Level Set Method for Image Segmentation and Manga Stylization
Segmentation has always been a crucial and challenging topic in various computer vision and graphics applications. Information from image features can be incorporated into image segmentation techniques to make the process more accurate and robust. This dissertation focuses on encoding these feature information into the image processing procedures, including image segmentation and manga stylization rendering.
The fundamental part of this dissertation includes the discussion on the construction of the speed function, which is important in applying the curve-evolution based image segmentation. We firstly investigate the curvature term in the speed function, and then show how to transform the image segmentation problem into an interface propagating problem. We propose two formulations to enhance the speed function in level set methods, in order to tackle the segmentation problem of tagged MR images. First, a relaxation factor is introduced, aiming at relaxing the boundary condition when the boundary is unclear or blurry. Second, in order to incorporate human visual sensitive information from the image, a simple and general model is introduced to incorporate shape, texture and color features. By further extending this model, we present a unified approach for segmenting and tracking of the high-resolution color anatomical Chinese Visible Human (CVH) data. The underlying relationship of these two applications relies on the proposed variational framework for the speed function. Our proposed method can be used to segment the first slice of the volume data. Then based on the extracted boundary on the first slice, our method can also be adapted to track the boundary of the homogeneous organs among the subsequent serial images. In addition to the promising segmentation results, the tracking procedure requires only a small amount of user intervention.
Our method can be naturally applied in the application of manga stylization rendering. We proposes a novel colorization technique that propagates color over manga regions exhibiting pattern-continuity as well as intensity-continuity. The proposed method works effectively on colorizing black-and-white manga which contains intensive amount of strokes, hatching, halftoning and screening. Once the user scribbles on the drawing, a local, statistical based pattern feature obtained with Gabor wavelet filters is applied to measure the pattern-continuity. The boundary is then propagated by the level set method that monitors the pattern-continuity. Regions with open boundaries or multiple disjointed regions with similar patterns can be sensibly segmented by a single scribble. With the segmented regions, various colorization techniques can be applied to replace colors, colorize with stroke preservation, or even convert pattern to shading. Base on the observation of the manga features, we then propose a framework to generate manga-style backgrounds from real photographs. It frees manga artists from the tedious and time-consuming background production. To mimic how manga artists produce the tidy background, it composes of two major steps, the line drawing and the screen laying. A line importance model is proposed to simplify and embolden lines in a stylish way. During the screen laying, texture analysis is utilized to automatically match the regions in photographs with screens in the database. Two types of screening mechanisms are proposed for matching shading & texture as well as the high-level structures.
- "Manga Colorization",
Y. Qu, T. T. Wong and P. A. Heng,
ACM Transactions on Graphics (SIGGRAPH 2006 issue), Vol. 25, No. 3, July 2006, pp. 1214-1220.
- "Image Segmentation Using the Level Set Method",
Y. Qu, P. A. Heng and T. T. Wong,
Deformable Models: Theory and Biomaterial Applications, Edited by J. S. Suri and A. A. Farag, Springer, 2007, pp. 95-122.
- "Segmentation of Left Ventricle via Level Set Method Based on Enriched Speed Term",
Y. Qu, Q. Chen, P. A. Heng and T. T. Wong,
in Proceedings of the 7th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2004), Vol. I, Saint-Malo, France, September 2004, pp. 435-442.
Home Copyright © 1996-2012 Tien-Tsin Wong. All rights reserved.