Digital camera and document processing system using the digital camera

• US 6,812,995 B2
• Filed: 08/08/2001
• Issued: 11/02/2004
• Est. Priority Date: 12/09/1997
• Status: Expired due to Fees

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Honma, Hideo
• Primary Examiner(s): Font, Frank G.
• Assistant Examiner(s): Brown, Khaled
• Application Number:
  US09/923,366
• Publication Number:
  US 20010046036A1
• Time in Patent Office: 1,182 Days
• Field of Search: 355/18, 355/19, 355/21, 355/32, 355/41, 358/515, 358/501, 358/530, 358/403, 382/289, 250/208.1
• US Class Current: 355/18
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/166 Normalisation of pattern dimensions
• CPC Class Codes: G06V 30/18076 by analysing connectivity, e.g. edge linking, connected component analysis or slices

Abstract

A digital camera capable of performing accurate document reading, and a document processing system utilizing the digital camera. In the document processing system, a document is divided into blocks and each block is sensed by a CCD 103; perspective correction is performed on the image data of each of the plurality of images obtained by divisionally sensing the document; and OCR process is performed on the corrected image data to convert the corrected image data to text data. The converted text data, corresponding to the image data of each of the plurality of images, is combined into one text data, and the combined text data is outputted for printing.

Claims

1. A document processing system comprising:

input means which input image data corresponding to each of a plurality of block images which are obtained from divisionally sensing a single object by using a camera;

correction means which correct a distortion of each of the plurality of block images caused by the camera'"'"'s signal sensing in units of block images in accordance with an instruction inputted by a user of the camera;

combining means which combine the image data corresponding to each of the plurality of block images corrected by said correction means, into one entire body of image data, taking into consideration an adjacent or overlapping portion in the plurality of block images; and

output means which output the entire body of image data obtained by said combining means.

2. The document processing system according to claim 1, wherein said input means includes a digital camera having a CCD, the digital camera comprising assisting means for assisting to divide an image, drawn on a page of print medium, into a plurality of blocks and input a plurality of images in a block unit.

3. The document processing system according to claim 1, further comprising selection means for selecting the block images to be corrected by said correction means in accordance with an instruction inputted by the user.

4. The document processing system according to claim 1, further comprising character recognition means for performing a character recognition process on each of the plurality of block images represented by the image data inputted by said input means, and

wherein said combining means further comprises:

detecting means for detecting a portion which is adjacent to each other or overlapped with each other in the plurality of block images, based on image data corresponding to each of the plurality of images; and

connection means for connecting text data, generated by said character recognition means, corresponding to the image data of each of the plurality of images, based on a detection result of said detecting means.

5. The document processing system according to claim 1, wherein said output means is a printer.

6. An information processing apparatus adapted to perform document processing in a document processing system, comprising:

storage means which store image data corresponding to each of a plurality of block images which are obtained from manually and divisionally sensing a single object by using a digital camera;

correction means which correct a distortion of each of the plurality of block images caused by the manual and divisional sensing in units of block images in accordance with an instruction inputted by a user; and

combining means which combine the image data corresponding to each of the plurality of block images corrected by said correction means, into one entire body of image data, taking into consideration an adjacent or overlapping portion in the plurality of block images.

7. The apparatus according to claim 6, further comprising:

character recognition means for performing a character recognition process on the image data corresponding to each of the plurality of block images stored by said storage means,

wherein said combining means combine text data, generated by said character recognition means, which corresponds to each of the plurality of block images.

8. The apparatus according to claim 7, wherein said combining means comprises:

detecting means for detecting a portion, in the plurality of block images, adjacent to or overlapped with another portion in the plurality of block images, based on the image data corresponding to the plurality of block images; and

connecting means for connecting the text data which corresponds to each of the plurality of block images, based on a detection result from said detecting means.

9. The apparatus according to claim 8, wherein said detecting means detect the adjacent or overlapped portion in units of a character, and said connecting means connect the text data corresponding to each of the plurality of block images in units of a character, based on the detection result so as to form a complete text.

10. An image processing method comprising the steps of:

inputting image data corresponding to each of a plurality of block images which are obtained from divisionally sensing a single object by using a camera;

correcting a distortion of each of the plurality of block images in units of block images;

combining the image data corresponding to each of the plurality of the corrected block images into one entire body of image data; and

outputting the combined entire body of image data.

11. The method according to claim 10, wherein the distortion of each of the plurality of block images is caused by the camera'"'"'s divisional sensing.

12. The method according to claim 10, wherein the step of correcting includes correcting the distortion in accordance with an instruction inputted by a user of the camera.

13. The method according to claim 10, wherein the step of combining includes taking into consideration an adjacent or overlapping portion in the plurality of block images.

14. The method according to claim 10, wherein the step of inputting includes assisting to divide an image, drawn on a page of print medium, into a plurality of blocks, and inputting a plurality of divided images in a block unit, by using a camera having a CCD.

15. The method according to claim 14, further comprising the step of performing a character recognition process on each of the plurality of block images represented by the inputted image data,

wherein the step of combining further comprises the steps of:

detecting a portion which is adjacent to each other or overlapped with each other in the plurality of block images, based on image data corresponding to each of the plurality of images; and

connecting text data, generated by the character recognition process, corresponding to the image data of each of the plurality of images, based on the detection result.

16. The method according to claim 10, further comprising the step of selecting the block images to be corrected in accordance with an instruction inputted by a user of the camera.

17. The method according to claim 10, wherein the step of outputting includes outputting the entire image by a printer.

18. An image processing method comprising the steps of:

storing image data corresponding to each of a plurality of block images which are obtained from divisionally sensing a single object by using a camera, into a memory;

correcting a distortion of each of the plurality of block images caused by the divisional sensing in units of block images; and

combining the image data corresponding to each of the plurality of the corrected block images into one entire body of image data.

19. The method according to claim 18, wherein the distortion of each of the plurality of block images is caused by the camera'"'"'s divisional sensing.

20. The method according to claim 18, wherein the step of correcting includes correcting the distortion in accordance with an instruction inputted by a user of the camera.

21. The method according to claim 18, wherein the step of combining includes taking into consideration an adjacent or overlapping portion in the plurality of block images.

22. The method according to claim 18, further comprising the step of performing a character recognition process on the image data corresponding to each of the plurality of block images stored in the memory,

wherein the step of combining includes combining text data, generated by the character recognition process, which corresponds to each of the plurality of block images.

23. The method according to claim 22, wherein the step of combining comprises the steps of:

detecting a portion, in the plurality of block images, adjacent to or overlapped with another portion in the plurality of block images, based on the image data corresponding to the plurality of block images; and

connecting the text data which corresponds to each of the plurality of block images, based on a detection result obtained in said detecting step.

24. The method according to claim 23, wherein the step of detecting includes detecting the adjacent or overlapped portion in units of a character, and the step of connecting includes connecting the text data which corresponds to each of the plurality of block images in units of a character, based on the detection result so as to form a complete text.

25. An image processing method comprising the steps of:

sensing divisionally a single object of the camera in block units in accordance with a predetermined division pattern;

performing an OCR process on image data corresponding to each of the plurality of the sensed block images so as to convert the image data to text data; and

combining the converted text data which corresponds to the image data of each of the plurality of block images into one entire body of text data.

26. The method according to claim 25, wherein the step of combining includes taking into consideration an adjacent or overlapping portion in the plurality of block images.

27. The method according to claim 26, further comprising the steps of:

instructing to set either a document sensing mode for sensing a document or a natural image sensing mode for sensing an object other than the document in accordance with a type of the object;

instructing to select one of the plurality of division patterns in accordance with an instruction inputted by a user of the camera; and

performing correction on the image data corresponding to each of the plurality of sensed block images, based on the selected division pattern.

28. The method according to claim 27, wherein the document sensing mode is a mode for sensing the object as a binary monochrome image, and the natural image sensing mode is a mode for sensing the object as a multi-valued color image.

29. The method according to claim 27, wherein the step of performing correction includes correcting a distortion of the sensed image in a person-machine interactive manner with respect to the horizontal and vertical directions, and the clockwise direction and counter-clockwise direction with the origin at the center of the displayed image, while referring to the image displayed on a display screen.

30. The method according to claim 26, wherein the step of combining comprises the steps of:

detecting a portion adjacent to each other or overlapped with each other in the plurality of block images, based on the image data of each of the plurality of block images; and

connecting text data corresponding to the image data of each of the plurality of block images, based on a detection result obtained in said detecting step.

31. The method according to claim 25, further comprising the steps of displaying a plurality of division patterns on a display screen, each being selectively used for dividing an image of the object into a plurality of block images.

32. The method according to claim 31, wherein said display displays a sensed image.

33. The method according to claim 31, wherein the step of displaying includes displaying a sensing sequence on each block included in each of the division patterns.

34. The method according to claim 33, wherein the step of displaying includes displaying a sensing sequence number upon sensing the object, based on the selected division pattern.

35. An image processing method, comprising the steps of:

displaying a division pattern used for dividing an image of an object into a plurality of block images and a sensing sequence for each block included in the division pattern;

sensing the object by using a camera, based on the division pattern;

performing an OCR process on image data corresponding to each of the plurality of the sensed block images, based on the division pattern, to convert the image data to text data; and

combining the converted text data which corresponds to the image data of each of the plurality of block images, into one body of text data.

36. The method according to claim 35, wherein the step of displaying includes displaying a sensing sequence number upon sensing the object, based on the division pattern.

37. An image processing apparatus comprising:

an input unit for inputting image data corresponding to each of a plurality of block images which are obtained from divisionally sensing a single object by using a camera;

a control unit for correcting a distortion of each of the plurality of block images in units of block images, and combining the image data corresponding to each of the plurality of the corrected block images into one entire body of image data; and

an output unit for outputting the combined entire image data.

38. An image processing apparatus comprising:

a memory for storing image data corresponding to each of a plurality of block images which are obtained from divisionally sensing a single object using the camera;

a control unit, adapted to correct a distortion of each of the plurality of block images caused by the divisional sensing in units of block images, and to combine the image data corresponding to each of the plurality of the corrected block images, into one entire body of image data.