APPARATUS AND METHOD FOR PROCESSING IMAGE

• US 20090232397A1
• Filed: 03/13/2009
• Published: 09/17/2009
• Est. Priority Date: 03/14/2008
• Status: Abandoned Application

• Current Assignee: NEC Corporation
• Original Assignee: NEC Corporation
• Inventors: HARA, MASANORI
• Application Number:
  US12/403,731
• Publication Number:
  US 20090232397A1
• Time in Patent Office: Days
• US Class Current: 382/169
• CPC Class Codes: G06T 2207/20008 Globally adaptive
• CPC Class Codes: G06T 2207/20104 Interactive definition of region of interest [ROI]
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 5/40 using histogram techniques
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06V 10/273 removing elements interfering with the pattern to be recognised
• CPC Class Codes: G06V 40/1347 Preprocessing; Feature extraction

Abstract

An image processing apparatus includes a data storage section configured to store an image data of a streaked pattern image as a gray-scale image and a direction distribution data indicating a direction distribution of a streaked pattern noise in a first area of the streaked pattern image; and a first image enhancing section configured to execute a first image enhancing process in the first area. The direction distribution data relates a first position as a position of a first pixel in the first area and a first direction as a direction of the streaked pattern noise in the first position. The first image enhancing section determines a first reference area as a local area which contains the first pixel based on the first direction such that the first reference area is contained in the first area, and calculates a post-process density as a density after the first image enhancing process in the first pixel based on a first density histogram in the first reference area.

Claims

1. An image processing apparatus comprising:

a data storage section configured to store an image data of a streaked pattern image as a gray-scale image and a direction distribution data indicating a direction distribution of a streaked pattern noise in a first area of the streaked pattern image; and

a first image enhancing section configured to execute a first image enhancing process in the first area,

wherein the direction distribution data relates a first position as a position of a first pixel in the first area and a first direction as a direction of the streaked pattern noise in the first position,

said first image enhancing section determines a first reference areas as a local area which contains the first pixel based on the first direction such that the first reference area is contained in the first area, and calculates a post-process density as a density after the first image enhancing process in the first pixel based on a first density histogram in the first reference area.

2. The image processing apparatus according to claim 1, further comprising:

a data generating section; and

a direction estimating section,

wherein said data generating section generates a first area data indicating the first area and a representative line data indicating representative lines of the streaked pattern noise in response to an input operation, and

said direction estimating section executes calculation to a direction of the streaked pattern noise in a position of each pixel within the first area based on the first area data and the representative line data and generates the direction distribution data of based on the calculation result.

3. The image processing apparatus according to claim 1, wherein said first image enhancing section determines a second reference area as a local area containing a second pixel based on a second direction as a direction of the streaked pattern noise in a second position as a position of the second pixel within the first area such that the second reference area is contained in the first area,

the first pixel is contained in the second reference area, and

said first image enhancing section calculates the post-process density from a pre-process density as a density before the image process in the first pixel such that the post-process density is contained in a predetermined density range, through a linear transformation using a local maximum as the smallest one of a maximum density in the first density histogram and a maximum density of the second density histogram in the second reference area and a local minimum as the largest one of a minimum density in the first density histogram and a minimum density in the second density histogram.

4. The image processing apparatus according to claim 3, wherein the local maximum is Pmax, the local minimum is Pmin, a minimum of the density range is Tmin, a maximum of the density range is Tmax, the pre-process density is Gb, and the post-process density is Ga, and

said first image enhancing section calculates the post-process density based on the following equation:

Ga=(Gb−

Pmin)(Tmax−

Tmin)/(Pmax−

Pmin)+Tmin

5. The image processing apparatus according to claim 1, wherein said first image enhancing section determines the first reference area to have a shape curved along a curved line contained in the streaked pattern noise.

6. The image processing apparatus according to claim 5, wherein said first image enhancing section detects a third pixel contained in the first area based on the first position and the first direction, detects a fourth pixel contained in the first area based on a third position as a position of the third pixel and a third direction as a direction of the streaked pattern noise in the third pixel, and determines the first reference area such that the fourth pixel is contained the first reference area.

7. The image processing apparatus according to claim 1, further comprising:

a second image enhancing section configured to execute a second image enhancing process in a second area as an area other than the first area of the streaked pattern image,

wherein said second image enhancing section determines a second reference area as a local area which contains the second pixel within the second area such that the second reference area is contained in the second area, calculates a density after the second image enhancing process in the second pixel based on a second density histogram in the second reference area, and

the first reference area and the second reference area are determined such that maximum ranges are same, based on one of a local histogram equalizing method and a contrast stretch method in the first image enhancing process and the second image enhancing process, respectively.

8. An image processing apparatus comprising:

a data storage section configured to store an image data of a streaked pattern image as a gray-scale image and a direction distribution data indicating a direction distribution of a streaked pattern noise in a first area of the streaked pattern image; and

a first image enhancing section configured to execute a first image enhancing process in the first area,

wherein said first image enhancing section determines for each of pixels in the first area, a reference area as a local area containing the pixel based on a direction of the streaked pattern noise in a position of the pixel such that the reference area is contained in the first area, to determine a plurality of the reference areas which contains a first pixel in the first area,

each of a plurality of density histograms of the plurality of reference areas has a maximum density and a minimum density, and there are a plurality of maximum densities and a plurality of minimum densities for the first pixel, and

said first image enhancing section calculates a post-process density as a density after the first image enhancing process to the first pixel from a pre-process density as a density before the image process to the first pixel such that the-post-process density is contained in a predetermined density range, through a linear transformation using a local maximum as the smallest one of the plurality of maximum densities and a local minimum as the largest one the plurality of minimum densities.

9. An image processing apparatus comprising:

a data storage section configured to store an image data of a streaked pattern image as a gray-scale image and a direction distribution data indicating a direction distribution of a streaked pattern noise in a first area-of the streaked pattern image; and

a first image enhancing section configured to execute a first image enhancing process in the first area,

wherein the direction distribution data relates a first position as a position of a first pixel in the first area and a first direction as a direction of the streaked pattern noise in the first position,

said first image enhancing section determines a first reference area as a local area containing the first pixel based on the first direction such that the first reference area is contained in the first area, and calculates a post-process density as a density of the first pixel after the first image enhancing-process, based on a first density histogram in the first reference area.

10. An image processing method comprising:

executing a first image enhancing process on a first area of a streaked pattern image as a gray-scale image,

wherein a streaked pattern noise exists in the first area,

said executing comprises;

determining a first reference area as a local area containing a first pixel based on a first direction as a direction of the streaked pattern noise in a first position as a position of the first pixel in the first area such that the first reference area is contained in the first area; and

calculating a post-process density as a density after the first image enhancing process on the first pixel based on a first density histogram in the first reference area.

11. The image processing method according to claim 10, further comprising:

generating a direction distribution data indicating a direction distribution of the streaked pattern noise,

wherein the direction distribution data relates the first position and the first direction,

said generating comprises;

generating a first area data indicating the first area and a representative line data indicating representative lines of the streaked pattern noise based on an input operation; and

calculating the direction of the streaked pattern noise on a position of each pixel in the first area based on the first area data and the representative line data.

12. The image processing method according to claim 10, wherein said executing a first image enhancing process comprises:

determines a second reference area as a local area containing a second pixel based on a second direction as the direction of the streaked pattern noise on a second position as a position of the second pixel in the first area such that the second reference area is contained in the first area, and

the first pixel is contained in the second reference area,

said calculating the post-process density comprises;

calculating the post-process density from a pre-process density as a density before the image process in the first pixel, such that the post-process density is contained in a predetermined density range, through a linear transformation using a local maximum as the smallest one of a maximum density in a first density histogram and a maximum density in a second density histogram in the second reference area, and a local minimum of the largest one of a minimum density in the first density histogram and a minimum density in the second density histogram.

13. The image processing method according to claim 12, wherein the local maximum is Pmax, the local minimum is Pmin, a minimum of the density range is Tmin, a maximum of the density range is Tmax, the pre-process density is Gb, and the post-process density is Ga, and

said calculating the post-process density comprises:

calculating the post-process density based on the following equation;

Ga=(Gb−

Pmin)(Tmax−

Tmin)/(Pmax−

Pmin)+Tmin

14. The image processing method according to claim 10, wherein said determining the first reference area comprises:

determining the first reference area to have a shape curved along a curved line contained in the streaked pattern noise.

15. The image processing method according to claim 14, wherein said determining the first reference area comprises:

detecting a third pixel contained in the first area based on the first position and the first direction;

detecting a fourth pixel contained in the first area based on a third position as a position of the third pixel and a third direction as a direction of the streaked pattern noise in the third pixel; and

determining the first reference area such that the fourth pixel is contained the first reference area.

16. The image processing method according to claim 10, further comprising:

executing a second image enhancing process on a second area as an area other than the first area of the streaked pattern image,

wherein said executing the second image enhancing process comprises;

determining a second reference area as a local area containing a second pixel in the second area such that the second reference area is contained in the second area; and

calculating a density after the second image enhancing process on the second pixel based on a second density histogram in the second reference area, and

the first reference area and the second reference area are determined to be coincident with each other in maximum range, based on one of a local histogram equalizing method and a local contrast stretch method in the first image enhancing process and the second image enhancing process.

17. An image processing method comprising:

executing a first image enhancing process on a first area of a streaked pattern image as a gray-scale image,

wherein a streaked pattern noise exists in the first area,

said executing comprises;

determining for each of pixels in the first area, a reference area as a local area containing the pixel based on a direction of the streaked pattern noise in a position of the pixel such that the reference area is contained in the first area, to determine a plurality of the reference areas which contains a first pixel in the first area; and

calculating a post-process density as a density after the first image enhancing process to the first pixel,

each of a plurality of density histograms of the plurality of reference areas has a maximum density and a minimum density, and there are a plurality of maximum densities and a plurality of minimum densities for the first pixel, and

said calculating the post-process density comprises;

calculating the post-process density from a pre-process density as a density before the image process to the first pixel such that the post-process density is contained in a predetermined density range, through a linear transformation using a local maximum as the smallest one of the plurality of maximum densities and a local minimum as the largest one the plurality of minimum densities.

18. A computer-readable recording medium in which a computer-readable program is recorded to realize an image processing method which comprises:

executing a first image enhancing process on a first area of a streaked pattern image as a gray-scale image,

wherein a streaked pattern noise exists in the first area,

said executing comprises;

determining a first reference area as a local area containing a first pixel based on a first direction as a direction of the streaked pattern noise in a first position as a position of the first pixel in the first area such that the first reference area is contained in the first area; and

calculating a post-process density as a density after the first image enhancing process on the first pixel based on a first density histogram in the first reference area.

19. The computer-readable recording medium according to claim 18, wherein the image processing method further comprises:

generating a direction distribution data indicating a direction distribution of the streaked pattern noise,

wherein the direction distribution data relates the first position and the first direction,

said generating comprises;

generating a first area data indicating the first area and a representative line data indicating representative lines of the streaked pattern noise based on an input operation; and

calculating the direction of the streaked pattern noise on a position of each pixel in the first area based on the first area data and the representative line data.

20. The computer-readable recording medium according to claim 19, wherein said executing a first image enhancing process comprises:

determines a second reference area as a local area containing a second pixel based on a second direction as the direction of the streaked pattern noise on a second position as a position of the second pixel in the first area such that the second reference area is contained in the first area, and

the first pixel is contained in the second reference area,

said calculating the post-process density comprises;

calculating the post-process density from a pre-process density as a density before the image process in the first pixel, such that the post-process density is contained in a predetermined density range, through a linear transformation using a local maximum as the smallest one of a maximum density in a first density histogram and a maximum density in a second density histogram in the second reference area, and a local minimum of the largest one of a minimum density in the first density histogram and a minimum density in the second density histogram.

21. The computer-readable recording medium according to claim 20, wherein the local maximum is Pmax, the local minimum is Pmin, a minimum of the density range is Tmin, a maximum of the density range is Tmax, the pre-process density is Gb, and the post-process density is Ga, and

said calculating the post-process density comprises:

calculating the post-process density based on the following equation;

Ga=(Gb−

Pmin)(Tmax−

Tmin)/(Pmax−

Pmin)+Tmin

22. The computer-readable recording medium according to claim 18, wherein said determining the first reference area comprises:

determining the first reference area to have a shape curved along a curved line contained in the streaked pattern noise.

23. The computer-readable recording medium according to claim 22, wherein said determining the first reference area comprises:

detecting a third pixel contained in the first area based on the first position and the first direction;

detecting a fourth pixel contained in the first area based on a third position as a position of the third pixel and a third direction as a direction of the streaked pattern noise in the third pixel; and

determining the first reference area such that the fourth pixel is contained the first reference area.

24. The computer-readable recording medium according to claim 18, wherein the image processing method further comprises:

executing a second image enhancing process on a second area as an area other than the first area of the streaked pattern image,

wherein said executing the second image enhancing process comprises;

determining a second reference area as a local area containing a second pixel in the second area such that the second reference area is contained in the second area; and

calculating a density after the second image enhancing process on the second pixel based on a second density histogram in the second reference area, and

the first reference area and the second reference area are determined to be coincident with each other in maximum range, based on one of a local histogram equalizing method and a local contrast stretch method in the first image enhancing process and the second image enhancing process.