Image Sampling Using Q-Learning

International Journal of Computer Science and Engineering

© 2021 by SSRG - IJCSE Journal

Volume 8 Issue 1

Year of Publication : 2021

Authors : Ningxia He

10.14445/23488387/IJCSE-V8I1P102

How to Cite?

Ningxia He, "Image Sampling Using Q-Learning," SSRG International Journal of Computer Science and Engineering , vol. 8,  no. 1, pp. 5-12, 2021. Crossref, https://doi.org/10.14445/23488387/IJCSE-V8I1P102

Abstract:

With the advent of the digital information age and multimedia technology development, the amount of image data is increasing day by day. The method of image sampling has been paid much attention to. The traditional triangular mesh sampling method needs to initialize the sampling set and the metric tensor before sampling, which is prone to problems such as unreasonable specification. Therefore, an intelligent image sampling method based on the Q-Learning reinforcement learning algorithm is proposed. Built on the interaction between reinforcement learning agents and the environment, an adaptive sampling method is designed to update agents' characteristics constantly. The experimental results show that this method can achieve the same effect as the traditional triangular mesh sampling method and is more intelligent.

Keywords:

image sampling, reinforcement Learning, Q-Learning algorithm

References:

[1] Voronin, V. V. Holographic representation in image processing tasks. Pattern Recognition and Image Analysis (Advances in Mathematical Theory and Applications) 11.1 (2001) 265-267.
[2] Ying, Liu, Surendra Ranganath, and Xiaofang Zhou. Wavelet-based image segment representation." Electronics Letters 38(19) (2002) 1091-1092.
[3] Monasse, Pascal, and Frederic Guichard. Fast computation of a contrast-invariant image representation. IEEE Transactions on Image Processing 9(5) (2000) 860-872.
[4] Gan, Tao, Yanmin He, and Weile Zhu. Fast $ M $-Term Pursuit for Sparse Image Representation. IEEE Signal Processing Letters 15 (2008) 116-119.
[5] He, Zhihai. Peak transform for efficient image representation and coding. IEEE Transactions on Image Processing 16(7) (2007) 1741-1754.
[6] Wallace, Gregory K. "Overview of the JPEG (ISO/CCITT) still image compression standard. Image Processing Algorithms and Techniques. 1244. International Society for Optics and Photonics, 1990.
[7] Flusser, Jan. Refined moment calculation using image block representation. IEEE Transactions on Image Processing 9(11) (2000) 1977-1978.
[8] Sullivan, Gary J., and Richard L. Baker. Efficient quadtree coding of images and video. IEEE Transactions on image processing 3(3) (1994) 327-331.
[9] Shukla, Rahul, et al. rate-distortion optimized tree-structured compression algorithms for piecewise polynomial images. IEEE transactions on image processing 14(3) (2005) 343-359.
[10] Scholefield, Adam, and Pier Luigi Dragotti. Quadtree structured image approximation for denoising and interpolation. IEEE transactions on image processing 23(3) (2014) 1226-1239.
[11] Burt, Peter J., and E. H. Edward. Adelson, The laplacian pyramid as a compact image code. IEEE Transactions on Communications 31(4) (1983) 532-540.
[12] Tran, Anh, et al. An efficient pyramid image coding system. ICASSP'87. IEEE International Conference on Acoustics, Speech, and Signal Processing. 12. IEEE, 1987.
[13] De Araújo, Bruno Rodrigues, et al. A survey on implicit surface polygonization. ACM Computing Surveys (CSUR) 47(4) (2015) 1-39.
[14] Bommes, David, et al. Quad‐mesh generation and processing: A survey. Computer Graphics Forum. 32(6). (2013).
[15] Botsch, Mario, et al. Polygon mesh processing. CRC Press, 2010.
[16] Maglo, Adrien, et al. Progressive compression of manifold polygon meshes. Computers & Graphics 36(5) (2012) 349-359.
[17] Adams, Michael D. A flexible content-adaptive mesh-generation strategy for image representation. IEEE Transactions on Image Processing 20(9) (2011) 2414-2427.
[18] Terzopoulos, Demetri, and Manuela Vasilescu. Sampling and reconstruction with adaptive meshes. CVPR. 91 (1991).
[19] Courchesne, O., et al. Adaptive mesh generation of MRI images for 3D reconstruction of human trunk. International Conference Image Analysis and Recognition. Springer, Berlin, Heidelberg, 2007.
[20] Sarkis, Michel, and Klaus Diepold. Content adaptive mesh representation of images using binary space partitions. IEEE Transactions on Image Processing 18(5) (2009) 1069-1079.
[21] Joshi, Siddharth, and Stephen Boyd. Sensor selection via convex optimization. IEEE Transactions on Signal Processing 57(2) (2008) 451-462.
[22] Lawler, Eugene L., and David E. Wood. Branch-and-bound methods: A survey. Operations research 14(4) (1966) 699-719.
[23] Yao, Leehter, William A. Sethares, and Daniel C. Kammer. Sensor placement for on-orbit modal identification via a genetic algorithm. AIAA Journal 31(10) (1993) 1922-1928.
[24] Basirian, Saeed, and Alexander Jung. "Random walk sampling for big data over networks." 2017 International Conference on Sampling Theory and Applications (SampTA). IEEE, 2017.
[25] Abramenko, Oleksii, and Alexander Jung. Graph signal sampling via reinforcement learning. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). IEEE, 2019.
[26] Lu, Yongjie, et al. Energy-Efficient Depth-Based Opportunistic Routing with Q-Learning for Underwater Wireless Sensor Networks. Sensors 20(4) (2020) 1025.
[27] Xu, Qichao, Zhou Su, and Rongxing Lu. Game theory and
reinforcement learning-based secure edge caching in mobile social networks. IEEE Transactions on Information Forensics and Security (2020).
[28] Liu, Libin, and Urbashi Mitra. On Sampled Reinforcement Learning in Wireless Networks: Exploitation of Policy Structures. IEEE Transactions on Communications 68(5) (2020): 2823-2837.
[29] Kaelbling, Leslie Pack, Michael L. Littman, and Andrew W. Moore. Reinforcement learning: A survey. Journal of artificial intelligence research 4 (1996) 237-285.
[30] Sutton, Richard S., and Andrew G. Barto. Reinforcement learning: An introduction. MIT Press, 2018.
[31] Watkins, Christopher JCH, and Peter Dayan. Q-learning. Machine learning 8(3-4) (1992) 279-292.
[32] Al, Walid Abdullah, and Il Dong Yun. Partial policy-based reinforcement learning for anatomical landmark localization in 3d medical images. IEEE Transactions on Medical Imaging 39(4) (2019) 1245-1255.
[33] Fisher, Ronald A. The use of multiple measurements in taxonomic problems. Annals of eugenics 7(2) (1936) 179-188.
[34] Weber, Allan G. The USC-SIPI image database version 5. USC-SIPI Report 315(1) (1997).
[35] da Silva, Eduardo Sant'Ana, Anderson Santos, and Helio Pedrini. Metrics For Image Surface Approximation Based On Triangular Meshes. Image Analysis & Stereology 37(1) (2018) 71-82.