Image processing device and image processing program

• US 6,798,913 B2
• Filed: 03/16/2001
• Issued: 09/28/2004
• Est. Priority Date: 03/27/2000
• Status: Expired due to Fees

• Current Assignee: Minolta Corporation Limited (Konica Minolta Inc.)
• Original Assignee: Minolta Corporation Limited (Konica Minolta Inc.)
• Inventors: Toriyama, Hideyuki
• Primary Examiner(s): Mehta, Bhavesh M.
• Assistant Examiner(s): Desire, Gregory M
• Application Number:
  US09/809,205
• Publication Number:
  US 20010026640A1
• Time in Patent Office: 1,292 Days
• Field of Search: 382/173, 382/175-176, 382/190, 382/199, 382/203, 382/229, 701/509, 701/517, 358/462, 715/521, 715/529, 715/531
• US Class Current: 382/229
• CPC Class Codes: G06V 10/25 Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text
• CPC Class Codes: H04N 1/3873 defined only by a limited number of coordinate points or parameters, e.g. corners, centre; for trimming

Abstract

An image processing device and a computer program product capable of accurately determining a user-desired region even when a region has been only roughly marked by a user, wherein a specific region within an image to be processed is detected; the image to be processed is allocated into a plurality of blocks; text included in the image to be processed is recognized; it is determined based on a result of text recognition that presence and absence of relevance between a first block which is partially included in the specific region and a second block which is entirely included in the specific region among the allocated blocks; and it is determined whether or not an image of the first block should be treated as an image belonging to the specific region in accordance with a result of determination as to the relevance.

Claims

1. An image processing device comprising:

a detector for detecting a specific region within an image to be processed;

an image allocator for allocating the image to be processed into a plurality of blocks;

a text recognizing unit for recognizing text included in the image to be processed;

a first determining unit for, on the basis of a recognition result of the text recognizing unit, determining presence and absence of relevance between a first block which is partially included in the specific region and a second block which is entirely included in the specific region among a plurality of blocks allocated by the image allocator; and

a second determining unit for determining whether or not an image of the first block should be treated as an image belonging to the specific region in accordance with a determination result of the first determining unit, wherein the second determining unit determines that the image of the first block should be treated as the image belonging to the specific region when the first determining unit has determined that there is relevance between the first block and the second block.

2. An image processing device as claimed in claim 1, further comprising an image processor for performing specific image processing on the specific region or regions outside the specific region based on a determination result of the second determining unit.

3. An image processing device as claimed in claim 2, wherein the specific image processing is erasure of the image.

4. An image processing device as claimed in claim 1, wherein the first determining unit determines whether or not a context is appropriate between an article comprised of text belonging to the first block and an article comprised of text belonging to the second block, and determines there is relevance between the first block and the second block when the context is appropriate.

5. An image processing device as claimed in claim 4, wherein the first determining unit has a dictionary recording a plurality of words and phrases, and determines the context is appropriate when a word or phrase straddling across a final or leading text line belonging to the first block and a leading or final text line belonging to the second block matches any words and phrases recorded in the dictionary.

6. An image processing device as claimed in claim 1, wherein the image allocator allocates the image to be processed based on lines within the image to be processed.

7. An image processing device as claimed in claim 1, wherein the image allocator allocates the image to be processed based on white spaces within the image to be processed.

8. An image processing device as claimed in claim 1, wherein the detector detects a closed region circumscribed by a line of specific color within the image to be processed as the specific region.

9. An image processing device as claimed in claim 1, further comprising an image reader for reading a document image to obtain data of the image to be processed.

10. A computer program product for making a computer execute processing which comprises the steps of:

1) detecting a specific region within an image to be processed;

2) allocating the image to be processed into a plurality of blocks;

3) recognizing text included in the image to be processed;

4) on the basis of a result of recognition at the step 3, determining presence and absence of relevance between a first block which is partially included in the specific region and a second block which is entirely included in the specific region among a plurality of blocks allocated at the step 2; and

5) determining whether or not an image of the first block should be treated as an image belonging to the specific region in accordance with a result of determination at the step 4,

wherein it is determined at the step 5 that the image of the first block should be treated as the image image belonging to the specific region when it has been determined at the step 4 that there is relevance between the first block and the second block.

11. A computer program product as claimed in claim 10, wherein the processing further comprises a step of performing specific image processing on the specific region or regions outside the specific region based on a result of determination at the step 5.

12. A computer program product as claimed in claim 11, wherein the specific image processing is erasure of the image.

13. A computer program product as claimed in claim 10, wherein at the step 4, it is determined whether or not a context is appropriate between an article comprised of text belonging to the first block and an article comprised of text belonging to the second block, and it is determined that there is relevance between the first block and the second block when the context is appropriate.

14. A computer program product as claimed in claim 13, wherein at the step 4, a dictionary recording a plurality of words and phrases is referred, and it is determined that the context is appropriate when a word or phrase straddling across a final or leading text line belonging to the first block and a leading or final text line belonging to the second block matches any words and phrases recorded in the dictionary.

15. A computer program product as claimed in claim 10, wherein the image to be processed is allocated at the step 2 based on lines within the image to be processed.

16. A computer program product as claimed in claim 10, wherein the image to be processed is allocated at the step 2 based on white spaces within the image to be processed.

17. A computer program product as claimed in claim 10, wherein a closed region circumscribed by a line of specific color within the image to be processed is detected as the specific region at the step 1.

18. A computer program product as claimed in claim 10, wherein the processing further comprises a step of reading a document image to obtain data of the image to be processed.