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

• US 8,824,796 B2
• Filed: 07/06/2012
• Issued: 09/02/2014
• 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): Alavi, Amir
• Assistant Examiner(s): Lesnick, Alexander J
• Application Number:
  US13/543,605
• Publication Number:
  US 20130044953A1
• Time in Patent Office: 788 Days
• Field of Search: None
• US Class Current: 382/170
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1473 Recognising objects as potential recognition candidates based on visual cues, e.g. shapes
• 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 determine with high accuracy whether or not an input image contains a background element. The image processing apparatus includes a decimated image generator for generating a decimated image through pixel decimation from an input image, an edge pixel extractor for extracting edge pixels from the decimated image, an edge class extractor for extracting an isolated edge pixel from among the edge pixels, a histogram generator for generating an isolated histogram based on the isolated edge pixel, and a decision unit for making, based on the isolated histogram, a decision as to whether or not the input image contains a background element.

Claims

1. An image processing apparatus comprising:

a decimated image generator for generating a decimated image through pixel decimation from an input image;

an edge pixel extractor for extracting edge pixels from said decimated image;

an edge class extractor for extracting an isolated edge pixel from among said edge pixels;

a histogram generator for generating an isolated histogram from only said isolated edge pixel; and

a decision unit for making, based on said isolated histogram, a decision as to whether or not said input image contains a background element.

2. The image processing apparatus according to claim 1, wherein said edge class extractor further extracts a connected edge pixel from among said edge pixels,

said histogram generator further generates a connected histogram based on said connected edge pixel, and

said decision unit, based on said isolated histogram and said connected histogram, makes a decision as to whether or not said input image contains said background element.

3. The image processing apparatus according to claim 2, wherein said decision unit makes a decision as to whether or not said input image contains said background element, based on an interrelationship between a convergence rate of said connected histogram and a convergence rate of said isolated histogram.

4. The image processing apparatus according to claim 2, wherein said decision unit makes a decision as to whether or not said input image contains said background element, based on an interrelationship between a maximum value of said connected histogram and a maximum value of said isolated histogram.

5. The image processing apparatus according to claim 1, wherein said decision unit makes a decision as to whether or not said input image contains said background element, based on a convergence rate of said isolated histogram.

6. The image processing apparatus according to claim 5, wherein said decision unit obtains said convergence rate, based on a spread of a range over which a ratio relative to a maximum value of said isolated histogram is not less than a predetermined ratio.

7. An image processing method comprising:

generating a decimated image through pixel decimation from an input image;

extracting edge pixels from said decimated image;

extracting an isolated edge pixel from among said edge pixels;

generating an isolated histogram from only said isolated edge pixel; and

based on said isolated histogram, making, using a computer, a decision as to whether or not said input image contains a background element.

9. The method according to claim 7, further extracts further comprising extracting a connected edge pixel from among said edge pixels,

generating a connected histogram based on said connected edge pixel, and

based on said isolated histogram and said connected histogram, making a decision as to whether or not said input image contains said background element.

10. The method according to claim 9, further comprising making a decision as to whether or not said input image contains said background element, based on an interrelationship between a convergence rate of said connected histogram and a convergence rate of said isolated histogram.

11. The method according to claim 9, further comprising making a decision as to whether or not said input image contains said background element, based on an interrelationship between a maximum value of said connected histogram and a maximum value of said isolated histogram.

12. The method according to claim 7, further comprising making a decision as to whether or not said input image contains said background element, based on a convergence rate of said isolated histogram.

13. The method according to claim 12, further comprising obtaining said convergence rate, based on a spread of a range over which a ratio relative to a maximum value of said isolated histogram is not less than a predetermined ratio.

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

generating a decimated image through pixel decimation from an input image;

extracting edge pixels from said decimated image;

extracting an isolated edge pixel from among said edge pixels;

generating an isolated histogram from only said isolated edge pixel; and

based on said isolated histogram, making a decision as to whether or not said input image contains a background element.