Basic Search / Detailed Display

Author: 楊依哲
Yi-che Yang
Thesis Title: 自動模糊影像的偵測與分類系統
An Automatic System for Blurred Image Detection and Classification
Advisor: 吳怡樂
Yi-Leh Wu
Committee: 陳建中
Jiann-Jone Chen
Cheng-Yuan Tang
Degree: 碩士
Department: 電資學院 - 資訊工程系
Department of Computer Science and Information Engineering
Thesis Publication Year: 2012
Graduation Academic Year: 100
Language: 英文
Pages: 37
Keywords (in Chinese): 模糊影像奇異值分解特徵值梯度Hough Transform直線偵測
Keywords (in other languages): Blurred regions detection and classification, Singular value features, Gradient, Hough Transform, Dilation algorithm, Erosion algorithm
Reference times: Clicks: 364Downloads: 9
School Collection Retrieve National Library Collection Retrieve Error Report
  • 由於數位相機與數位相片普及化,使得接踵而來的數位資料劇增。使用者可以輕易透過數位設備取得數位影像資料,但是礙於設備的優劣或使用者本身的習慣,往往因為數位影像取得的不當而造成影像的模糊。模糊影像的處理一直是多媒體分析上的問題,我們提出一個自動模糊影像的偵測與分類系統,可以為使用者從大量的數位影像中偵測模糊影像,並將其分類。

    在偵測方法上,我們分析模糊影像的奇異值分解結果,同時擷取重要的特徵值,將兩者作為模糊影像偵測的標準。在模糊影像分類的部分,我們計算模糊影像的梯度,並利用奇異值分解與梯度之間的關係,透過Hough Transform的直線偵測方法達到模糊影像分類的目的。由實驗結果顯示我們的方法確實有助於改善模糊影像的處理,同時為多媒體分析與電腦視覺的應用提供了良好的準備工作。

    This work proposes an effective and simple automatic image blurred region detection and classification method. Many digital photos contain defocus blurred or motion blurred regions. To detect the image blurred regions, we examine the singular value feature for each image pixel by pixel. And for the image blurred classification, we compute the gradient with the Hough Transform for each image pixels, and use the dilation / erosion algorithms to increase accuracy. Experiment results show that the proposed method can detect image blurred regions effectively, and classify defocus blur regions and motion blur regions accurately.

    論文摘要 Abstract Contents List of Figures List of Tables Chapter 1. Introduction Chapter 2. Design Overview Chapter 3. Proposed Methods 3.1 Blurred Image Detection 3.1.1 Singular Value Decomposition (SVD) 3.1.2 SVD in Proposed Technique 3.2 Blurred Image Classification 3.2.1 Estimated Gradient Cross Type Adjacent Type 3.2.2 The Hough Transform 3.2.3 Dilation and Erosion Operators Chapter 4. Experiment 4.1 Experiment Data 4.2 Experiment Result Chapter 5. Conclusion and Future Work Reference

    [1]Amit Agrawal, Yi Xu, and Ramesh Raskar, “Invertible Motion Blur in Video,” ACM Transactions on Graphics, vol. 28, no. 3, August 2009.
    [2]Anat Levin, Peter Sand, Taeg Sang Cho, Fredo Durand, and William T. Freeman, “Motion-Invariant Photography,” ACM Transactions on Graphics, v.27 n.3, August 2008.
    [3]Anat Levin, Alex Rav-Acha, and Dani Lischinski, “Spectral Matting,” in Proceedings of IEEE Computer Vision and Pattern Recognition, 2007.
    [4]Bolan Su, Shijian Lu, and Chew Lim Tan, ”Blurred Image Region Detection and Classification,” ACM Multimedia 2011 ,28 November - 1 December 2011, Scottsdale, Arizona, USA, 2011.
    [5]Changyin Zhou, Stephen Lin, and Shree Nayar, “Coded Aperture Pairs for Depth from Defocus,” In IEEE International Conference on Computer Vision, October 2009.
    [6]Deepa Kundur, Dimitrios Hatzinakos, and Henry Leung, “Robust Classification of Blurred Imagery,” IEEE Transactions on Image Processing, vol. 9(2), 2000.
    [7]Harry C. Andrews, and Claude L. Patterson, “Singular Value Decomposition (SVD) Image Coding,” IEEE Transactions on Communications, vol. COM-24, 1976.
    [8]Harry C. Andrews, and Claude L. Patterson, “Singular Value Decomposition and Digital Image Processing,” IEEE Transactions on Acoustics, Speech, and Signal Processing, 24(1976), 1976.
    [9]H.K. Yuen, J. Illingworth, and J.Kittler, “Ellipse Detection Using the Hough Transform,” Proceedings of the 4th Alvey Vision Conference, 1988.
    [10]J. Illingworth, and J. Kittler, “A Survey of the Hough Transform,” Compute. Vision, Graph. Image Processing, 1988.
    [11]Jerome Da Rugna, and Hubert Konik, “Automatic Blur Detection for Meta-Date Extraction in Content-based Retrieval Context,” In Simone Santini and Raimondo Schettini, editors, Internet Image V, vol. 5304, December 2003.
    [12]Joseph (Yossi) Gil, and Ron Kimmel, “Efficient Dilation, Erosion, Opening, and Closing Algorithms,” IEEE Transactions. Pattern Analysis and Machine Intelligence, vol. 24, 2002.
    [13]Lu Yuan, Jian Sun, Long Quan, and Heung-Yeung Shum, “Image Deblurring with Blurred/Noisy Image Pairs,” ACM Transactions on Graphics, v.26 n.3, July 2007.
    [14]Mosh Ben-Ezra, and Shree K. Nayar, “Motion-Based Motion Deblurring,” IEEE Transactions on Pattern Analysis and Machine Intelligence, v.26 n.6, June 2004.
    [15]Moshe Ben-Ezra, and Shree K. Nayar, “Motion Deblurring Using Hybrid Imaging,” In Computer Vision and Pattern Recognition, volume I, June 2003.
    [16]Neel Joshi, C.Lawrence Zitnick, Richard Szeliski, and David J. Kriegman, “Image Deblurring and Denoising using Color Priors,” In: Proceedings of IEEE Computer Vision and Pattern Recognition, 2009.
    [17]Neel Joshi, Sing Bing Kang, C. Lawrence Zitnick, and Richard Szeliski, “Image Deblurring using Inertial Measurement Sensors,” ACM Transactions on Graphics, vol. 29, no. 3, 2010.
    [18]Oliver Cossairt, Changyin Zhou, and Shree Nayar, “Diffusion Coded Photography for Extended Depth of Field,” ACM Transactions on Graphics. 29, 31, 2010.
    [19]P.V.C. Hough, “Method and Means for Recognizing Complex Patterns,” U.S. Patent 3,069,654, Dec. 18, 1962.
    [20]Ramesh Raskar, Amit Agrawal, and Jack Tumbin, “Coded Exposure Photography: Motion Deblurring using Fluttered Shutter,” ACM Transactions on Graphics (TOG), v.25 n.3, July 2006.
    [21]Renting Liu, Zhaorong Li, and Jiaya Jia, “Image Partial Blur Detection and Classification,” In IEEE Conf. on Computer Vision and Pattern Recognition, 2008, Volume, Issue, 23-28 June 2008.
    [22]Richard O. Duda, and Peter E. Hart, “Use of the Hough Transformation to Detect Lines and Curves in Pictures,” Communications of the ACM, v.15 n.1, January 1972.
    [23]Robert M. HaraLick, Stanley R. Sternberg, and Xinhua Zhuang, ”Image Analysis Using Mathematical Morphology,” IEEE Transactions Pattern Analysis and Machine Intelligence, 1987.
    [24]Su Chen, and Robert M. Haralick, “Recursive Erosion, Dilation, Opening, and Closing Transforms,” IEEE Transactions Image Processing, 1995.
    [25]Sunghyum Cho, and Seungyong Lee, “Fast Motion Deblurring,” ACM Transactions on Graphics (SIGGRAPH ASIA 2009), 28(5): article no. 145, 2009.
    [26]Thuy Tuong Nguyen, Xuan Dai Pham, and Jae Wook Jeon, “An Improvement of the Standard Hough Transform to Detect Line Segments,” IEEE International Conference on Industrial Technology, April 2008.
    [27]Ville Ojansivu, and Janne Heikkila, “Blur Insensitive Texture Classification Using Local Phase Quantization,” In Proceeding of the 3rd International Conference on Image and Signal Processing, 2008.