Title :
Identification of degraded traffic sign symbols by a generative learning method
Author :
Ishida, Hiroyuki ; Takahashi, Tomokazu ; Ide, Ichiro ; Mekada, Yoshito ; Murase, Hiroshi
Author_Institution :
Graduate Sch. of Inf. Sci., Nagoya Univ.
Abstract :
We present a novel training method for recognizing traffic sign symbols undergoing image degradations. In order to cope with the degradations, it is desirable to use similarly degraded images as training data. Our method artificially generates these data from an original image in accordance with the actual degradations. We experimentally confirmed the usefulness of our method for the camera-based traffic sign recognition
Keywords :
image recognition; learning (artificial intelligence); traffic engineering computing; camera-based traffic sign recognition; degraded traffic sign symbol identification; generative learning method; image degradations; traffic sign symbol recognition; Cameras; Degradation; Image edge detection; Image generation; Image recognition; Image segmentation; Information science; Learning systems; Shape; Training data;
Conference_Titel :
Pattern Recognition, 2006. ICPR 2006. 18th International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
0-7695-2521-0
DOI :
10.1109/ICPR.2006.674
