Title :
Application of Opposition-Based Reinforcement Learning in Image Segmentation
Author :
Sahba, Farhang ; Tizhoosh, Hamid R. ; Salama, Magdy M M A
Author_Institution :
Dept. of Syst. Design Eng., Waterloo Univ., Ont.
Abstract :
In this paper a method for image segmentation using an opposition-based reinforcement learning scheme is introduced. We use this agent-based approach to optimally find the appropriate local values and segment the object. The agent uses an image and its manually segmented version and takes some actions to change the environment (the quality of segmented image). The agent is provided with a scalar reinforcement signal as reward/punishment. The agent uses this information to explore/exploit the solution space. The values obtained can be used as valuable knowledge to fill the Q-matrix. The results demonstrate potential for applying this new method in the field of medical image segmentation
Keywords :
computer vision; image segmentation; learning (artificial intelligence); matrix algebra; software agents; Q-matrix; agent-based approach; medical image segmentation; object segmentation; opposition-based reinforcement learning; scalar reinforcement signal; Application software; Computational intelligence; Design engineering; Image segmentation; Learning; Machine intelligence; Pattern analysis; Signal processing; System analysis and design; Systems engineering and theory;
Conference_Titel :
Computational Intelligence in Image and Signal Processing, 2007. CIISP 2007. IEEE Symposium on
Conference_Location :
Honolulu, HI
Print_ISBN :
1-4244-0707-9
DOI :
10.1109/CIISP.2007.369176
