Title :
On-road speed sign recognition using fuzzy kernel-based learning vector quantization
Author :
Chiang, Hsin-Han ; Lee, Tsu-Tian ; Lee, Jian-Xun
Author_Institution :
Dept. Electr. Eng., Fu Jen Catholic Univ., Taipei, Taiwan
Abstract :
This paper presents an automatic speed sign recognition for providing the visual driving-assistance of speed limits awareness. To reduce the influence of digital noise caused by lighting condition and pollution, a segmentation based on pan-red color information is applied to extract the shape of speed sign. Based on the edge gradient information of a circle shape, a radially symmetry detection strategy is proposed for fast detecting the speed sign candidate from road scenes. The recognition of the content of speed sign is achieved through the fuzzy kernel-based learning vector quantization (FKLVQ) which also verifies each candidate to eliminate non-target blobs. Results show the feasibility and effectiveness of the proposed system under a wide variety of visual conditions.
Keywords :
fuzzy set theory; learning (artificial intelligence); shape recognition; vector quantisation; automatic speed sign recognition; content recognition; edge gradient information; fuzzy kernel based learning vector quantization; on-road speed sign recognition; pan red color information; Image color analysis; Image edge detection; Image segmentation; Mathematical model; Neurons; Pixel; Shape; Speed sign recognition; color segmentation; fuzzy; learning vector quantization(LVQ); radial symmetry detection;
Conference_Titel :
System Science and Engineering (ICSSE), 2011 International Conference on
Conference_Location :
Macao
Print_ISBN :
978-1-61284-351-3
Electronic_ISBN :
978-1-61284-472-5
DOI :
10.1109/ICSSE.2011.5961872
