Extra Form
Author Gyeongrok Lee, Hochang Lee, Taemin Lee, Kyunghyun Yoon
Location WSCG 2012
Abstract Luminance quantization, which maps the luminance values of an image to discrete levels, is widely used for image abstraction and the expression of a cartoonlike effect. Existing luminance quantization techniques use each pixel’s luminance value separately, leading to a noisy image. Additionally, they do not take the shape of the imaged object into consideration. Thus, they suffer limitations in terms of cartoonlike shade representation. We propose a new luminance quantization algorithm that takes into account the shape of the image. We extract the silhouette from the image, compute edge-distance values, and incorporate this information intothe process of luminance quantization. We integrate the luminance values of neighboring pixels using an anisotropic filter, using gradient information for this filtering. As a result, ourquantized image is superior to that given by existing techniques.
?

Shortcut

PrevPrev Article

NextNext Article

Larger Font Smaller Font Up Down Go comment Print Attachment

Image Abstraction with Cartoonlike Shade Representation

Gyeongrok Lee       Hochang Lee       Taemin Lee       Kyunghyun Yoon

CAU CGLab

IA_BIG1.JPG

Abstract

Luminance quantization, which maps the luminance values of an image to discrete levels, is widely used for image abstraction and the expression of a cartoonlike effect. Existing luminance quantization techniques use each pixel’s luminance value separately, leading to a noisy image. Additionally, they do not take the shape of the imaged object into consideration. Thus, they suffer limitations in terms of cartoonlike shade representation. We propose a new luminance quantization algorithm that takes into account the shape of the image. We extract the silhouette from the image, compute edge-distance values, and incorporate this information intothe process of luminance quantization. We integrate the luminance values of neighboring pixels using an anisotropic filter, using gradient information for this filtering. As a result, ourquantized image is superior to that given by existing techniques.


  1. A multi-level depiction method for painterly rendering based on visual perception cue

    A multi-level depiction method for painterly rendering based on visual perception cueHochang Lee Sanghyun Seo Seungtaek Ryoo Keejoo Ahn Kyunghyun Yoon CAU CGLab AbstractIncreasing the level of detail (LOD) in brushstrokes within areas of int...
    Read More
  2. A Novel Color Transfer Algorithm for Impressionistic Paintings

    A Novel Color Transfer Algorithm for Impressionistic PaintingsHochang Lee Taemin Lee Kyunghyun Yoon CAU CGLab AbstractExisting color reproduction algorithms achieve image enhancement or visualization by correcting tone and hue. Although thes...
    Read More
  3. Image Abstraction with Cartoonlike Shade Representation

    Image Abstraction with Cartoonlike Shade RepresentationGyeongrok Lee Hochang Lee Taemin Lee Kyunghyun Yoon CAU CGLab AbstractLuminance quantization, which maps the luminance values of an image to discrete levels, is widely used for image abs...
    Read More
  4. Artistic Image Generation for Emerging Multimedia Services by Impressionist Manner

    Artistic Image Generation for Emerging Multimedia Services by Impressionist MannerSanghyun Seo Seungtaek Ryoo Kyunghyun Yoon CAU CGLab AbstractIn this article, we propose the rendering framework for painting-like image generation and general...
    Read More
  5. Directional texture transfer with edge enhancement

    Directional texture transfer with edge enhancementHochang Lee Sanghyun Seo Kyunghyun Yoon CAU CGLab AbstractTexture transfer re-renders a target image with high-frequency information (texture) taken fromparts of a reference image that is mat...
    Read More
  6. Directional Texture Transfer

    Directional Texture TransferHochang Lee Sanghyun Seo Seungtaek Ryoo Kyunghyun Yoon CAU CGLab AbstractA texture transfer algorithm modifies the target image replacing the high frequency information with the example source image. Previ- ous tex...
    Read More
Board Pagination Prev 1 Next
/ 1