Image processing apparatus, method and computer-readable medium for binarizing scanned data

Patent metadata

Field	Value
Publication number	US-10535140-B2
Application number	US-201715824221-A
Country	US
Kind code	B2
Filing date	Nov 28, 2017
Priority date	Nov 30, 2016
Publication date	Jan 14, 2020
Grant date	Jan 14, 2020

Abstract

An image processing apparatus includes a controller configured to control an image scanner to generate scanned data by scanning an image recorded on a document sheet, calculate an edge intensity of each of pixels included in the scanned data, determine a binarization threshold from pixel values of particular pixels, the particular pixels being a part of the pixels included in the scanned data, each particular pixel having a density value higher than density values of surrounding pixels thereof and having an edge intensity equal to or higher than an edge threshold, and generate a binary image from the scanned data, using the binarization threshold.

First claim

What is claimed is:

1. An image processing apparatus comprising:
an image scanner; and
a controller configured to:
control the image scanner to generate scanned data by scanning an image recorded on a document sheet;
calculate an edge intensity of each of pixels included in the scanned data;
determine a binarization threshold from pixel values of particular pixels, the particular pixels being a part of the pixels included in the scanned data, each particular pixel having a density value higher than density values of surrounding pixels of the particular pixel, each particular pixel having an edge intensity equal to or higher than an edge threshold, the particular pixels being separated from background pixels that represent a background color of the scanned data; and
generate a binary image from the scanned data, using the binarization threshold.

2. The image processing apparatus according to claim 1 ,
wherein the controller is further configured to:
remove, from among the particular pixels, a specific number of pixels preferentially in descending order of luminance values of the particular pixels; and
set, as the binarization threshold, a highest luminance value of particular pixels remaining after the specific number of pixels have been removed.

3. The image processing apparatus according to claim 2 ,
wherein the controller is further configured to:
calculate an average edge intensity by averaging edge intensities of pixels at four corners of a scanned image represented by the scanned data;
in a case where the average edge intensity is less than a threshold, set a removal rate to a first removal rate;
in a case where the average edge intensity is equal to or more than the threshold, set the removal rate to a second removal rate higher than the first removal rate; and
remove, from among the particular pixels, the specific number of pixels corresponding to the set removal rate.

4. The image processing apparatus according to claim 2 , further comprising:
an input interface; and
a memory,
wherein the controller is further configured to:
accept a user operation via the input interface;
set a noise removal flag stored in the memory to one of a first flag value and a second flag value in accordance with the user operation, the first flag value representing that noise data is to be removed from the scanned data, the second flag value representing that noise data is not to be removed from the scanned data; and
in response to the noise removal flag being set to the first flag value, remove noise data from the scanned data, using the binary image generated in the binarization process, and

wherein the controller is further configured to:
in response to the noise removal flag being set to the first flag value, remove, from among the particular pixels, the specific number of pixels corresponding to a first removal rate; and
in response to the noise removal flag being set to the second flag value, remove, from among the particular pixels, the specific number of pixels corresponding to a second removal rate, the second removal rate being higher than the first removal rate.

5. The image processing apparatus according to claim 1 ,
wherein the controller is further configured to:
calculate an average edge intensity by averaging edge intensities of pixels at four corners of a scanned image represented by the scanned data;
in a case where the average edge intensity is less than a threshold, set the edge threshold to a first threshold value;
in a case where the average edge intensity is equal to or more than the threshold, set the edge threshold to a second threshold value higher than the first threshold value; and
determine the binarization threshold, using the set edge threshold.

6. The image processing apparatus according to claim 1 ,
wherein the controller is further configured to:
apply a Laplacian filter to each of a luminance value, a first color difference value, and a second color difference value of a target pixel of the pixels included in the scanned data; and
calculate, as an edge intensity of the target pixel, a sum of respective squares of the luminance value, the first color difference value, and the second color difference value to each of which the Laplacian filter has been applied.

7. The image processing apparatus according to claim 6 ,
wherein the controller is further configured to:
calculate, as the edge intensity of the target pixel, a sum of:
a first weight coefficient multiplied by the square of the luminance value to which the Laplacian filter has been applied;
a second weight coefficient multiplied by the square of the first color difference value to which the Laplacian filter has been applied, the second weight coefficient being less than the first weight coefficient; and
a third weight coefficient multiplied by the square of the second color difference value to which the Laplacian filter has been applied, the third weight coefficient being less than the first weight coefficient.

8. The image processing apparatus according to claim 1 ,
wherein the controller is further configured to:
decimate the pixels included in the scanned data; and
calculate an edge intensity of each of pixels remaining after the pixels included in the scanned data have been decimated.

9. The image processing apparatus according to claim 1 ,
wherein the controller is further configured to:
remove noise data from the scanned data, using the binary image generated in the binarization process.

10. The image processing apparatus according to claim 1 ,
wherein the controller comprises:
a processor; and
a memory storing processor-executable instructions configured to, when executed by the processor, cause the processor to:
control the image scanner to generate the scanned data by scanning the image recorded on the document sheet;
calculate the edge intensity of each pixel included in the scanned data;
determine the binarization threshold from the pixel values of the particular pixels; and
generate the binary image from the scanned data, using the binarization threshold.

11. A method implementable on a processor coupled with an image scanner, the method comprising:
controlling the image scanner to generate scanned data by scanning an image recorded on a document sheet;
calculating an edge intensity of each of pixels included in the scanned data;
determining a binarization threshold from pixel values of particular pixels, the particular pixels being a part of the pixels included in the scanned data, each particular pixel having a density value higher than density values of surrounding pixels of the particular pixel, each particular pixel having an edge intensity equal to or higher than an edge threshold, the particular pixels being separated from background pixels that represent a background color of the scanned data; and
generating a binary image from the scanned data, using the binarization threshold.

12. A non-transitory computer-readable medium storing computer-readable instructions that are executable by a processor coupled with an image scanner, the instructions being configured to, when executed by the processor, cause the processor to:
control the image scanner to generate scanned data by scanning an image recorded on a document sheet;
calculate an edge intensity of each of pixels included in the scanned data;
determine a binarization threshold from pixel values of particular pixels, the particular pixels being a part of the pixels included in the scanned data, each particular pixel having a density value higher than density values of surrounding pixels of the particular pixel, each particular pixel havi

Assignees

• Brother Ind Ltd

Inventors

• Motoyama Toshiki
• Hasegawa Tomohiko

Classifications

• G06T2207/10024

  Color image · CPC title

• G06T2207/30176

  Document · CPC title

• G06T5/20

  using local operators · CPC title

• G06T7/13

  Edge detection · CPC title

• G06T7/11

  Region-based segmentation · CPC title