Results

Please find below all results that were submitted for the final GTSRB dataset. The teams marked with a are participants of the final competition session that was held at IJCNN 2011. For results of the first phase of the competition, please see the IJCNN 2011 Competition result table.

Each entry is linked to the corresponding publication (except, for now, for the competition entries). The full list of references is located below the table.

Team	Method	Total	Subset
[156] DeepKnowledge Seville	CNN with 3 Spatial Transformers	99.71%	99.71%
[3] IDSIA	Committee of CNNs	99.46%	99.46%
[155] COSFIRE	Color-blob-based COSFIRE filters for object recogn	98.97%	98.97%
[1] INI-RTCV	Human Performance	98.84%	98.84%
[4] sermanet	Multi-Scale CNNs	98.31%	98.31%
[2] CAOR	Random Forests	96.14%	96.14%
[6] INI-RTCV	LDA on HOG 2	95.68%	95.68%
[5] INI-RTCV	LDA on HOG 1	93.18%	93.18%
[7] INI-RTCV	LDA on HOG 3	92.34%	92.34%

References

[1] Human Performance, INI-RTCV , Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition, Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition, J. Stallkamp, M. Schlipsing, J. Salmen, C. Igel, August 2012, Neural Networks (32), pp. 323-332

[2] Random Forests, CAOR , Traffic sign classification using K-d trees and Random Forests , Traffic sign classification using K-d trees and Random Forests , F. Zaklouta, B. Stanciulescu, O. Hamdoun, August 2011, International Joint Conference on Neural Networks (IJCNN) 2011

[3] Committee of CNNs, IDSIA , Multi-column deep neural network for traffic sign classification, Multi-column deep neural network for traffic sign classification, D. Ciresan, U. Meier, J. Masci, J. Schmidhuber, August 2012, Neural Networks (32), pp. 333-338

[4] Multi-Scale CNNs, sermanet , Traffic sign recognition with multi-scale Convolutional Networks, Traffic sign recognition with multi-scale Convolutional Networks, P. Sermanet, Y. LeCun, August 2011, International Joint Conference on Neural Networks (IJCNN) 2011

[5] LDA on HOG 1, INI-RTCV, Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition, Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition, J. Stallkamp, M. Schlipsing, J. Salmen, C. Igel, August 2012, Neural Networks (32), pp. 323-332

[6] LDA on HOG 2, INI-RTCV, Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition, Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition, J. Stallkamp, M. Schlipsing, J. Salmen, C. Igel, August 2012, Neural Networks (32), pp. 323-332

[7] LDA on HOG 3, INI-RTCV, Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition, Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition, J. Stallkamp, M. Schlipsing, J. Salmen, C. Igel, August 2012, Neural Networks (32), pp. 323-332

[155] Color-blob-based COSFIRE filters for object recogn, COSFIRE, Color-blob-based COSFIRE filters for Object Recognition, Color-blob-based COSFIRE filters for Object Recognition, Baris Gecer, George Azzopardi, Nicolai Petkov, 2017, Image and Vision Computing(57), pp. 165-174

[156] CNN with 3 Spatial Transformers, DeepKnowledge Seville, Álvaro Arcos-García and Juan A. Álvarez-García and Luis M. Soria-Morillo, Neural Networks