Image processing apparatus, image processing method, and storage medium

• US 7,949,155 B2
• Filed: 09/12/2005
• Issued: 05/24/2011
• Est. Priority Date: 03/08/2005
• Status: Expired due to Fees

• Current Assignee: Fuji Xerox Company Limited (Fujifilm Holdings Corporation)
• Original Assignee: Fuji Xerox Company Limited (Fujifilm Holdings Corporation)
• Inventors: Kimura, Shunichi
• Primary Examiner(s): Bali; Vikkram
• Assistant Examiner(s): Brooks; Julian D
• Application Number:
  US11/223,008
• Publication Number:
  US 20060204099A1
• Time in Patent Office: 2,080 Days
• Field of Search: 382/177, 382/112, 382/222, 382/228
• US Class Current: 382/112
• CPC Class Codes: G06V 10/98 Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern

Abstract

An image processing apparatus includes image memory that stores an image; character recognition rate acquisition unit that segments the image stored in the image memory into a plurality of partial images and acquiring a character recognition rate for each partial image; image quality assessment unit that calculates a parameter showing the image quality of the image based on the character recognition rates of the plural partial images acquired by the character recognition rate acquisition unit; and output unit that outputs assessment results obtained by the image quality assessment unit.

Claims

1. An image processing apparatus comprising:

an image memory that stores an image corresponding to each page of a document and obtained by scanning the document;

a character recognition rate acquisition unit that segments the image stored in the image memory into a plurality (n) of partial images and acquires a character recognition rate for each partial image;

an image quality assessment unit that calculates a parameter showing the image quality of the image for said each page, based on the character recognition rates of the plurality of partial images acquired by the character recognition rate acquisition unit, and decides whether a scanning error is present by comparing the parameter with a threshold value; and

an output unit that outputs a number of a page containing the scanning error, and an assessment result determined based on the parameter, and also outputs a message inquiring as to whether re-scanning is necessary if the image quality assessment unit decides that the scanning error is present, wherein

the parameter is calculated using the formula;

Qs=1−

(α

_max−

α

_max) or

Qs=α

_min/α

_max

where a α

_max and α

_min are maximum and minimum values of character recognition rate α

_i for each partial image, and Qs is a real number satisfying the condition 0≦

Qs≦

1,

the character recognition rate a, is normalized using the formula;

2. The image processing apparatus according to claim 1, wherein the character recognition rate acquisition unit further comprises:

an image segmentation unit that segments the image stored in the image memory into the plurality of partial images; and

a character recognition unit that performs character recognition processing on each of the plurality of partial images segmented by the image segmentation unit.

3. The image processing apparatus according to claim 1, wherein the character recognition rate acquisition unit further comprises:

a character recognition unit that performs character recognition processing on the image stored by the image memory; and

an image segmentation unit that segments the image that has been subjected to character recognition processing by the character recognition unit into a plurality of partial images.

4. The image processing apparatus according to claim 1, wherein the parameter reflects a positional measure that indicates a position in the distribution of the character recognition rates of the plurality of partial images.

5. The image processing apparatus according to claim 4, wherein the positional measure is any of the maximum value, minimum value, mean value, median value, or mode value of the character recognition rates of the plurality of partial images.

6. The image processing apparatus according to claim 1, wherein the parameter reflects a distributional measure showing the spread of the distribution of the character recognition rates of the plurality of partial images.

7. The image processing apparatus according to claim 6, wherein the parameter is calculated using at least two measures from among the maximum value, minimum value, mean value, median value, or mode value of the character recognition rates of the plurality of partial images.

8. The image processing apparatus according to claim 7, wherein the distributional measure is any of the variance, standard deviation, confidence interval width, or distance from uniform distribution of the character recognition rates of the plurality of partial images.

9. The image processing apparatus according to claim 1, wherein the parameter is a value determined based both on the positional measure, which indicates a position in the distribution of the character recognition rates of the plurality of partial images, and on the distributional measure, which indicates the spread of the distribution of the character recognition rates of the plurality of partial images.

10. The image processing apparatus of claim 1, wherein the output unit notifies a user of an option to replace the stored image with a replacement image.

11. The image processing apparatus of claim 1, wherein the assessment results are at least one numerical value corresponding to the image quality of the image.

12. The image processing apparatus of claim 1, wherein the assessment results indicate a binary condition of whether or not the image quality meets a predetermined condition.

13. The image processing apparatus according to claim 1, wherein if a number characters contained in the partial image is smaller than a predetermined number, the image quality assessment unit calculates the parameter based on character recognition rates other than a character recognition rate of the partial image.

14. An image processing method comprising:

scanning a document;

storing an image corresponding to each page of the document based at least in part on the scanning of the document;

segmenting the image into a plurality (n) of partial images;

acquiring character recognition rates for the image;

calculating a parameter showing the image quality of the image for said each page, based on the acquired character recognition rates of the plurality of partial images;

deciding whether a scanning error is present by comparing the parameter with a threshold value; and

outputting a number of a page containing the scanning error, and an assessment result determined based on the parameter, and also outputting a message inquiring as to whether re-scanning is necessary if a decision that the scanning error is present has been made, wherein

the parameter is calculated using the formula;

Qs=1−

(α

_max−

α

_max) or

Qs=α

_min/α

_max

where α

_max and α

_min are maximum and minimum values of character recognition rate α

_ifor each partial image, and Qs is a real number satisfying the condition 0≦

Qs≦

1,

the character recognition rate a, is normalized using the formula;

15. The image processing method of claim 14, further comprising:

outputting to a user an option to replace the stored image with a replacement image.

16. The image processing method of claim 14, wherein the assessment results are at least one numerical value corresponding to the image quality of the image.

17. The image processing method of claim 14, wherein the assessment results indicate a binary condition of whether or not the image quality meets a predetermined condition.

18. The image processing method of claim 14, further comprising:

outputting to a user an option to replace the stored image with a replacement image.

19. The image processing method of claim 14, wherein the assessment results are at least one numerical value corresponding to the image quality of the image.

20. The image processing method of claim 14, wherein the assessment results indicate a binary condition of whether or not the image quality meets a predetermined condition.

21. The image processing method according to claim 14, wherein if a number of characters contained in the partial image is smaller than a predetermined number, the parameter is calculated based on character recognition rates other than a character recognition rate of the partial image.

22. A non-transitory computer readable storage medium storing a computer readable program executable by a computer for causing the computer to execute a process, the process comprising:

scanning a document;

storing an image corresponding to each page of the document based at least in part on the scanning of the document;

segmenting the image into a plurality (n) of partial images;

acquiring character recognition rates for the image;

calculating a parameter showing the image quality of the image for said each page, based on the acquired character recognition rates of the plurality of partial images;

deciding whether a scanning error is present by comparing the parameter with a threshold value; and

outputting a number of a page containing the scanning error, and an assessment result determined based on the parameter, and also outputting a message inquiring as to whether re-scanning is necessary if a decision that the scanning error is present has been made;

wherein

the parameter is calculated using the formula;

Qs=1−

(α

_max−

α

_max) or

Qs=α

_min/α

_max

where α

_max and α

_min are maximum and minimum values of character recognition rate α

_ifor each partial image, and Qs is a real number satisfying the condition 0≦

Qs≦

1,

the character recognition rate α

_i, is normalized using the formula;

23. The non-transitory computer readable storage medium according to claim 22, wherein if a number of characters contained in the partial image is smaller than a predetermined number, the parameter is calculated based on the character recognition rates other than a character recognition rate of the partial image.