Title :
Increasing Object Recognition Rate using Reinforced Segmentation
Author :
Sahba, Farshid ; Tizhoosh, Hamid R. ; Salama, Magdy M. A.
Author_Institution :
Syst. Design Eng., Waterloo Univ., Ont., Canada
Abstract :
In this paper a new approach to object extraction and recognition based on reinforcement learning is presented. We use this novel idea as a method to optimally segment the image and increase the recognition rate. The success rate is compared with a classical approach. Preliminary results demonstrate increase in recognition rate.
Keywords :
feature extraction; image segmentation; learning (artificial intelligence); object recognition; image segmentation; object extraction; object recognition; reinforcement learning; Data mining; Design engineering; Image recognition; Image segmentation; Laboratories; Learning; Machine intelligence; Object detection; Object recognition; Pattern analysis; Image segmentation; Learning systems; Object detection;
Conference_Titel :
Image Processing, 2006 IEEE International Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
1-4244-0480-0
DOI :
10.1109/ICIP.2006.312518
