跳到主要內容

臺灣博碩士論文加值系統

(18.97.14.87) 您好!臺灣時間:2025/02/13 03:20
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:盧聖亞
研究生(外文):LU, SHENG-YA
論文名稱:基於深度學習之預測高斯雜訊標準差的影像修復方法
論文名稱(外文):Image Restoration with Predicting Deviation of Gaussian Noise Based on Deep Learning
指導教授:游寶達游寶達引用關係
指導教授(外文):YU, PAO-TA
口試委員:游寶達蔡鴻旭許政穆
口試日期:2019-07-19
學位類別:碩士
校院名稱:國立中正大學
系所名稱:資訊工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2019
畢業學年度:107
語文別:英文
論文頁數:57
中文關鍵詞:深度學習影像復原高斯雜訊
外文關鍵詞:Deep LearningImage RestorationGaussian Noise
相關次數:
  • 被引用被引用:0
  • 點閱點閱:393
  • 評分評分:
  • 下載下載:34
  • 收藏至我的研究室書目清單書目收藏:0
本篇論文結合了深度學習方法和傳統濾波器,設計了一種可以提高影像修復效果的新方法。在本篇論文中,CNN會被用來預測雜訊影像的標準差。為此,我們設計了一種對CNN的訓練資料集進行預處理的方法,並設計了符合我們需求的CNN模型。預處理方法包括三個步驟:影像復原,雜訊分離和轉換成直方圖。在預測出標準差後,會選用一款濾波器,這款濾波器會使用預測出來的標準差來改善影像修復的效果。
本篇論文進行了多次實驗,證實了預處理的效果確實有助於提高CNN模型的準確性。此外,在將本篇論文的預測標準差的方法和其他預測標準差的方法進行比較後,證實了我們方法整體的精準度比其他的方法高。最後,實驗證實了使用本篇論文方法後,我們選用的濾波器的影像恢復效果會更好。

This thesis combines the methods of deep learning and traditional filters to design a new method to improve the effect of image restoration. In this thesis, CNN has been used to predict the deviation of the noisy image. Therefore, we have designed a method for preprocessing the training data of CNN and designed a CNN model that fits our needs. The preprocessing method consists of three steps, image restoration, noise separation, and histogram transform. After predicting the deviation, a filter will be selected and it will use the predicted deviation to improve the image restoration.
In this thesis, several experiments have been carried out to confirm that the effect of preprocessing is helpful to improve the accuracy of CNN model. In addition, the predicting deviation method of this thesis will be compared with the additional method, and confirm that the effect of the overall accuracy of our method is higher than the accuracy of the additional method. Finally, the experiment confirmed that after using this method of this thesis, the image restoration effect of the selected filter will be better.

Chapter 1 Introduction 1
1.1 Overview 1
1.2 Motivation 2
1.3 Organization and Thesis 2
Chapter 2 Related Works 3
2.1 Convolution Neural Network (CNN) 3
2.1.1 Convolution Layer 4
2.1.2 Pooling Layer 7
2.1.3 Fully Connected Layer 8
2.1.4 Activation Function 9
2.1.5 Optimizer 9
2.1.6 Loss Function 10
2.2 Gaussian Noise 10
2.3 Bilateral Filter 12
2.4 Non-Local Means (NLM) 13
2.5 TensorFlow 14
2.6 Keras 15
2.7 Scikit-Image 15
2.8 IAPR TC-12 Benchmark 15
Chapter 3 The Proposed Method 17
3.1 Data Preprocessing 17
3.1.1 Image Restoration 17
3.1.2 Noise Separation 18
3.1.3 Histogram Transform 21
3.2 Network Architecture 24
3.3 The Details of Implementation 25
3.3.1 The Training Data 25
3.3.2 Model 25
Chapter 4 Experiment Result 27
4.1 Comparison with Different Filters 27
4.2 Training Result (P-NPM) 29
4.2.1 The Loss of Model 31
4.2.2 Predicted Result of P-NPM 31
4.3 Training Result (NP-NPM) 35
4.3.1 The Loss of Model 36
4.3.2 Predicted Result of NP-NPM 37
4.4 Comparison P-NPM and NP-NPM 40
4.5 Comparison P-NPM and Scikit-Image API 43
4.6 Results of Restoration with NLM 47
Chapter 5 Conclusion 53
5.1 Conclusion 53
5.2 Future Research 54
Reference 55


[1] Yann LeCun, Yoshua Bengio, Geoffrey Hinton, "Deep Learning," Nature, vol. 521, no. 7553, p. 436, 2015.
[2] Yann LeCun, L´eon Bottou, Yoshua Bengio, Patrick Haffner, "Gradient-Based Learning Applied," Proceedings of The IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[3] Alex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," in Neural Information Processing Systems, 2012.
[4] Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed,Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich, "Going Deeper With Convolutions," in Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition, 2015.
[5] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, "Deep Residual Learning for Image Recognition," in Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition, 2016.
[6] Holger R. Roth, Le Lu, Jiamin Liu, Jianhua Yao, Ari Seff, Kevin Cherry, Lauren Kim, Ronald M. Summers, "Improving Computer-Aided Detection using Convolutional Neural Networks and Random View Aggregation," IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1170-1181, 2016.
[7] Qi Dou, Hao Chen, Lequan Yu, Lei Zhao, Jing Qin, Defeng Wang, Vincent CT Mok, Lin Shi, Pheng-Ann Heng, "Automatic Detection of Cerebral Microbleeds from MR Images via 3D Convolutional Neural Networks," IEEE Transactions on Medical Imaging, vol. 35, no. 5, pp. 1182-1195, 2016.
[8] Yi Sun, Xiaogang Wang, Xiaoou Tang, "Deep Learning Face Representation from Predicting 10,000 Classes," in Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition, 2014.
[9] Omkar M. Parkhi, Andrea Vedaldi, Andrew Zisserman, "Deep Face Recognition," BMVC, vol. 1, no. 3, p. 6, 2015.
[10] Brody Huval, Tao Wang, Sameep Tandon, Jeff Kiske, Will Song, Joel Pazhayampallil, "An Empirical Evaluation of Deep Learning on Highway Driving," ArXiv Preprint ArXiv:1504.01716, 2015.
[11] Chenyi Chen, Ari Seff, Alain Kornhauser, Jianxiong Xiao, "Deepdriving: Learning Affordance For Direct Perception in Autonomous Driving," Proceedings of the IEEE International Conference on Computer Vision, pp. 2722-2730, 2015.
[12] Oriol Vinyals, Alexander Toshev, Samy Bengio, Dumitru Erhan, "Show and Tell: A Neural Image Caption Generator," pp. 3156-3164, 2015.
[13] Antoni Buades, Bartomeu Coll, Jean-Michel Morel, "A Non-Local Algorithm for Image Denoising," IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 60-65, 2005.
[14] Diederik P. Kingma, Jimmy Ba, "Adam: A Method for Stochastic Optimization," ArXiv Preprint ArXiv:1412.6980, 2014.
[15] A. Bovik, "Chapter 7 - Image Noise Models," in The Essential Guide to Image Processing, Academic Press, 2009, pp. 143-167.
[16] Carlo Tomasi, Roberto Manduchi, "Bilateral Filtering for Gray and Color Images," ICCV, vol. 98, no. 1, p. 2, 1998.
[17] B. K. S. Kumar, "Image Denoising Based on Gaussian/Bilateral Filter and Its Method Noise Thresholding," Signal, Image and Video Processing, vol. 7, no. 6, pp. 1159-1172, 2013.
[18] Buades, Antoni, Bartomeu Coll, Jean-Michel Morel, "A Review of Image Denoising Algorithms, With A New One," Multiscale Modeling & Simulation, vol. 4, no. 2, pp. 490-530, 2005.
[19] Geng Chen, Pei Zhang, Yafeng Wu, Dinggang Shen, Pew-Thian Yap, "Denoising Magnetic Resonance Images using Collaborative Non-Local Means," Neurocomputing, no. 177, pp. 215-227, 2016.
[20] Mark S. Nixon, Alberto S. Aguado, "Feature Extraction and Image Processing," Academic Press, 2008, p. 88.
[21] Antoni Buades, Bartomeu Coll, Jean-Michel Morel, "Non-Local Means Denoising," vol. 1, pp. 208-212, 2011.
[22] "TensorFlow," [Online]. Available: https://www.tensorflow.org/.
[23] "Keras," [Online]. Available: https://keras.io/.
[24] "Scikit-Image: Image Processing in Python," [Online]. Available: https://scikit-image.org/.
[25] Michael Grubinger, Paul Clough , Müller Henning, Thomas Deselaers, "The IAPR TC12 Benchmark: A New Evaluation Resource for Visual Information Systems," in International Conference on Language Resources and Evaluation, Genoa, Italy, 2006.
[26] Zhou Wang, Alan C. Bovik, Hamid R. Sheikh, Eero P. Simoncelli, "Image Quality Assessment: From Error Visibility to Structural Similarity," IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600-612, 2004.
[27] Zhou Wang, Eero P. Simoncelli, Alan C. Bovik, "Multi-Scale Structural Similarity for Image Quality Assessment.," The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, pp. 1398-1402, 2003.
[28] JohnImmerkær, "Fast Noise Variance Estimation," Computer Vision and Image Understanding, vol. 64, no. 2, pp. 300-302, 1996.
[29] Dong-Hyuk Shin , Rae-Hong Park, Seungjoon Yang, Jae-Han Jung, "Block-Based Noise Estimation using Adaptive Gaussian Filtering," IEEE Transactions on Consumer Electronics, vol. 51, no. 1, pp. 218-226, 2005.
[30] David L. Donoho, Iain M. Johnstone, "Ideal Spatial Adaptation by Wavelet Shrinkage," Biometrika, vol. 81, no. 3, pp. 425-455, 1994.

QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top