A reinforcement learning framework for parameter control in computer vision applications

被引：3
|
作者：
Taylor, GW [1 ]
机构：
[1] Univ Waterloo, Pattern Anal & Machine Intelligence Lab, Waterloo, ON N2L 3G1, Canada
来源：
1ST CANADIAN CONFERENCE ON COMPUTER AND ROBOT VISION, PROCEEDINGS | 2004年
关键词：
D O I：
10.1109/CCCRV.2004.1301489
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We propose a framework for solving the parameter selection problem for computer vision applications using reinforcement learning agents. Connectionist-based function approximation is employed to reduce the state space. Automatic determination of fuzzy membership functions is stated as a specific case of the parameter selection problem. Entropy of a fuzzy event is used as a reinforcement. We have carried out experiments to generate brightness membership functions for several images. The results show that the reinforcement learning approach is superior to an existing simulated annealing-based approach.
引用
收藏
页码：496 / 503
页数：8
相关论文
共 50 条
  • [31] Vision-based Deep Reinforcement Learning to Control a Manipulator
    Kim, Wonchul
    Kim, Taewan
    Lee, Jonggu
    Kim, H. Jin
    [J]. 2017 11TH ASIAN CONTROL CONFERENCE (ASCC), 2017, : 1046 - 1050
  • [32] Vision-based robust control framework based on deep reinforcement learning applied to autonomous ground vehicles
    de Morais, Gustavo A. P.
    Marcos, Lucas B.
    Bueno, Jose Nuno A. D.
    de Resende, Nilo F.
    Terra, Marco Henrique
    Grassi Jr, Valdir
    [J]. CONTROL ENGINEERING PRACTICE, 2020, 104
  • [33] Generalizable control for quantum parameter estimation through reinforcement learning
    Han Xu
    Junning Li
    Liqiang Liu
    Yu Wang
    Haidong Yuan
    Xin Wang
    [J]. npj Quantum Information, 5
  • [34] Deep Reinforcement Learning Based Parameter Control in Differential Evolution
    Sharma, Mudita
    Komninos, Alexandros
    Lopez-Ibanez, Manuel
    Kazakov, Dimitar
    [J]. PROCEEDINGS OF THE 2019 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE (GECCO'19), 2019, : 709 - 717
  • [35] A parameter control method inspired from neuromodulators in reinforcement learning
    Murakoshi, K
    Mizuno, J
    [J]. 2003 IEEE INTERNATIONAL SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN ROBOTICS AND AUTOMATION, VOLS I-III, PROCEEDINGS, 2003, : 7 - 12
  • [36] Generalizable control for quantum parameter estimation through reinforcement learning
    Xu, Han
    Li, Junning
    Liu, Liqiang
    Wang, Yu
    Yuan, Haidong
    Wang, Xin
    [J]. NPJ QUANTUM INFORMATION, 2019, 5 (1)
  • [37] Intelligent Assessment of Advertising Art Design Based on Reinforcement Learning and Computer Vision
    Lin Y.
    Wang B.
    [J]. Computer-Aided Design and Applications, 2024, 21 (S23): : 254 - 267
  • [38] A Computer Vision Encyclopedia-Based Framework with Illustrative UAV Applications
    Morley, Terence
    Morris, Tim
    Turner, Martin
    [J]. COMPUTERS, 2021, 10 (03) : 1 - 11
  • [39] Deep learning computer vision for robotic disassembly and servicing applications
    Brogan, Daniel P.
    DiFilippo, Nicholas M.
    Jouaneh, Musa K.
    [J]. Array, 2021, 12
  • [40] Editorial: Resource Efficient Deep Learning for Computer Vision Applications
    Li, Yang
    Song, Houbing Herbert
    [J]. MOBILE NETWORKS & APPLICATIONS, 2024,
12345