Method and apparatus for producing digital cartoons

• US 8,207,987 B2
• Filed: 11/12/2008
• Issued: 06/26/2012
• Est. Priority Date: 11/16/2007
• Status: Active Grant

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: Lee, Ji Hyung, Koo, Bon Ki, Kim, Bo Youn, Kim, Hee Jeong, Choi, Yoon-Seok, Park, Il Kyu, Lee, Seung Wook, Cho, Hwan-gue, Ryu, Dong-Sung, Hwang, Won-Il, Chun, Bong-Kyung
• Primary Examiner(s): Sams, Michelle L
• Application Number:
  US12/292,073
• Publication Number:
  US 20090135198A1
• Time in Patent Office: 1,322 Days
• Field of Search: 345/629, 345/619
• US Class Current: 345/619
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text
• CPC Class Codes: G06T 15/02 Non-photorealistic rendering
• CPC Class Codes: G06T 2207/20192 Edge enhancement; Edge preservation
• CPC Class Codes: G06T 7/13 Edge detection

Abstract

An apparatus for producing digital cartoons includes: an image collection unit for collecting photorealistic image data; and a cartooning processor for performing a rendering process including image abstraction and edge generation on the photorealistic image data collected by the image collection unit to generate cartooned images. The apparatus further includes a stylization unit for producing a cartoon page having various shapes of cartoon frames, resizing the cartooned images to place the resized images into the cartoon frames and adding cartoon elements to the images placed in the cartoon frames.

Claims

1. An apparatus for producing digital cartoons comprising:

an image collection unit configured to collect photorealistic image data;

a cartooning processor configured to perform a rendering process including image abstraction and edge generation on the photorealistic image data collected by the image collection unit to generate cartooned images; and

a stylization unit configured to produce a cartoon page having various shapes of cartoon frames, resizing the cartooned images to place the resized images into the cartoon frames and adding cartoon elements to the images placed in the cartoon frames,

wherein the cartoon elements include word balloons having word ends, and the stylization unit is configured to determine a location of the word ends using a reference point, a center of a word balloon, and a tangent line of the word balloon.

2. The apparatus of claim 1, wherein the image abstraction includes simplification of colors in the photorealistic image data.

3. The apparatus of claim 2, wherein the image abstraction is performed using bilateral filtering and mean-shift segmentation.

4. The apparatus of claim 1, wherein the edge generation is performed using Laplacian filtering and Canny edge detection to generate edges on contours of objects in the photorealistic image data.

5. The apparatus of claim 1, wherein the photorealistic image data are images taken by a digital camera or extracted from scenes of two-dimensional based movies or dramas.

6. The apparatus of claim 1, wherein the cartoon elements further include backgrounds, letters and speedlines.

7. The apparatus of claim 1, wherein the word balloons are automatically placed in each cartoon frame depending on a sequence of lines of cartoon characters in the cartoon frame by using an EPFLP (Extended Point-Feature Label Placement) method and a heuristic method using a QLayout evaluation function.

8. A method for producing digital cartoons, the method comprising:

collecting photorealistic image data using an image collection unit;

performing a cartooning process, using a cartooning processor, on the photorealistic image data to generate a cartooned image;

performing a stylization process, using a stylization unit, on the cartooned image to complete a cartoon page, wherein the cartooned image includes cartoon elements, and the cartoon elements include word balloons having word ends; and

determining a location of the word ends, using the stylization unit, by using a reference point, a center of a word balloon, and a tangent line of the word balloon.

9. The method of claim 8, wherein performing a cartooning process includes:

abstracting the photorealistic image data to simplify colors in the photorealistic image data; and

generating edges on contours of objects in the abstracted photorealistic image data.

10. The method of claim 9, wherein abstracting the photorealistic data is performed using bilateral filtering and mean-shift segmentation.

11. The method of claim 9, wherein generating the edges is performed using Laplacian filtering and Canny edge detection.

12. The method of claim 8, wherein performing the stylization process includes:

producing a cartoon page having various shapes of cartoon frames;

resizing the cartooned images to place the resized images into the cartoon frames; and

adding cartoon elements to the images placed in the cartoon frames.

13. The method of claim 12, wherein the cartoon elements further include backgrounds, letters and speedlines.

14. The method of claim 8, wherein the word balloons are automatically placed in each cartoon frame depending on a sequence of lines of cartoon characters in the cartoon frame by using EPFLP (Extended Point-Feature Label Placement) method and a heuristic method using a QLayout evaluation function.