Image processing apparatus and method

Patent metadata

Field	Value
Publication number	US-9299005-B2
Application number	US-201314015054-A
Country	US
Kind code	B2
Filing date	Aug 30, 2013
Priority date	Sep 5, 2012
Publication date	Mar 29, 2016
Grant date	Mar 29, 2016

Abstract

An image processing apparatus and method include a receiver configured to receive an image, a display configured to display the received image, an extractor configured to extract a first object contour by applying a preset algorithm to an area of the displayed image designated by a user and extract a second object contour based on the designated area, an image analyzer configured to analyze the displayed image, and a controller configured to determine weight values for the first and second object contours based on an analysis result of the image analyzer and extract an object contour based on the first and second object contours to which the determined weight values are applied. The image processing apparatus extracts an object intended by a user even in a heavily noisy image.

First claim

What is claimed is:

1. An image processing apparatus, comprising:
a receiver configured to receive an image;
a display configured to display the received image;
one or more hardware processors which provide:
an extractor configured to extract a first object contour by applying a preset algorithm to an area of the displayed image designated by a user and extract a second object contour based on the designated area;
an image analyzer configured to analyze the displayed image; and
a controller configured to determine a weight value for the first object contour and a weight value for the second object contour based on an analysis result of the image analyzer and extract an object contour based on the first object contour and the second object contour to which the determined weight value of the first object contour and the weight value for the second object contour are applied.

2. The image processing apparatus as claimed in claim 1 , wherein the controller calculates a degree of reliability of the first object contour based on the analysis result of the image analyzer and determines a first weight value assigned to the first object contour and a second weight value assigned to the second object contour, based on the calculated degree of reliability.

3. The image processing apparatus as claimed in claim 2 , wherein the controller calculates a plurality of degrees of reliability for a plurality of first local areas of the first object contour, determines a plurality of first local area weight values assigned to the plurality of local areas, respectively, to be proportional to the calculated degrees of reliability for the local areas, and determines the first weight value for a respective local area as a maximum value when a corresponding degree of reliability for the respective local area among the plurality of calculated degrees of reliability for the local areas is equal to or larger than a preset threshold value.

4. The image processing apparatus as claimed in claim 3 , wherein the controller determines a plurality of second local area weight values assigned to the plurality of second local areas of the second object contour, respectively, based on the plurality of first weight values assigned to the plurality of local areas of the first object contour, and
wherein the plurality of second weight values for the plurality of second local areas of the second object contour are inversely proportional to the plurality of first weight values for the plurality of first local areas of the first object contour.

5. The image processing apparatus as claimed in claim 1 , wherein the image analyzer detects at least one among color, brightness, an edge, and distributed information for each local area among a plurality of local areas constituting at least one of the displayed image and the first object contour, and
wherein the controller calculates the degrees of reliability for each local area among the plurality of local areas constituting the first object contour based on a result of the detection.

6. The image processing apparatus as claimed in claim 1 , further comprising a user interface configured to receive a user command,
wherein the controller designates the area according to the user command received through the user interface.

7. The image processing apparatus as claimed in claim 1 , wherein the controller determines a plurality of corresponding local areas corresponding to each other among a plurality of first local areas and a plurality of second local areas constituting the first object contour and the second object contour, respectively, based on at least one of a pixel value and a position for each local area among the plurality of first local areas and the plurality of second local areas constituting the first object contour and the second object contour, respectively.

8. The image processing apparatus as claimed in claim 7 , wherein the determining the plurality of corresponding local areas comprises extracting the object contour using the following equation:
( x,y ) OC =( x,y ) 1OC W ( x,y ) 1OC +( x,y ) 2OC W ( x,y ) 2OC
wherein (x,y) 1OC is a first local area of the first object contour, W(x,y) 1OC is a first weight value which is assigned to the first local area, (x,y) 2OC is a second local area of the second object contour, and W(x,y) 2OC is a second weight value which is assigned to the second local area.

9. An image processing method which processes an image received in an image processing apparatus, the method comprising:
displaying the received image;
extracting, using at least one processor, a first object contour by applying a preset algorithm to an area of the displayed image designated by a user and extracting a second object contour based on the designated area;
determining a weight value for the first object contour and a weight value for the second object contour based on an analysis result of the displayed image; and
extracting an object contour based on the first object contour and the second object contour to which the determined weight value of the first object contour and the weight value for the second object contour are applied.

10. The image processing method as claimed in claim 9 , wherein the determining includes:
calculating a degree of reliability of the first object contour based on the analysis result; and
determining a first weight value assigned to the first object contour, and a second weight value assigned to the second object contour, based on the calculated degree of reliability.

11. The image processing method as claimed in claim 10 , wherein the determining includes:
calculating a plurality of degrees of reliability for a plurality of first local areas of the first object contour;
determining a plurality of first weight values assigned to the plurality of first local areas, respectively, to be proportional to the calculated degrees of reliability; and
setting first weight value for a respective local area as a maximum value when a corresponding degree of reliability for the respective local area among the plurality of calculated degrees of reliability is equal to or larger than a preset threshold value.

12. The image processing method as claimed in claim 11 , wherein the determining includes determining a plurality of second local area weight values assigned to the plurality of second local areas of the second object contour, respectively, based on the plurality of first weight values which are to be assigned to the local areas of the first object contour, and
wherein the plurality of second weight values for the local areas of the second object contour are inversely proportional to the plurality of first weight values for the plurality of first local areas of the first object contour.

13. The image processing method as claimed in claim 9 , wherein the determining includes:
detecting at least one of color, brightness, an edge, and distributed information for each local area among a plurality of local areas constituting at least one of the displayed image and the first object contour; and
calculating degrees of reliability for each local area among the plurality of local areas constituting the first object contour based on a result of the detection.

14. The image processing method as claimed in claim 9 , further comprising:
receiving a user command; and
designating the area according to the received user command.

15. The image processing method as claimed in claim 9 , wherein the extracting includes determining a plurality of corresponding local areas corresponding to each other among a plurality of first local areas and a plurality of

Assignees

• Samsung Electronics Co Ltd

Inventors

• Kim Chang-Won
• Ahn Won-Seok
• Jeong Jin-Woo
• Han Seung-Hoon
• Han Young-Seok

Classifications

• G06T7/12 Primary

  Edge-based segmentation · CPC title

• G06T2207/20136

  Physics · mapped topic

• G06T7/0083

  Physics · mapped topic

• G06K9/48 Primary

  Physics · mapped topic

• G06T2207/20096

  Interactive definition of curve of interest · CPC title