Method and apparatus for recognizing a character based on a photographed image

Patent metadata

Field	Value
Publication number	US-9235779-B2
Application number	US-201514738096-A
Country	US
Kind code	B2
Filing date	Jun 12, 2015
Priority date	Dec 13, 2011
Publication date	Jan 12, 2016
Grant date	Jan 12, 2016

Abstract

An apparatus and a method for recognizing a character based on an input image is provided. The apparatus includes an input unit configured to receive the input image and a controller configured to select, from the input image, a region of image analysis to be used for image analysis, and to analyze the selected region of image analysis to determine a type of the input image, to apply, to the input image, an image effect for distinguishing a character region and a background region in the input image if the type of the input image indicates that the input image is obtained by photographing a display screen, to binarize output of the image effect according to the determined type of the input image, and to recognize a character from the binarized output of the image effect.

First claim

What is claimed is:

1. An apparatus for recognizing a character based on an input image, the apparatus comprising:
an input unit configured to receive the input image; and
a controller configured to:
select, from the input image, a region of image analysis to be used for image analysis, and to analyze the selected region of image analysis to determine a type of the input image;
to apply, to the input image, an image effect for distinguishing a character region and a background region in the input image if the type of the input image indicates that the input image is obtained by photographing a display screen;
to binarize output of the image effect according to the determined type of the input image; and
to recognize a character from the binarized output of the image effect.

2. The apparatus of claim 1 , wherein the controller is further configured to divide the selected region of image analysis into analysis blocks of a predetermined size, to generate a representative analysis block by superposing the divided analysis blocks to match each pixel corresponding to a same location, to calculate a representative color value of each pixel included in the representative analysis block, and to analyze the input image based on each calculated representative color value.

3. The apparatus of claim 2 , wherein the controller is further configured to calculate a first average representative color value of pixels included in a row and a column where pixels having relatively high representative color values exist in the representative analysis block, excluding a pixel having a maximum representative color value in the representative analysis block, to calculate a second average representative color value of remaining pixels, to compare the first average representative color value and the second average representative color value, and to determine the type of the input image based on a result of the comparison.

4. The apparatus of claim 3 , wherein the controller is further configured to determine whether a difference value between the first average representative color value and the second average representative color value is greater than or equal to a predetermined threshold color value, to determine the input image as a display screen image when the difference value is greater than or equal to the threshold color value, and to determine the input image as an image different from the display screen image when the difference value is less than the threshold color value.

5. The apparatus of claim 1 , wherein the controller is further configured to apply a blurring effect to the input image so that a difference value between a color value of the character region and a color value of the background region in the input image is greater than or equal to a predetermined threshold difference value.

6. A method of recognizing a character based on an input image, the method comprising:
receiving the input image;
selecting, from the input image, a region of image analysis to be used for image analysis;
determining a type of the input image by analyzing the selected region of image analysis;
applying, to the input image, an image effect for distinguishing a character region and a background region in the input image if the type of the input image indicates that the input image is obtained by photographing a display screen;
binarizing output of the image effect according to the determined type of the input image; and
recognizing a character from the binarized output of the image effect.

7. The method of claim 6 , wherein determining the type of the input image comprises:
dividing the selected region of image analysis into analysis blocks of a predetermined size;
generating a representative analysis block by superposing the divided analysis blocks to match each pixel corresponding to a same location;
calculating a representative color value of each pixel included in the representative analysis block; and
analyzing the input image based on each calculated representative color value.

8. The method of claim 7 , wherein analyzing the input image comprises:
calculating a first average representative color value of pixels included in a row and a column where pixels having relatively high representative color values exist in the representative analysis block, excluding a pixel having a maximum representative color value in the representative analysis block;
calculating a second average representative color value of remaining pixels; and
comparing the first average representative color value and the second average representative color value to determine a type of the input image based on a result of the comparison.

9. The method of claim 8 , wherein determining the type of the input image comprises:
determining whether a difference value between the first average representative color value and the second average representative color value is greater than or equal to a predetermined threshold color value;
determining the input image as a display screen image when the difference value is greater than or equal to the threshold color value; and
determining the input image as an image different from the display screen image when the difference value is less than the threshold color value.

10. The method of claim 6 , wherein applying the image effect for distinguishing the character region and the background region comprises:
applying a blurring effect to the input image so that a difference value between a color value of the character region and a color value of the background region in the input image is greater than or equal to a predetermined threshold difference value.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Kim Sang-Ho
• Kang Woo-Sung
• Kwon Mu-Sik
• Kim Jung-Rim
• Park Jeong-Wan

Classifications

• G06V30/162

  Quantising the image signal · CPC title

• G06V30/414 Primary

  Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text · CPC title

• G06V30/10

  Character recognition · CPC title

• G06K9/00463

  Physics · mapped topic

• G06K9/38

  Physics · mapped topic