Information processing system, information processing apparatus, and image forming apparatus

Patent metadata

Field	Value
Publication number	US-2021234975-A1
Application number	US-202117228463-A
Country	US
Kind code	A1
Filing date	Apr 12, 2021
Priority date	Nov 22, 2018
Publication date	Jul 29, 2021
Grant date	—

Abstract

An information processing system acquires, using a reading device, a read image from an original on which a handwritten character is written; acquires, based on the read image, a partial image that is a partial region of the read image and a binarized image that expresses the partial image by two tones; performs learning of a learning model based on learning data that uses the partial image as a correct answer image and the binarized image as an input image; acquires print data including a font character; generates conversion image data including a gradation character obtained by inputting the font character to the learning model; and causes an image forming device to form an image based on the generated conversion image data.

First claim

1 . An information processing system comprising:
an image forming device configured to from an image on a sheet; a reading device configured to read an original; a unit configured to acquire, using the reading device, a read image from an original on which a handwritten character is written; a unit configured to acquire, based on the read image, a partial image that is a partial region of the read image and a binarized image that expresses the partial image by two tones; a unit configured to perform learning of a learning model based on learning data that uses the partial image as a correct answer image and the binarized image as an input image; a unit configured to acquire print data including a font character; a unit configured to generate conversion image data including a gradation character obtained by inputting the font character to the learning model; and a unit configured to cause the image forming device to form an image based on the generated conversion image data.

2 . The information processing system according to claim 1 , further comprising:
a unit configured to detect a character included in the read image; and a unit configured to generate the partial image based on a result of the detection.

3 . The information processing system according to claim 2 , wherein a step of performing the detection is one of a step of performing edge extraction and a step of performing contour extraction.

4 . The information processing system according to claim 2 , wherein the partial image is an image including one character.

5 . The information processing system according to claim 2 , wherein the partial image is an image including a part of one character.

6 . The information processing system according to claim 5 , wherein the part of the character is one of a vertical line portion, a horizontal line portion, a stop portion, and a sweeping portion.

7 . The information processing system according to claim 1 , further comprising:
a unit configured to divide the read image into a plurality of partial regions each having a predetermined size; and a unit configured to generate the partial image as an image of one region of the plurality of partial regions.

8 . The information processing system according to claim 1 , further comprising a unit configured to generate the binarized image by binarizing the partial image.

9 . The information processing system according to claim 1 , further comprising:
a display device configured to display information; and a unit configured to cause the display device to display a screen for designating a sending destination of the read image.

10 . The information processing system according to claim 1 , further comprising:
a display device configured to display information; and a unit configured to cause the display device to display a screen capable of designating whether to perform processing using the learning model in image formation of the print data.

11 . The information processing system according to claim 1 , further comprising:
a unit configured to generate conversion image data including a gradation character obtained by inputting the font character to the learning model; and a unit configured to cause the image forming device to form an image based on the generated conversion image data.

12 . The information processing system according to claim 1 , wherein the font character is one of a hiragana, a katakana, a Chinese character, and an alphabet.

13 . The information processing system according to claim 1 , wherein the learning model is a learning model that has learned that a lower portion of a vertical line included in a character becomes dark.

14 . The information processing system according to claim 1 , wherein the learning model is a learning model that has learned that a right side portion of the vertical line included in the character becomes dark.

15 . The information processing system according to claim 1 , wherein the learning model is a learning model that has learned that an intersection portion of the vertical line included in the character becomes dark.

16 . The information processing system according to claim 1 , wherein the learning model is a learning model that has learned gradation for the stop portion included in the character.

17 . The information processing system according to claim 1 , wherein the learning model is a learning model that has learned gradation for the sweeping portion included in the character.

18 . An information processing apparatus comprising:
a unit configured to acquire a read image obtained by reading, by a reading device, an original on which a handwritten character is written; a unit configured to acquire, based on the read image, a partial image that is a partial region of the read image and a binarized image that expresses the partial image by two tones; and a unit configured to generate learning data that uses the partial image as a correct answer image and the binarized image as an input image, wherein the learning data is used for learning of a learning model that outputs a gradation character having gradation in response to input of a font character.

19 . An image forming apparatus comprising:
an image forming device configured to from an image on a sheet; a unit configured to acquire print data including a font character; a unit configured to acquire image data including a gradation character obtained by inputting the font character to a learning model based on the print data; and a unit configured to cause the image forming device to form an image based on the acquired image data, wherein the learning model is a learning model learned using learning data that uses a partial image as a correct answer image and a binarized image as an input image, and the partial image is an image of a partial region of a read image obtained by reading, by a reading device, an original on which a handwritten character is written, and the binarized image is an image that expresses the partial image by two tones.

Assignees

• Canon Kk

Inventors

• Okuma Keisui

Classifications

• H04N1/00392 Primary

  Other manual input means, e.g. digitisers or writing tablets · CPC title

• G06V10/267

  by performing operations on regions, e.g. growing, shrinking or watersheds · CPC title

• H04N1/00331 Primary

  with an apparatus performing optical character recognition (character recognition G06V30/10) · CPC title

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title