Abstract
This paper comes to solve the problem of parameter tuning in image processing. This task is mostly done manually by users, but the multitude of possible values makes it tedious and time consuming. A distributed reinforcement learning using the Q-learning algorithm combined with Kalman filters is proposed to help users to find the optimal values of a combination of image processing operators. This combination is used to extract an object of interest from an image. The obtained results show how the proposed method behaves well to reach good results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhao, X.M., Wang, W.X., Wang, L.P.: Parameter optimal determination for canny edge detection. Imaging Sci. J. 59(6), 332–341 (2011). https://doi.org/10.1179/136821910x12867873897517
Qaffou, I., Sadgal, M., Elfazziki, A.: a multi-agents architecture to learn vision operators and their parameters. Int. J. Comput. Sci. Issues 9(3), 140 (2012)
Qaffou, I., Sadgal, M., Elfazziki, A.: Selecting vision operators and fixing their optimal parameters values using reinforcement learning. In: Elmoataz, A., Mammass, D., Lezoray, O., Nouboud, F., Aboutajdine, D. (eds.) ICISP 2012. LNCS, vol. 7340, pp. 103–112. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-31254-0_12
Benchikhi, L., et al.: A Novel Adaptive Discrete Cuckoo Search Algorithm for parameter optimization in computer vision. Intel. Artif. 20(60), 51–71 (2017)
Nickolay, B., Schneider, B., Jacob, S.: Parameter optimisation of an image processing system using evolutionary algorithms. In: Sommer, G., Daniilidis, K., Pauli, J. (eds.) Computer Analysis of Images and Patterns, pp. 637–644. Springer Berlin Heidelberg, Berlin, Heidelberg (1997). https://doi.org/10.1007/3-540-63460-6_173
Taylor, G.W.: a reinforcement learning framework for parameter control in computer vision applications. In: Proceedings of the First Canadian Conference on Computer and Robot Vision (CRV 2004). IEEE (2004)
Qaffou, I.: Optimization of the process of parameter adjustment: image processing as a case study. In: IEEE 6th International Conference on Optimization and Applications (2020)
Qaffou, I.: Adaptive image processing using multi-agent reinforcement learning. In: Kacprzyk, J., Balas, V.E., Ezziyyani, M. (eds.) Advanced Intelligent Systems for Sustainable Development (AI2SD’2020): Volume 2, pp. 499–507. Springer International Publishing, Cham (2022). https://doi.org/10.1007/978-3-030-90639-9_40
Qaffou, I.: A machine learning assistant for choosing operators and tuning their parameters in image processing tasks. In: Masrour, T., Cherrafi, A., El Hassani, I. (eds.) A2IA 2020. AISC, vol. 1193, pp. 339–350. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-51186-9_24
Georgeff, M.P.: A theory of action for multi-agent planning. In: Proceedings of the AAAI-84, pp. 125–129. Austin, TX (1984)
Vanderveken, D.: The Logic of Speech Acts. Cambridge University Press (1994)
Malone, T.W.: Modeling coordination in organizations and markets. Manage. Sci. 33, 1317–1332 (1986)
Ferber, J.: Les systèmes multi-agents: vers une intelligence collective. France, InterEditions, Paris (1995)
Watkins, C.J.C.H.: Learning from Delayed Rewards. PhD thesis, Cambridge University (1989)
Kalman, R.E.: A new approach to linear filtering and prediction problems. Transactions of the American Society of Mechanical Engineers. J. Basic Eng. (1960)
Transaction of the ASME- Journal of Basic Engineering, 82 (series D), 35–45
Harkat, S.: Application du Filtre de Kalman sur la variabilité pluviométrique dans le bassin versant de Chellif » Algerie,Université de Chlef, 188pp (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Qaffou, I. (2023). A New Distributed Architecture Based on Reinforcement Learning for Parameter Estimation in Image Processing. In: Kacprzyk, J., Ezziyyani, M., Balas, V.E. (eds) International Conference on Advanced Intelligent Systems for Sustainable Development. AI2SD 2022. Lecture Notes in Networks and Systems, vol 637. Springer, Cham. https://doi.org/10.1007/978-3-031-26384-2_82
Download citation
DOI: https://doi.org/10.1007/978-3-031-26384-2_82
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26383-5
Online ISBN: 978-3-031-26384-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)