Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Despite decades of research on automatic license plate recognition (ALPR), optical character recognition (OCR) still leaves room for improvement in this context, given that a single OCR miss is enough to miss the entire plate. We propose an OCR approach based on convolutional neural networks (CNNs) for feature extraction. The architecture of our CNN is chosen from thousands of random possibilities and its filter weights are set at random and normalized to zero mean and unit norm. By training linear support vector machines (SVMs) on the resulting CNN features, we can achieve recognition rates of over 98% for digits and 96% for letters, something that neither SVMs operating on image pixels nor CNNs trained via back-propagation can achieve. The results are obtained in a dataset that has 182 samples per digit and 28 per letter, and suggest the use of random CNNs as a promising alternative approach to ALPR systems. 298303CAPES,Conselho Nacional de Desenvolvimento Cientifico e Tecnologico (CNPq),Fundacao Carlos Chagas Filho de Amparo a Pesquisa do Estado do Rio de Janeiro (FAPERJ)Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Du, S., Ibrahim, M., Shehata, M.S., Badawy, W.M., Automatic license plate recognition (ALPR): A state-of-the-art review (2013) IEEE Transactions on Circuits and Systems for Video Technologie, 23 (2), pp. 311-325Anagnostopoulos, C.-N., Anagnostopoulos, I., Psoroulas, I., Loumos, V., Kayafas, E., License plate recognition from still images and video sequences: A survey (2008) IEEE Transactions on Intelligent Transportation Systems, 9 (3), pp. 377-391Hegt, H., De La Haye, R., Khan, N., A high performance license plate recognition system (1998) IEEE International Conference on Systems, Man, and Cybernetics (SMC, 5, pp. 4357-4362Chang, S.-L., Chen, L.-S., Chung, Y.-C., Chen, S.-W., Automatic license plate recognition (2004) IEEE Transactions on Intelligent Transportation Systems, 5 (1), pp. 42-53Lee, E.R., Kim, P.K., Kim, H.J., Automatic recognition of a car license plate using color image processing (1994) IEEE International Conference Image Processing (ICIP, 2, pp. 301-305Matas, J., Zimmermann, K., Unconstrained licence plate and text localization and recognition (2005) IEEE Intelligent Transportation Systems (ITS, pp. 225-230Anagnostopoulos, C.-N., Anagnostopoulos, I., Loumos, V., Kayafas, E., A license plate-recognition algorithm for intelligent transportation system applications (2006) IEEE Transactions on Intelligent Transportation Systems, 7 (3), pp. 377-392Nukano, T., Fukumi, M., Khalid, M., Vehicle license plate character recognition by neural networks (2004) International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS, pp. 771-775Jiao, J., Ye, Q., Huang, Q., A configurable method for multistyle license plate recognition (2009) Pattern Recognition, 42 (3), pp. 358-369Thome, N., Robinault, L., A cognitive and video-based approach for multinational license plate recognition (2011) Machine Vision Applications, 22 (2), pp. 389-407Le Cun, Y., Bottou, L., Bengio, Y., Haffner, P., Gradient-based learning applied to document recognition (1998) Proceedings of the IEEE, 86 (11), pp. 2278-2324Cortes, C., Vapnik, V.N., Support-vector networks (1995) Machine Learning, 20 (3), pp. 273-297Wang, T., Wu, D.J., Coates, A., Ng, A.Y., End-to-end text recognition with convolutional neural networks (2012) IEEE International Conference on Pattern Recognition (ICPR, pp. 3304-3308Coates, A., Carpenter, B., Case, S.S.C., Suresh, B., Wu, D.J., Ng, A.Y., Text detection and character recognition in scene images with unsupervised feature learning (2011) IEEE International Conference on Document Analysis and Recognition (ICDAR, pp. 440-445Pinto, N., Cox, D.D., Beyond simple features: A large-scale feature search approach to unconstrained face recognition (2011) IEEE International Conference on Automatic Face and Gesture Recognition (FG, pp. 8-15Pinto, N., Stone, Z., Zickler, T., Cox, D.D., Scaling-up biologicallyinspired computer vision: A case study in unconstrained face recognition on facebook (2011) IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW, pp. 35-42Krizhevsky, A., Sutskever, I., Hinton, G.E., ImageNet Classification with Deep Convolutional Neural Networks (2012) Advances in Neural Information Processing SystemsGeisler, W.S., Albrecht, D.G., Cortical neurons: Isolation of contrast gain control (1992) Vision Research, 32 (8), pp. 1409-1410Mendes, P.R., Neves, J.M.R., Tavares, A.I., Menotti, D., (2011) Vehicle License Plate Location (VLPL) Algorithms, , https://github.com/pedrormjunior/vlplMendes, P.R., Neves, J.M.R., Tavares, A.I., Menotti, D., Towards an automatic vehicle access control system: License plate location (2011) IEEE International Conference on Systems, Man, and Cybernetics (SMC, pp. 2916-2921Nomura, S., Yamanaka, K., Shiose, T., Kawakami, H., Katai, O., Morphological preprocessing method to thresholding degraded (2009) Word Images Pattern Recognition Letters, 30 (8), pp. 729-744(2013), https://github.com/omitted/vlpc, Omitted Vehicle license plate charactersBergstra, J., Bengio, Y., (2012) Random Search for Hyper-parameter Optimization, 13, pp. 281-305Palm, R.B., (2012) Prediction As A Candidate for Learning Deep Hierarchical Models of Data, , https://github.com/rasmusbergpalm/DeepLearnToolbox, Master's thesis, Technical University of Denmark, DTU Informatics, Lyngby, DenmarkGuo, J.-M., Liu, Y.-F., License plate localization and character segmentation with feedback self-learning and hybrid binarization techniques (2008) IEEE Transactions on Vehicle Technology, 57 (3), pp. 1417-1424Comelli, P., Ferragina, P., Granieri, M.N., Stabile, F., Optical recognition of motor vehicle license plates (1995) IEEE Transactions on Vehicle Technology, 44 (4), pp. 790-799Coates, A., Ng, A.Y., Learning feature representations with Kmeans (2012) Neural Networks: Tricks of the Trade, pp. 561-580. , 2nd ed SpringerCoates, A., Ng, A., The importance of encoding versus training with sparse coding and vector quantization (2011) International Conference on Machine Learning (ICML, pp. 921-928Coates, A., Ng, A.Y., Lee, H., An analysis of single-layer networks in unsupervised feature learning (2011) Journal of Machine Learning Research-Proceedings Track, 15, pp. 215-223