Traffic sign shape classification based on Support Vector Machines and the FFT of the signature of blobs Export

@inproceedings{citeulike:2467504, abstract = {In many traffic sign recognition systems, one of the main tasks is the classification of the shape of the blob, which is intended to simplify the recognition process. In this paper, we have developed a new shape classification algorithm based on Support Vector Machines classifiers and the FFT of the signature of the blob. The FFT of the signature yields invariance to object scalings and rotations. Furthermore, the FFT is the vector input to the classifier. This classifier is trained to cope with projection deformations and occlusions. The algorithm has been tested under adverse conditions, such as geometric distortions, i.e. scaling, rotations and projection deformations, and occlusions. The experimental results show good robustness when the system is working with real, outdoor road images.}, author = {Gil-Jimenez, P. and Gomez-Moreno, H. and Siegmann, P. and Lafuente-Arroyo, S. and Maldonado-Bascon, S.}, booktitle = {Intelligent Vehicles Symposium, 2007 IEEE}, citeulike-article-id = {2467504}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/IVS.2007.4290143}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4290143}, doi = {10.1109/IVS.2007.4290143}, journal = {Intelligent Vehicles Symposium, 2007 IEEE}, keywords = {blob, classification, sign, svm}, pages = {375--380}, posted-at = {2008-03-04 19:50:23}, priority = {2}, title = {Traffic sign shape classification based on Support Vector Machines and the FFT of the signature of blobs}, url = {http://dx.doi.org/10.1109/IVS.2007.4290143}, year = {2007} }

TY - CONF ID - citeulike:2467504 L3 - citeulike-article-id:2467504 N2 - In many traffic sign recognition systems, one of the main tasks is the classification of the shape of the blob, which is intended to simplify the recognition process. In this paper, we have developed a new shape classification algorithm based on Support Vector Machines classifiers and the FFT of the signature of the blob. The FFT of the signature yields invariance to object scalings and rotations. Furthermore, the FFT is the vector input to the classifier. This classifier is trained to cope with projection deformations and occlusions. The algorithm has been tested under adverse conditions, such as geometric distortions, i.e. scaling, rotations and projection deformations, and occlusions. The experimental results show good robustness when the system is working with real, outdoor road images. JF - Intelligent Vehicles Symposium, 2007 IEEE EP - 380 TI - Traffic sign shape classification based on Support Vector Machines and the FFT of the signature of blobs T2 - Intelligent Vehicles Symposium, 2007 IEEE SP - 375 KW - blob KW - classification KW - sign KW - svm AU - Gil-Jimenez, P AU - Gomez-Moreno, H AU - Siegmann, P AU - Lafuente-Arroyo, S AU - Maldonado-Bascon, S PY - 2007/// UR - http://dx.doi.org/10.1109/IVS.2007.4290143 ER -