DocumentCode :
515331
Title :
A reinforcement learning method to adjust parameter of a texture segmentation
Author :
Qaffou, Issam ; Sadgal, Mohamed ; Elfazziki, Abdelaziz
Author_Institution :
Dept. Inf., Univ. Cadi Ayyad, Marrakech, Morocco
fYear :
2010
fDate :
28-30 March 2010
Firstpage :
1
Lastpage :
5
Abstract :
In spite of all the progress known frequently by the computer vision field, the user intervention stays always necessary. In all images processing tasks, it is to the user to adjust the parameters of the vision operators in order to reach the desired result. The manually adjustment of these parameters isn´t an easy work, it becomes more tedious with complicated vision applications such as texture detection. This paper comes to help the user by proposing him a scientific method to automatically adjust these parameters. Our method is based on reinforcement learning, the optimal parameters are determined according to the definition of states, actions and reward. Our method takes in account not only the system opportunities, but also the user preferences. And through the learning mechanism it will suggest trustworthy solutions. An example to test our method by detecting an object in a textural image is given.
Keywords :
computer vision; image segmentation; image texture; learning (artificial intelligence); computer vision; image processing; reinforcement learning method; texture detection; texture segmentation; vision operators; Biomedical imaging; Cancer detection; Computer vision; Image analysis; Image processing; Image segmentation; Learning systems; Machine vision; Object detection; Testing; Q-learning; Reinforcement Learning (RL); Texture segmentation; parameter adjustment; vision;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Informatics and Systems (INFOS), 2010 The 7th International Conference on
Conference_Location :
Cairo
Print_ISBN :
978-1-4244-5828-8
Type :
conf
Filename :
5461725
Link To Document :
بازگشت