我提出了一個可以自動評估立體圖像品質的盲蔽式3D圖像品質估測器(CAP-3DIQA)，該模型架構分為兩階段，分別是分類層與預測層，首先會將失真圖像在分類層中進行分類，然後根據失真類型的總數將失真圖像分為若干個子集，用意是為了聚集有相同的失真類型特徵的圖像。經過分類層的處理後，將分類後的失真圖像集輸入預測層中，該層包含五種相異的預測通道，來分別預測圖像的品質分數。最後，我使用支持向量機(SVM)的回歸模型對最終的圖像品質評估進行預測，其中回歸模型是將五條通道的圖像品質預測的結果組合當作輸入。我所提出的架構分別在三種公開且常使用的資料庫上進行測試，這三種資料庫分別是LIVE 3D Image Quality Database Phase I、LIVE 3D Image Quality Database Phase II 和 MCL 3D Image Quality Database。在LIVE 3D Image Quality Database Phase I和 MCL 3D Image Quality Database中僅包含對稱性失真的立體圖像，而在LIVE 3D Image Quality Database Phase II 中則包含對稱性與非對稱性失真的立體圖像。實驗結果表明，我所提出的模型在立體圖像品質評估上有很顯著的效能，且與其他現有的估測器相比，也有很大的競爭力。

We proposed a blind image quality assessment model named classification and prediction for 3D images quality assessment (denoted by CAP-3DIQA) that can automatically evaluate the stereoscopic image quality. First, the model executed the classified process in the classification layer, then the process separated the distorted images into several subsets according to the total number of distortion types, in order to assemble the images with the same distortion type characteristics. After the process of classification layer, the classified distorted image set is fed into the predicted image quality layer that contains five different channels which predicted image quality score individually. Finally, we used the regression module of support vector machine (SVM) to evaluate the final image quality score which the input of the regression model is the combination of five channel’s output. The model we proposed is test on the three public and popular databases, which are LIVE 3D Image Quality Database Phase I, LIVE 3D Image Quality Database Phase II and MCL 3D Image Quality Database. LIVE Phase I and MCL databases contains only symmetric-distorted stereoscopic images, LIVE Phase II contains both symmetric-distorted and asymmetric-distorted stereoscopic images. The experimental results on these databases show that our proposed model leads to significant improved performance on quality prediction of stereoscopic images competition with other existing quality metrics.

摘要 i
Abstract ii
目錄 iii
圖目錄 iv
表目錄 vi
第一章 緒論 1
1.1 前言 1
1.2 論文的動機與大綱 2
第二章 文獻探討與相關背景知識 4
2.1 文獻探討 4
2.2 相關背景知識 5
2.2.1 雙眼視覺合成圖 5
2.2.2 機器學習 6
第三章 論文研究方法 8
3.1 分類層 9
3.1.1 提取用於分類層的特徵 9
3.1.2 分類模型的概述 12
3.2 預測層 17
3.2.1 提取用於預測層的特徵 18
3.2.2 回歸模型的概述 26
第四章 實驗結果 41
4.1 資料庫介紹 41
4.2 實驗分析與結果討論 49
第五章 結論與未來展望 57
參考文獻 58

[1] T.-J. Liu, Y.-C. Lin,W. Lin, and C.-C. J. Kuo, "Visual quality assessment: recent developments, coding applications and future trends," APSIPA Transactions on Signal and Information Processing, pp. vol. 2, e4, 2013.
[2] T.-J. Liu,W. Lin, and C.-C. J. Kuo, "Recent developments and future trends in visual quality assessment," Proceedings of Asia-Pacific Signal and Information Processing Association Annual Submit and Conference, p. 18–21, 2011.
[3] H. R. Sheikh, M. F. Sabir and A. C. Bovik, "A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms," IEEE Transactions on Image Processing, vol. 15, no. 11, pp. 3440-3451, Nov 2006.
[4] H. R. Sheikh and A. C. Bovik, "Image information and visual quality," IEEE Transactions on Image Processing, vol. 15, no. 2, pp. 430-444, Feb 2006.
[5] Z. Wang, E.P. Simoncelli, and A. C. Bovik, "Multi-scale structural similarity for image quality assessment," IEEE Asilomar Conf. Signals, Systems, and Computers, pp. 1398-1402, 2003.
[6] A. Benoit, P. Le Callet, P. CampisiEmail and R. Cousseau, "Using disparity for quality assessment of stereoscopic images," Proceedings of the 15th IEEE International Conference on Image Processing, 2008.
[7] M.-J. Chen, C.-C. Su, D.-K. Kwon, L.K. Cormack and A.C. Bovik, "Full-reference quality assessment of stereopairs accounting for rivalry," Signal Processing: Image Communication, vol. 28, no. 10, pp. 1143-1155, Oct 2013.
[8] Feng Shao, Gang-yi Jiang, Mei Yu, Fucui Li, Zongju Peng, Randi Fu, "Binocular energy response based quality assessment of stereoscopic images," Digital Signal Processing, vol. 29, pp. 45-53, 2014.
[9] A. K. Moorthy and A. C. Bovik, "A Two-Step Framework for Constructing Blind Image Quality Indices," IEEE Signal Processing Letters, vol. 17, no. 5, pp. 513-516, May 2010.
[10] A. Mittal, A. K. Moorthy and A. C. Bovik, "Referenceless Image Spatial Quality Evaluation Engine," 45th Asilomar Conference on Signals, Systems and Computers, Nov 2011.


[11] M.A. Saad, A. C. Bovik, and C. Charrier, "DCT Statistics Model-Based Blind Image Quality Assessment," Proceedings of the IEEE International Conference on image Processing (ICIP), pp. 3093-3096, Sept 2011.
[12] A. K. Moorthy and A. C. Bovik, "Blind Image Quality Assessment: From Scene Statistics to Perceptual Quality," IEEE Transactions Image Processing, vol. 20, no. 12, pp. 3350-3364, Dec 2011.
[13] D. Ghadiyaram and A. C. Bovik, "Blind image quality assessment on real distorted images using deep belief nets," Proc. IEEE Global Conf. Signal Inf. Process., pp. 946-950, Dec 2014.
[14] L. Kang, P. Ye, Y. Li, and D. Doermann, "Convolutional neural networks for no-refernce image quality assessment," Proc. IEEE Conf.Comput. Vis. Pattern Recognit., pp. 1733-1740, Jun 2014.
[15] M.-J. Chen, L. K. Cormack, and A. C. Bovik, "No reference quality assessment of natural stereopairs," IEEE Transactions on Image Processing, vol. 22, no. 9, pp. 3379-3391, 2013.
[16] W. Zhou and L. Yu, "Binocular Responses for No-Reference 3D Image Quality Assessment," IEEE Transactions on Multimedia, vol. 18, no. 6, pp. 1077-1084, Jun 2016.
[17] F. Shao, K. Li, W. Lin, G. Jiang and Q. Dai, "Learning Blind Quality Evaluator for Stereoscopic Images Using Joint Sparse Representation," IEEE Transactions on Multimedia, vol. 18, no. 10, pp. 2104-2114, Oct 2016.
[18] Ching-Ti Lin, Tsung-Jung Liu, Kuan-Hsien Liu, "VISUAL QUALITY PREDICTION ON DISTORTED STEREOSCOPIC IMAGES," IEEE International Conference on Image Processing (ICIP), 2017.
[19] F. Shao, W. Tian, W. Lin, G. Jiang and Q. Dai, "Toward a Blind Deep Quality Evaluator for Stereoscopic Images Based on Monocular and Binocular Interactions," IEEE Transactions on Image Processing, vol. 25, no. 5, pp. 2059-2074, May 2016.
[20] G. Engel, "The visual processes underlying binocular brightness summation," Vision Research, vol. 7, no. 9, pp. 753-767, 1967.
[21] D.W. Curtis and S.J. Rule, "Binocular processing of brightness in forma tion: a vector-sum model," Journal of Experimental Psychology: Human Perception and Performance, pp. 132-143, Feb 1978.


[22] Jian Ding, George Sperling and Ramesh Srinivasan, "Attentional Modulation of SSVEP Power Depends on the Network Tagged by the Flicker Frequency," Cerebral Cortex, vol. 16, no. 7, p. 1016–1029, July 2006.
[23] A. I. Cogan, "Human binocular interaction: Towards a neural model," Vision Research, vol. 27, no. 12, pp. 2125-2139, 1987.
[24] T. Ojala, M. Pietikainen and D. Harwood, "Performance evaluation of texture measures with classification based on Kullback discrimination of distributions," Proceedings of 12th International Conference on Pattern Recognition, Jerusalem, vol. 1, pp. 582-585, 1994.
[25] T.Ojala, M. Pietikäinen and D. Harwood, "A comparative study of texture measures with classification based on featured distributions," Pattern Recognition, vol. 29, no. 1, pp. 51-59, 1996.
[26] T. Ojala, M. Pietikainen and T. Maenpaa, "Multiresolution gray-scale and rotation invariant texture classification with local binary patterns," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 24, no. 7, pp. 971-987, Jul 2002.
[27] C. C. Chang and C. J. Lin, "Libsvm: A Library for Support," 2001. [Online]. Available: https://www.csie.ntu.edu.tw/~cjlin/libsvm/.
[28] N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on Systems, Man, and Cybernetics, vol. 1, pp. 62-66, Jan 1979.
[29] I. Guyon and A. Elisseeff, "An introduction to variable and feature selection," j. mach. learn. res, vol. 3, pp. 1157-1182, March 2003.
[30] A. K. Moorthy, C.-C. Su, A. Mittal, and A. C. Bovik, "Subjective evaluation of stereoscopic image quality," Signal Processing: Image Communication, vol. 28, no. 8, pp. 870-883, 2013.
[31] "LIVE 3D Image Quality database phase I," [Online]. Available: http://live.ece.utexas.edu/research/quality/live_3dimage_phase1.html.
[32] "LIVE 3D Image Quality Database - Phase II," [Online]. Available: http://live.ece.utexas.edu/research/quality/live_3dimage_phase2.html.
[33] R. Song, H. Ko, and C. C. J. Kuo, "MCL-3D: A database for stereoscopic image quality assessment using 2D-image-plus-depth source," J. Inf. Sci. Eng., vol. 31, no. 5, p. 1593–1611, 2015.