Image processing apparatus, image processing method, and computer-readable, non-transitory medium

• US 8,818,095 B2
• Filed: 07/06/2012
• Issued: 08/26/2014
• Est. Priority Date: 08/18/2011
• Status: Active Grant

• Current Assignee: PFU Limited (Fujitsu Limited)
• Original Assignee: PFU Limited (Fujitsu Limited)
• Inventors: Du, Jiyun
• Primary Examiner(s): COUSO, JOSE L
• Application Number:
  US13/543,544
• Publication Number:
  US 20130044952A1
• Time in Patent Office: 781 Days
• US Class Current: 382/170
• CPC Class Codes: G06T 2207/30176 Document
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/136 involving thresholding
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/162 Quantising the image signal
• CPC Class Codes: H04N 1/403 Discrimination between the two tones in the picture signal of a two-tone original

Abstract

There are provided an image processing apparatus, image processing method and a computer-readable, non-transitory medium that can binarize the input image so that the characters can be differentiated with high accuracy from the background area. The image processing apparatus includes an edge pixel extractor for extracting edge pixels from an input image, a first histogram generator for generating a first histogram based on a luminance value of each of the edge pixels, a second histogram generator for generating a second histogram based on a minimum luminance value among the luminance values of pixels neighboring each of the edge pixels, a static threshold calculator for obtaining a static threshold based on the first histogram and the second histogram, and a binarization unit for binarizing the input image by using the static threshold.

Claims

1. An image processing apparatus comprising:

an edge pixel extractor circuit for extracting edge pixels from an input image;

a first histogram generator circuit for generating a first histogram based on a luminance value of each of said edge pixels;

a second histogram generator circuit for generating a second histogram based on a minimum luminance value among the luminance values of pixels neighboring each of said edge pixels;

a static threshold calculator circuit for obtaining a static threshold based on said first histogram and said second histogram; and

a binarization circuit for binarizing said input image by using said static threshold.

2. The image processing apparatus according to claim 1, further comprising a dynamic threshold calculator circuit for obtaining, for each of said edge pixels, a dynamic threshold based on the luminance value of said edge pixel and on the minimum luminance value among the luminance values of the pixels neighboring said edge pixel, and wherein

said binarization circuit binarizes said edge pixel and said neighboring pixels by using said dynamic threshold obtained for said edge pixel, and binarizes other pixels than said edge pixel and said neighboring pixels by using said static threshold.

3. The image processing apparatus according to claim 1, wherein when a luminance value representing a converging point on a low-luminance side of said first histogram is equal to or higher than a luminance value representing a converging point on a high-luminance side of said second histogram, said static threshold calculator circuit sets said static threshold equal to an average value taken between the luminance value representing the converging point on the low-luminance side of said first histogram and the luminance value representing the converging point on the high-luminance side of said second histogram.

4. The image processing apparatus according to claim 1, wherein when the luminance value representing the converging point on the low-luminance side of said first histogram is lower than the luminance value representing the converging point on the high-luminance side of said second histogram, said static threshold calculator circuit sets said static threshold equal to a luminance value taken at a point where said first histogram intersects said second histogram.

5. The image processing apparatus according to claim 2, wherein said dynamic threshold calculator circuit calculates said dynamic threshold by taking a sum of the luminance value of said edge pixel and said minimum luminance value each multiplied by a predetermined weighting factor.

6. An image processing method comprising:

extracting edge pixels from an input image;

generating a first histogram based on a luminance value of each of said edge pixels;

generating a second histogram based on a minimum luminance value among the luminance values of pixels neighboring each of said edge pixels;

obtaining a static threshold based on said first histogram and said second histogram; and

binarizing said input image by using said static threshold, wherein the method is performed by one or more processors.

8. The image processing method according to claim 6, further comprising obtaining, for each of said edge pixels, a dynamic threshold based on the luminance value of said edge pixel and on the minimum luminance value among the luminance values of the pixels neighboring said edge pixel, and wherein

said binarizing comprises binarizing said edge pixel and said neighboring pixels by using said dynamic threshold obtained for said edge pixel, and binarizing other pixels than said edge pixel and said neighboring pixels by using said static threshold.

9. The image processing method according to claim 6, wherein when a luminance value representing a converging point on a low-luminance side of said first histogram is equal to or higher than a luminance value representing a converging point on a high-luminance side of said second histogram, setting said static threshold equal to an average value taken between the luminance value representing the converging point on the low-luminance side of said first histogram and the luminance value representing the converging point on the high-luminance side of said second histogram.

10. The image processing method according to claim 6, wherein when the luminance value representing the converging point on the low-luminance side of said first histogram is lower than the luminance value representing the converging point on the high-luminance side of said second histogram, setting said static threshold equal to a luminance value taken at a point where said first histogram intersects said second histogram.

11. The image processing method according to claim 8, wherein said dynamic threshold is calculated by taking a sum of the luminance value of said edge pixel and said minimum luminance value each multiplied by a predetermined weighting factor.

7. A computer-readable, non-transitory medium storing a computer program, wherein said computer program causes a computer to execute a process, the process comprising:

extracting edge pixels from an input image;

generating a first histogram based on a luminance value of each of said edge pixels;

generating a second histogram based on a minimum luminance value among the luminance values of pixels neighboring each of said edge pixels;

obtaining a static threshold based on said first histogram and said second histogram; and

binarizing said input image by using said static threshold.