隨著網路及科技的日新月異，數位相機、平板、智慧型手機等可攜式影音多媒體裝置的普及化，使得數位影像資料每天以爆炸式地增長，進入大數據(Big Data)時代。在面對大量且複雜的影像資料庫，如何有效管理並依照使用者的需求檢索所需影像，是目前影像檢索技術所面臨的重要課題。為了學習出最佳的影像特徵描述，以取得穩定且正確的影像檢索結果，因此將不同架構的摺積神經網路結合在一起，以提升特徵描述的學習效果。
本論文提出使用兩種不同架構的摺積神經網路(Convolutional Neural Networks, CNN)組成混合式整體學習 (Mixture of Ensemble Learning) 模型的方法。其將兩種深度學習網路(AlexNet 和 NIN)學習出的影像特徵描述，經加權平均運算後，取得更能夠代表影像的特徵描述，以便能迅速得到正確的檢索結果。由實驗結果顯示，CNN的整體學習架構確實能夠有效提升學習的效果，使影像分類的準確度高於單一摺積神經網路。而將整體學習出來的影像特徵，應用到影像檢索之中，在CIFAR-10及CIFAR-100影像資料庫的檢索平均準確率(mean average precision, MAP )達到0.867和0.526的表現。

Rapid Internet deployment and technology development have led us into the era of Big Data. There are numerous digital image data being continuously produced by our pads, smartphones, digital cameras, and other portable multimedia devices. We are facing many problems of challenge. One of the primary problems is how we can find an effective method to manage our image datasets and conduct customized retrieval. We propose a model, which combines two distinguishable deep Convolutional Neural Networks (CNN) architectures to achieve better performance for image retrieval.
This paper proposes an ensemble model based on a mixed architecture of deep CNN. It utilizes two kinds of deep learning networks, AlexNet and Network In Network (NIN), to obtain the image features, and to compute the weighted average feature vectors for image retrieval. From our experiment result, ensemble architecture could effectively enhance learning with higher accuracy than single CNN in image classification. The proposed Mixture of deep CNN-based Ensemble Model (MCNNE) was applied to CIFAR-10 and CIFAR-100 datasets. It achieved 0.867 and 0.526 Mean Average Precision (MAP) in image retrieval tasks, respectively.

[1] Y. Liu, H. Liu, B. Zhang and G. Wu, “Extraction of if-then rules from trained neural network and its application to earthquake prediction,” Proceedings of the Third IEEE International Conference on Cognitive Informatics, 2004.
[2] T. Kondo, J. Ueno, and S. Takao, “Medical image diagnosis of lung cancer by revised GMDH-type neural network self-selecting optimum neuron architectures,” System Integration (SII), IEEE/SICE International Symposium, 2011.
[3] N.L.D. Khoa, K. Sakakibara, and I. Nishikawa, “Stock Price Forecasting using Back Propagation Neural Networks with Time and Profit Based Adjusted Weight Factors,” SICE-ICASE, International Joint Conference, 2006.
[4] G.E. Hinton, and R.R. Salakhutdinov, “Reducing the dimensionality of data with neural networks,” Science, Vol. 313. no. 5786, pp. 504 - 507, 28 July 2006.
[5] http://www.ling.fju.edu.tw/hearing/brain-into.htm
[6] 蘇木春、張孝德 機器學習 : 類神經網路.模糊系統以及基因演算法則，修訂第二版，全華圖書出版社，2004，ISBN 9572147374
[7] D.E. Rumelhart, G.E. Hinton, and R.J. Williams, “Learning representations by back-propagating errors,” Nature 323 (6088): 533–536, 8 October 1986.
[8] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-Based Learning Applied to Document Recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998
[9] I. Mrazova, and M. Kukacka, “Hybrid convolutional neural networks,” Industrial Informatics INDIN 2008. 6th IEEE International Conference, 2008.
[10] D. Ciresan, U. Meier, and J. Schmidhuber, “Multi-column deep neural networks for image classification,” in Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on, pp. 3642-3649, 2012.
[11] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks”, Advances in neural information processing systems, pp. 1097-1105, 2012.
[12] M. Lin, Q. Chen, and S. Yan, “Network in network,” Computing Research Repository, 2013.
[13] K. Simonyan, and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” International Conference on Learning Representations, 2015.
[14] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.1-9, 2015.
[15] T. G. Dietterich, “Ensemble methods in machine learning,” in Multiple classifier systems, Springer Berlin Heidelberg, pp.1-15, 2000.
[16] Y. Freund, R. Schapire, and N. Abe, “A short introduction to boosting,” Journal-Japanese Society For Artificial Intelligence, 1999.
[17] Y. Liu, D. Zhang, G. Lu, and W. Y. Ma, “A survey of content-based image retrieval with high-level semantics,” Pattern Recognition vol. 40, no.1, pp. 262-282, 2007.
[18] X.S. Zhou, and T.S. Huang, “CBIR: from low-level features to high-level semantics,” Proceedings of the SPIE, Image and Video Communication and Processing, San Jose, CA, vol. 3974, pp. 426–431, 2000.
[19] Y. Chen, J.Z. Wang, and R. Krovetz, “An unsupervised learning approach to content-based image retrieval,” IEEE Proceedings of the International Symposium on Signal Processing and its Applications, pp. 197–200, 2003.
[20] A.W. Smeulders, M. Worring, S. Santini, A. Gupta, and R. Jain, “Content-based image retrieval at the end of the early years,” Pattern Analysis and Machine Intelligence, IEEE Transactions on 22.12, pp. 1349-1380, 2000.
[21] M.J. Swain, and D.H. Ballard, “Color Indexing,” International Journal of Computer Vision, pp. 11-32, 1991.
[22] M.A. Stricker, and M. Orengo, “Similarity of color images,” IS&T/SPIE's Symposium on Electronic Imaging: Science & Technology. International Society for Optics and Photonics, 1995.
[23] G. Pass, R. Zabih, and J. Miller, “Comparing images using color coherence vectors,” Proceedings of the fourth ACM international conference on Multimedia. ACM, 1997.
[24] M. Ferman, A.M. Tekalp, and R. Mehrotra, “Robust Color Histogram Descriptors for Video Segment Retrieval and Identification”, IEEE Transactions on Image Processing, vol. 11, no. 5, pp. 497-508, 2002.
[25] H. Tamura, S. Mori, T. Yamawaki, “Texture features corresponding to visual perception,” IEEE Transactions on Systems, Man and Cybernetics, vol. 8, no. 6, pp.460-473, 1978.
[26] T. Ojala, M. Pietikäinen, and D. Harwood, “Performance evaluation of texture measures with classification based on Kullback discrimination of distributions,” Proceedings of the 12th IAPR International Conference on Pattern Recognition, vol. 1, pp. 582 – 585, 1994.
[27] X. Wang, T.X. Han, and S. Yan, “An HOG-LBP human detector with partial occlusion handling,” 2009 IEEE 12th International Conference on Computer Vision, 2009.
[28] C.H. Kuo, Y.H. Chou, and P.C. Chang, “Using Deep Convolutional Neural Networks for Image Retrieval,” Visual Information Processing and Communication VI, February 2016
[29] R. Xia, Y. Pan, H. Lai, C. Liu, and S. Yan, “Supervised Hashing for Image Retrieval via Image Representation Learning,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2014.
[30] D. Cireşan, U. Meier, and J. Masci, “Multi-column deep neural network for traffic sign classification,” Neural Networks, 2012.
[31] A. Coates, A.Y. Ng, and H. Lee, “An analysis of single-layer networks in unsupervised feature learning,” International conference on artificial intelligence and statistics, 2011.
[32] I.J. Goodfellow, D. Warde-Farley, M. Mirza, A. Courville, and Y. Bengio, “Maxout networks,” arXiv preprint arXiv:1302.4389, 2013.
[33] Y. Jia, et al., “Caffe: Convolutional architecture for fast feature embedding,” In Proceedings of the ACM International Conference on Multimedia, 2014.
[34] A. Torralba, R. Fergus, and W. Freeman, “80 million tiny images: A large data set for nonparametric object and scene recognition,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30, no. 11, pp. 1958-1970, 2008.