Title :
Using reinforcement learning for image thresholding
Author :
Shokri, Maryam ; Tizhoosh, Hamid R.
Author_Institution :
Dept. of Syst. Design Eng., Waterloo Univ., Ont., Canada
Abstract :
This paper introduces a reinforcement-learning concept to find the optimal threshold for digital images. The proposed approach can integrate human expert knowledge in an objective or subjective way to overcome the shortcomings of existing methods.
Keywords :
image segmentation; learning (artificial intelligence); digital images; human expert knowledge; image thresholding; reinforcement learning; Design engineering; Digital images; Graphical user interfaces; Histograms; Humans; Image processing; Learning; Lighting; Shape; Systems engineering and theory;
Conference_Titel :
Electrical and Computer Engineering, 2003. IEEE CCECE 2003. Canadian Conference on
Print_ISBN :
0-7803-7781-8
DOI :
10.1109/CCECE.2003.1226121
