Method for recognizing abnormal image

• US 7,480,420 B2
• Filed: 09/04/2002
• Issued: 01/20/2009
• Est. Priority Date: 09/04/2002
• Status: Expired due to Term

• Current Assignee: Intellectual Ventures I LLC (Intellectual Ventures LLC)
• Original Assignee: Transpacific IP Group Limited
• Inventors: Wang, Kuo-Jeng
• Primary Examiner(s): Bella; Matthew C.
• Assistant Examiner(s): LIEW, ALEX KOK SOON
• Application Number:
  US10/233,597
• Publication Number:
  US 20040131253A1
• Time in Patent Office: 2,330 Days
• Field of Search: 382/112
• US Class Current: 382/274
• CPC Class Codes: G06T 7/0006 using a design-rule based approach
• CPC Class Codes: G06V 10/993 Evaluation of the quality of the acquired pattern
• CPC Class Codes: H04N 1/00002 Diagnosis, testing or measuring; Detecting, analysing or monitoring not otherwise provided for error detection, error correction or monitoring in digital computers or digital computer components G06F11/00
• CPC Class Codes: H04N 1/00005 relating to image data
• CPC Class Codes: H04N 1/00013 Reading apparatus
• CPC Class Codes: H04N 1/00031 Testing, i.e. determining the result of a trial H04N1/00029 takes precedence; using test signals for transmission mode changing H04N2201/33371
• CPC Class Codes: H04N 1/00053 out of service, i.e. outside of normal operation
• CPC Class Codes: H04N 1/00068 Calculating or estimating

Abstract

A method for recognizing abnormal image is disclosed. The invention utilizes level comparisons of adjacent image lines to determine if there is any abnormal image amid an image picture and whether the abnormal image belongs to shading or LBB. The method comprises the following steps. First of all, two adjacent image lines having level values P_i and P_i−1 are selected. Then an absolute value of the P_i and the P_i−1 is calculated. Next the absolute value is compared with a value X. When the absolute value is smaller than X, then the image lines are determined as normal. On the contrary, when the absolute value is larger than X, then at least one of the image lines is determined as abnormal. Moreover, another two image lines having level values P_i+1 and P_i−2 separately adjacent the image lines having level values P_i and the P_i−1 are selected. An absolute value of the P_i+1 and the P_i−2 is calculated and the absolute value of the P_i+1 and the P_i−2 is compared to the value X. When the absolute value of the P_i+1 and the P_i−2 is smaller than X, then the image lines having level values P_i and P_i−1 are determined as shading. However, when the absolute value of the P_i+1 and the P_i−2 is larger than X, then the image lines having level values P_i, P_i−1, P_i+1 and P_i−2 are determined as LBB.

Claims

1. A method comprising:

selecting two adjacent image line, using a processor, each line representing a plurality of pixels, the image lines having respective level values P_i and P<sub>i−

1</sub>, the values P_i and P<sub>i−

1</sub> each representing the brightness level of the pixels represented by a corresponding one of the image lines;

calculating an absolute value of a difference between said values P_i and P<sub>1−

1</sub>;

comparing said absolute value of the difference between said values P_i and P<sub>i−

1</sub> to a value X, wherein if said absolute value of the difference between said values P_i and P<sub>i−

1</sub> is smaller than said value X, said two adjacent image lines are determined as normal, and wherein if said absolute value of the difference between said values P_i and P<sub>i−

1</sub> is larger than said value X, said two adjacent image lines are determined as abnormal;

if said absolute value of the difference between said values P_i and P<sub>i−

1</sub> is larger than said value X, selecting an image line having a level value P_i+1 adjacent to said image line having the level value P_i and further selecting an image line having a level value P<sub>i−

2</sub> adjacent to said image line having the level value P<sub>i−

1</sub>, each of the newly selected image lines representing a plurality of pixels, the values P_i+1 and P<sub>i−

2</sub> of the newly selected image lines each representing the brightness level of the pixels represented by a corresponding one of the newly selected image lines;

calculating an absolute value of a difference between said values P_i+1 and P<sub>i−

2</sub>; and

comparing said absolute value of the difference between said values P_i+1 and P<sub>i−

2</sub> to said value X.

2. The method according to claim 1, further comprising:

if said absolute value of the difference between said values P_i+1 and P<sub>i−

2</sub> is smaller than said value X, recognizing a shading abnormality for said image lines having level values P_i and P<sub>i−

1</sub>.

3. The method according to claim 1, further comprising:

if said absolute value of the difference between said values P_i+1 and P<sub>i−

2</sub> is larger than said value X, recognizing a dark band abnormality for said image lines having level values P_i, P<sub>i−

1</sub>, P_i+1 and P<sub>i−

2</sub>.

4. An apparatus, comprising:

a light source to illuminate an object to be scanned with light;

a component to convert at least a portion of light reflected from the object into a plurality of scan lines; and

circuitry configured to;

select two adjacent image lines having respective level values P_i and P<sub>i−

1</sub>, each of the values P_i, and P<sub>i−

1</sub> representing the brightness of a plurality of pixels represented by a corresponding one of the image lines;

determine a difference between said values P_i and P<sub>i−

1</sub>;

compare said difference between said values P_i and P<sub>i−

1</sub> to a first threshold value;

according to whether said difference exceeds the first threshold value, select an image line having a level value P_i+1 adjacent to said image line having the level value P_i and further select an image line having a level value P<sub>i−

2</sub> adjacent to said image line having the level value P<sub>i−

1</sub>, each of the values P_i+1 and P<sub>i−

2</sub> representing the brightness of a plurality of pixels represented by a corresponding one of the image lines;

determine a difference between said values P_i+1 and P<sub>i−

2</sub>; and

compare said difference between said values P_i+1 and P<sub>i−

2</sub> to a second threshold value.

5. The apparatus according to claim 4, wherein the circuitry is further operable to, if said difference between said values P_i and P_i−

1 does not exceed said first threshold value, recognize no abnormality for said image lines having level values P_i and P<sub>i−

1</sub>.

6. The apparatus according to claim 4, wherein the circuitry is further operable to, if said difference between said values P₁ and P_i−

1 exceeds said first threshold value, recognize an abnormality for said two image lines having level values P_i and P<sub>i−

1</sub>.

7. The apparatus according to claim 4, wherein the circuitry is further operable to, if said difference between said values P_i+1 and P_i−

2 does not exceed said second threshold value, recognize a shading abnormality for said image lines having level values P₁ and P<sub>i−

1</sub>.

8. The apparatus according to claim 4, wherein the circuitry is further operable to, if said absolute value of the difference between said values P_i+1 and P_i−

2 exceeds said second threshold value, recognize a dark band abnormality for said image lines having level values P_i P<sub>i−

1</sub>, P_i+1and P<sub>i−

2</sub>.

16. The apparatus of claim 4, wherein the threshold values are the same.

17. The apparatus of claim 4, wherein the circuitry is further operable to output an indication of an abnormality if the first threshold value is exceeded.

9. A method comprising:

selecting two adjacent image lines having respective level values P_i and P<sub>i−

1</sub>, using a processor, the values P_i and P<sub>i−

1</sub> each representing the brightness of a plurality of pixels represented by a corresponding one of the image lines;

calculating a difference between said values P_i and P<sub>i−

1</sub>;

comparing said difference between said values P_i and P<sub>i−

1</sub> to a first threshold value;

if said difference between said values P_i and P<sub>i−

1</sub> is larger than said first threshold value, selecting an image line having a level value P_i+1 adjacent to said image line having the level value P_i and further selecting an image line having a level value P<sub>i−

2</sub> adjacent to said image line having the level value P<sub>i−

1</sub>, each of the values P_i+1 and P_i+2 representing the brightness of a plurality of pixels represented by a corresponding one of the image lines;

calculating a difference between said values P_i+1 and P<sub>i−

2</sub>; and

comparing said difference between said values P_i+1 and P<sub>i−

2</sub> to a second threshold value.

10. The method according to claim 9, further comprising if said difference between said values P_i and P_i−

1 is smaller than said first threshold value, recognizing no abnormality for said two image lines having level values P_i and P<sub>i−

1</sub>.

11. The method according to claim 9, further comprising if said difference between said values P_i+1 and P_i−

2 is smaller than said second threshold value, recognizing a shading abnormality for said image lines having level values P_i and P<sub>i−

1</sub>.

12. The method according to claim 9, further comprising if said difference between said values P_i+1 and P_i−

2 is larger than said second threshold value, recognizing a dark band abnormality for said image lines having level values P_i, P<sub>i−

1</sub>, P_i+1 and P<sub>i−

2</sub>.

18. The method of claim 9, further comprising:

recognizing an abnormality if the first threshold is exceeded; and

outputting an indication of the abnormality.

19. The method of claim 9, further comprising:

recognizing a shading abnormality if the first threshold is exceeded and the second threshold is not exceeded; and

outputting an indication of the shading abnormality.

20. The method of claim 9, further comprising:

recognizing a dark band abnormality if both the thresholds are exceeded; and

outputting an indication of the dark band abnormality.

13. An article comprising:

a storage medium having stored thereon instructions, that, if executed, result in;

selecting two adjacent image lines having level values P_i and P<sub>i−

1</sub>, the level values each representing the brightness of a plurality of pixels represented by a corresponding one of the image lines;

determining a difference between said values P_i and P<sub>i−

1</sub>;

comparing said difference between said values P_i and P<sub>i−

1</sub> to a first threshold value, wherein if said difference between said values P_i and P<sub>i−

1</sub> does not exceed said first threshold value, said two adjacent image lines are determined as normal, and wherein if said difference between said values P_i and P<sub>i−

1</sub> exceeds said first threshold value, said two adjacent image lines are determined as abnormal; and

if said difference between said values P_i and P<sub>i−

1</sub> exceeds said first threshold value, selecting an image line having a level value P_i+1 adjacent to said image line having the level value P_i and further selecting an image line having a level value P<sub>i−

2</sub> adjacent to said image line having the level value P<sub>i−

1</sub>, each of the values P_i+1 and P<sub>i−

2</sub> representing the brightness of a plurality of pixels represented by a corresponding one of the image lines;

determining a difference between said values P_i+1 and P<sub>i−

2</sub>; and

comparing said difference between said values P_i+1 and P<sub>i−

2</sub> to a second threshold value.

14. The article according to claim 13, further comprising:

if said difference between said values P_i+1 and P<sub>i−

2</sub> does not exceed said second threshold value, recognizing a shading abnormality for said image lines having level values P_i and P<sub>i−

1</sub>.

15. The article according to claim 13, further comprising:

if said difference between said values P_i+1 and P<sub>i−

2</sub> exceeds said second threshold value, recognizing a dark band abnormality for said image lines having level values P_i, P<sub>i−

1</sub>, P_i+1 and P<sub>i−

2</sub>.

21. The article according to claim 13, further comprising:

recognizing an abnormality if the first threshold is exceeded; and

outputting an indication of the abnormality.

22. A system, comprising:

means for comparing first brightness indications of first adjacent image lines to determine a first variance in brightness, each first brightness indication representing a plurality of pixels associated with a corresponding one of the first image lines;

means for determining whether the first variance exceeds a threshold value;

according to whether the first variance exceeds the threshold value, means for selecting second image lines that are adjacent to the first adjacent image lines;

means for comparing second brightness indications of the second image lines to determine a second variance in brightness, each second brightness indication representing a plurality of pixels associated with a corresponding one of the second image lines;

means for determining whether a scanning abnormality has occurred according to the comparisons; and

means for identifying a shading abnormality if the first variance exceeds the threshold value and the second variance does not exceed the threshold value.

23. The system of claim 22, further comprising means for identifying no abnormality if the first variance does not exceed the threshold value.

24. The system of claim 22, further comprising means for identifying a dark band abnormality if both variances exceed the threshold value.

25. The system of claim 22, wherein the brightness of the pixels accurately represents at least a portion of markings included on a scanned document if no scanning abnormality is determined.

26. The system of claim 22, wherein the second image lines are selected if the first variance exceeds the threshold value.

27. The system of claim 22, further comprising means for outputting an indication of whether the scanning abnormality has occurred.

28. An apparatus comprising:

a light source to illuminate an object to be scanned with light;

a component to convert at least a portion of the light representing the object into a plurality of scan lines; and

circuitry configured to;

analyze first brightness indications of first adjacent image lines to determine a first variance in brightness, each first brightness indication representing a plurality of pixels associated with a corresponding one of the first image lines;

according to a magnitude of the first variance, select second image lines that are adjacent to the first adjacent image lines;

analyze second brightness indications of the second image lines to determine a second variance in brightness, each second brightness indication representing a plurality of pixels associated with a corresponding one of the second image lines; and

determine whether a scanning abnormality has occurred according to the comparisons, and identify a dark band abnormality if the magnitudes exceed threshold values.

29. The system of claim 28, wherein the circuitry is further configured to identify no abnormality if the magnitude of the first variance does not exceed a respective one of the threshold values.

30. The system of claim 28, wherein the second image lines are selected if the magnitude of the first variance exceeds a respective one of the threshold values.

31. The system of claim 30, wherein the circuitry is further configured to identify a shading abnormality if a magnitude of the second variance does not exceed a respective one of the threshold values.

32. The system of claim 30, wherein the circuitry is further configured to output an indication of whether the scanning abnormality has occurred.