step includes scanning the original image at the second density.

9. An image processing method according to claim 7, wherein the first discrimination step includes separating the original image into at least a usual character field, characters on a background, a continuous gradation field and a dot gradation field.

10. An image processing method according to claim 7, further including deleting a gradation image existing in a field which has not been discriminated in the first discrimination step as a gradation field and a gradation image existing in a field discriminated as a continuous gradation field.

11. An image processing method according to claim 7, wherein the characteristic value calculating step includes calculating a characteristic value of the original image in each of unit regions having different lengths in a main scanning direction and a sub-scanning direction in response to the second image signal of the original image obtained at the second density which is higher than the first density.

12. An image processing method according to claim 7, wherein the characteristic value calculating step includes calculating a segment component of the original image in a main scanning direction and a sub-scanning direction as the characteristic change value in response to the second image signal of the original image obtained at the second density which is higher than the first density.