隨著大數據(big data)時代的來臨，人類產生的數位化資料量每天以爆炸式地增長。在面對鉅量影音資料衝擊，如何有效管理日益龐大的多媒體資料庫，並根據使用者的需求取得所需之影像，是目前影像檢索領域所面臨的重要課題。影像檢索技術發展歷史悠久，包含基於文字或內容之影像檢索皆有廣泛的研究與應用，卻也面臨一些使用上的問題。基於文字之影像檢索需要人工註解而耗時耗力，且容易受到標記文字描述的主觀程度所影響；而基於內容之影像檢索則因為傳統影像內容特徵描述無法完整表達影像人類所感知的高階語意概念，使得檢索效果往往不如使用者的預期。
本論文利用深度學習中的摺積神經網路(convolutional neural networks, CNN)做為影像特徵學習的方法。能藉由許多不同層級的特徵處理，將影像內容轉換成抽象的深層語意概念，更能夠代表影像的關鍵特徵，讓使用者能迅速取得正確的檢索影像結果，有助於改善現有影像搜索技術之發展。由實驗結果顯示，CNN的深層架構確實能夠逐層學習出影像的關鍵特徵描述，影像分類的準確度高於一般神經網路。而將所學習的特徵描述應用到影像檢索中，CIFAR-10影像資料庫的檢索平均準確率(mean average precision, MAP )達到0.707的不錯表現。

In the age of Big Data, with the rapid development of Internet and mobile devices, people can easily obtain audio and video information everywhere. Because of the exponential growth of multimedia data, how to efficiently retrieve and manage multimedia information from huge databases becomes an important issue on image retrieval. In content-based image retrieval (CBIR), most existing hand-crafted feature descriptors were considered low-level and far from what human normally perceived the world. It is a challenging problem of “semantic gap” between low-level visual features captured by machines and high-level semantic concepts perceived by human.
This thesis focuses on the high-level image feature learning by the convolutional neural networks (CNN). CNN, as a deep learning framework, can extract image features in different layers, and transfer the image content into (abstract) semantic concepts. These high-level features descriptors can be better image representations than the hand-crafted feature descriptors, and further improve the image retrieval performance. The experimental results show that layer-wise learning of feature hierarchies in CNN can represent the images very well. Using CNN for feature extractions performed on CIFAR-10 dataset with 79.3% accuracy in image classification task, and with 0.707 of mean average precision (MAP) in image retrieval tasks.

[1] Y. Bengio, et al., “Greedy Layer-Wise Training of Deep Networks,” Advances in Neural Information Processing Systems 19, 2007.
[2] G. Casella, E. I. George, “Explaining the Gibbs Sampler,” The American Statistician, vol.46, no. 3, pp. 167-174, 1992.
[3] A. Mnih, and G. E. Hinton, “Learning nonlinear constraints with contrastive backpropagation,” In: Neural Networks, 2005. IJCNN'05. Proceedings. 2005 IEEE International Joint Conference on. IEEE, p. 1302-1307, 2005.
[4] Nair, Vinod, and G. E. Hinton, “3D object recognition with deep belief nets,” Advances in Neural Information Processing Systems, pp. 1339-1347, 2009.
[5] G. E. Dahl, et al., “Phone recognition with the mean-covariance restricted Boltzmann machine,” in Advances in Neural Information Processing Systems 23, 2010, pp. 469-477.
[6] G. E. Hinton, et al., “Deep Neural Networks for Acoustic Modeling in Speech Recognition,” IEEE Signal Processing Magazine, November, 2012.
[7] C. Neubauer, “Evaluation of convolutional neural networks for visual recognition,” IEEE Transactions on Neural Networks, vol. 9, no. 4, pp. 685-696, July 1998
[8] Andrew Ng, “Sparse Auto-encoder”, Lecture notes. Deep Learning and Unsupervised Feature Learning, Winter, 2011
[9] 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, 1998
[10] 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.
[11] I. Mrazova, M. Kukacka, “Hybrid convolutional neural networks”, Industrial Informatics INDIN 2008. 6th IEEE International Conference, 2008.
[12] S. Lawrence, et al. “Face recognition: A convolutional neural-network approach”, IEEE Transactions on Neural Networks, vol.8, no. 1, pp. 98-113, 1997.
[13] Y. Liu, et al., “A survey of content-based image retrieval with high-level semantics”, Pattern Recognition vol. 40, no.1, pp. 262-282, 2007.
[14] 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, May 2002.
[15] 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.
[16] R. Xia, et al., “Supervised hashing for image retrieval via image representation learning”, Proceedings of the AAAI Conference on Artificial Intelligence, 2014.
[17] S. Lazebnik, S. Cordelia, and P. Jean, “Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, 2006.
[18] D. Lowe, “Distinctive image features from scale-invariant keypoints”, In International journal of computer vision, vol. 60, no.2, pp. 91-110, 2004.
[19] J. Liu, “Image retrieval based on bag-of-words model”, arXiv preprint arXiv:1304.5168, 2013.
[20] A. Krizhevsky, G. E. Hinton, “Convolutional deep belief networks on cifar-10”, Unpublished manuscript, 2010.
[21] N. Vinod, G. E. Hinton, “Rectified linear units improve restricted boltzmann machines”, Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 807-814, 2010.
[22] A. Krizhevsky, G. E. Hinton, “Learning multiple layers of features from Tiny Images,” Master’s thesis, Department of Computer Science, University of Toronto, 2009.
[23] 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.