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

Patent metadata

Field	Value
Publication number	US-2017316559-A1
Application number	US-201715493526-A
Country	US
Kind code	A1
Filing date	Apr 21, 2017
Priority date	May 2, 2016
Publication date	Nov 2, 2017
Grant date	—

Abstract

An image processing apparatus for detecting a singular point from image data having a plurality of pixel signals arranged in a two-dimensional manner, having a stochastic resonance processing unit configured to perform parallel steps in each of which a noise is added to and the result is subjected to binarization processing, synthesize the results of the parallel steps and output the result, with regard to each of the plurality of pixel signals; and a unit configured to detect the singular point based on the output signal value from the stochastic resonance processing unit for each of the plurality of pixel signals. The stochastic resonance processing unit performs the binarization processing on a pixel as a processing target among the plurality of pixel signals based on the pixel signal of the pixel as the processing target and a pixel signal of a pixel adjacent to the pixel as the processing target in a predetermined direction.

First claim

What is claimed is:

1 . An image processing apparatus for detecting a singular point from image data having a plurality of pixel signals arranged in a two-dimensional manner, comprising:
a stochastic resonance processing unit configured to perform parallel steps in each of which a noise is added to and the result is subjected to binarization processing, synthesize the results of the parallel steps and output the result, with regard to each of the plurality of pixel signals; and a detection unit configured to detect the singular point based on the output signal value from the stochastic resonance processing unit for each of the plurality of pixel signals, wherein the stochastic resonance processing unit performs the binarization processing on a pixel as a processing target among the plurality of pixel signals based on the pixel signal of the pixel as the processing target and a pixel signal of a pixel adjacent to the pixel as the processing target in a predetermined direction.

2 . The image processing apparatus according to claim 1 , wherein
the stochastic resonance processing unit adds the noise to the pixel signal of the pixel as the processing target to subsequently ternarize the pixel signal using two different threshold values to subject the pixel as the processing target to a binarization processing based on the ternarizing result of pixels adjacent to the pixel as the processing target in the predetermined direction.

3 . The image processing apparatus according to claim 2 , wherein
the two threshold values are adjusted for the singular point as a detection target.

4 . The image processing apparatus according to claim 1 , wherein
the predetermined direction includes a plurality of directions different from one another.

5 . The image processing apparatus according to claim 1 , wherein
the image data is obtained by image-taking an image printed by a printing head in which a plurality of printing elements used for ejecting ink are arranged, and the predetermined direction includes a direction crossing the arrangement direction.

6 . The image processing apparatus according to claim 1 , wherein
the stochastic resonance processing unit performs the binarization processing based on the pixel signal of the pixel as the processing target and pixel signals of a plurality of pixels continuously adjacent to the pixel as the processing target in the predetermined direction.

7 . The image processing apparatus according to claim 1 , further comprising a unit configured to acquire the image data by image-taking an image.

8 . The image processing apparatus according to claim 7 , further comprising a printing unit configured to print the image.

9 . The image processing apparatus according to claim 1 , wherein
the noise is white noise.

10 . An image processing method for detecting a singular point from image data having a plurality of pixel signals arranged in a two-dimensional manner, comprising:
a stochastic resonance processing step of performing parallel steps in each of which a noise is added to and the result is subjected to binarization processing, synthesizing the results of the parallel steps and outputting the result, with regard to each of the plurality of pixel signals; and a step of detecting the singular point based on the output signal value from the stochastic resonance processing step for each of the plurality of pixel signals, wherein the stochastic resonance processing step performs the binarization processing on a pixel as a processing target among the plurality of pixel signals based on the pixel signal of the pixel as the processing target and a pixel signal of a pixel adjacent to the pixel as the processing target in a predetermined direction.

11 . The image processing method according to claim 10 , wherein
the stochastic resonance processing step adds the noise to the pixel signal of the pixel as the processing target to subsequently ternarize the pixel signal using two different threshold values to subject the pixel as the processing target to a binarization processing based on the ternarizing result of pixels adjacent to the pixel as the processing target in the predetermined direction.

12 . The image processing method according to claim 11 , wherein
the two threshold values are adjusted for the singular point as a detection target.

13 . The image processing method according to claim 10 , wherein
the predetermined direction includes a plurality of directions different from one another.

14 . The image processing method according to claim 10 , wherein
the image data is obtained by image-taking an image printed by a printing head in which a plurality of printing elements used for ejecting ink are arranged, and the predetermined direction includes a direction crossing the arrangement direction.

15 . The image processing method according to claim 10 , wherein
the stochastic resonance processing step performs the binarization processing based on the pixel signal of the pixel as the processing target and pixel signals of a plurality of pixels continuously adjacent to the pixel as the processing target in the predetermined direction.

16 . The image processing method according to claim 10 , further comprising a step of acquiring the image data by image-taking an image.

17 . The image processing method according to claim 16 , further comprising a printing step of printing the image.

18 . The image processing method according to claim 10 , wherein
the noise is white noise.

19 . A non-transitory computer-readable storage medium which stores a program for allowing a computer to execute an image processing method for detecting a singular point from image data having a plurality of pixel signals arranged in a two-dimensional manner, the image processing method comprising:
a stochastic resonance processing step of performing parallel steps in each of which a noise is added to and the result is subjected to binarization processing, synthesizing the results of the parallel steps and outputting the result, with regard to each of the plurality of pixel signals; and a step of detecting the singular point based on the output signal value from the stochastic resonance processing step for each of the plurality of pixel signals, wherein the stochastic resonance processing step performs the binarization processing on a pixel as a processing target among the plurality of pixel signals based on the pixel signal of the pixel as the processing target and a pixel signal of a pixel adjacent to the pixel as the processing target in a predetermined direction.

Assignees

• Canon Kk

Inventors

• Ishikawa Tomokazu
• Tanaka Wakako
• Suwa Tetsuya
• Hori Shinjiro

Classifications

• G06T7/77 Primary

  using statistical methods · CPC title

• G06T2207/10008

  from scanner, fax or copier · CPC title

• H04N1/00045 Primary

  using a reference pattern designed for the purpose, e.g. a test chart · CPC title

• H04N1/4072

  dependent on the contents of the original · CPC title

• G06T2207/30168

  Image quality inspection · CPC title