簡易檢索 / 詳目顯示
| 研究生： |
陳禹彤 Chen, Yu-Tung |
|---|---|
| 論文名稱： |
基於零穿越的邊緣權重內插法 A Weighted Edge Interpolation Method Based on Zero-crossing |
| 指導教授： |
戴顯權
Tai, Shen-Chuan |
| 學位類別： |
碩士 Master |
| 系所名稱： |
電機資訊學院 - 電腦與通信工程研究所 Institute of Computer & Communication Engineering |
| 論文出版年： | 2011 |
| 畢業學年度： | 99 |
| 語文別： | 英文 |
| 論文頁數： | 41 |
| 中文關鍵詞： | 超解析 、拉普拉斯濾波 、影像內插 |
| 外文關鍵詞： | super-resolution, Laplacian filter, image interpolation |
| 相關次數： | 點閱：82 下載：1 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
以內插為基礎的超解析法的好處是運算快速，尤其是在需要及時運算的應用上。然而這些方法通常會產生模糊的邊緣細節及鋸齒狀的誤差雜訊。本論文中，提出了一個有效率的零穿越邊緣導向內插法。首先我們對低解析度的影像使用拉普拉斯的高頻濾波器，找出可能的邊緣，並對偵測到的邊緣做量化用以產生有用的高解析梯度資訊。最後再依據這些量化的資訊來內插出高解析度影像。實驗結果顯示跟其它需要複雜運算的演算法相比之下，我們方法能提供更清晰且令人滿意的視覺影像。
The main advantage of interpolation-based super-resolution technique is fast to implement in real-time applications. However, these techniques usually result in blurred edge details as well as jagged artifacts. In this thesis, we propose an efficient edge-directed interpolation method which is based on zero-crossing edge detectors. First, a high-pass Laplacian filter is applied to the low-resolution image to determine the possible edges, and then the pixels of the filtered image are assigned different ranks in order to obtain a promising high-resolution gradient filed. Finally, the missing pixels of high-resolution image are interpolated with the ranked information. The simulation results show that our algorithm provides better PSNR performance and sharp, visually pleasing output image when compared to other more computation demanding algorithms
[1] Feng Liu, Jinjun Wang, Shenghuo Zhu, Michael Gleicher, Yihong Gong. Visual-Quality Optimizing Super Resolution. Computer Graphics Forum, Volume 28, Issue 1, pages 127–140, March 2009.
[2] Day-Funn Shen, Chui-Wen, Chiu, Pn-Jay Huang. Modified Laplacian Filter and Intensity Correction Technique for Image Resolution Enhancement. Multimedia and Expo, 2006 IEEE International Conference on, pages 457-460, July 2006.
[3] Hsuan-Ying Chen, Jin-Jang Leou. A visual attention approach to image interpolation. Multimedia and Expo, 2008 IEEE International Conference on, pages 169-172, June 2008.
[4] James A. Ward. Graphical Representation of Complex Roots. National Mathematics Magazine, Vol. 11, No. 7, pages 297-303, Apr. 1937.
[5] Jian Sun. Jian Sun. Zongben Xu. Heung-Yeung Shum. Image Super-Resolution using Gradient Profile Prior. Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, pages 1-8, June 2008.
[6] Jinjun Wang, Yihong Gong. Fast Image Super-Resolution using Connected Component Enhancement. Multimedia and Expo, 2008 IEEE International Conference on, pages 157-160, June 2008.
[7] Qiyong Guo, Hongzhi Liu, Wenbin Chen, I-fan Shen. Super Resolution Based on Gradient Field. Cybernetics and Intelligent Systems, 2008 IEEE Conference on, pages 164-168, Sept. 2008.
[8] Timo Ojala and Matti Pietikäinen. Unsupervised texture segmentation using feature distributions. Proc. ICIAP97. Florence, Italy, Vol. 1, pages 311–318. 1997.
[9] Xin Li , Michael T. Orchard. New edge-directed interpolation. Image Processing, IEEE Transactions on. pages 1521-, Oct. 2001.
[10] Xiaojun Jia. A Method of Image Enlargement Based on Constrained Pixels. Image and Signal Processing, 2009. CISP '09. 2nd International Congress on, pages 1-5, Oct. 2009.
[11] Yu-Wing Tai, Shuaicheng Liu, Michael S. Brown, Stephen Lin. Super resolution using Edge prior and single image detail synthesis. Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pages 2400-2407, June 2010.
[12] Kodak’s standard test images, http://r0k.us/graphics/kodak/, 2007.
校內：立即公開校外：2012-07-27公開