Multi-column deep neural network for traffic sign classification
Neural NetworksPublished 14 February 2012
Dan Cireşan, Ueli Meier, Jonathan Masci, Jürgen Schmidhuber
Citations1,039
SJR quartileQ1
SJR score1.49
SNIP2.02
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This work uses a fast, fully parameterizable GPU implementation of a Deep Neural Network (DNN) that does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way.
Abstract
We describe the approach that won the final phase of the German traffic sign recognition benchmark. Our method is the only one that achieved a better-than-human recognition rate of 99.46%. We use a fast, fully parameterizable GPU implementation of a Deep Neural Network (DNN) that does not require careful design of pre-wired feature extractors, which are rather learned in a supervised way. Combining various DNNs trained on differently preprocessed data into a Multi-Column DNN (MCDNN) further boosts recognition performance, making the system insensitive also to variations in contrast and illumination.
Keywords
Computer ScienceEngineering
Proceedings of the IEEEGradient-based learning applied to document recognition
58,219 Citations1998Yann LeCun, Léon Bottou +2 more
This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.
Journal of Electronic ImagingPattern Recognition and Machine Learning
21,976 Citations2007Christopher Bishop
Probability Distributions, linear models for Regression, Linear Models for Classification, Neural Networks, Graphical Models, Mixture Models and EM, Sampling Methods, Continuous Latent Variables, Sequential Data are studied.
The Journal of PhysiologyReceptive fields of single neurones in the cat's striate cortex
4,691 Citations1959David H. Hubel, T. N. Wiesel
The present investigation, made in acute preparations, includes a study of receptive fields of cells in the cat's striate cortex, which resembled retinal ganglion-cell receptive fields, but the shape and arrangement of excitatory and inhibitory areas differed strikingly from the concentric pattern found in retinalganglion cells.
Vision ResearchSparse coding with an overcomplete basis set: A strategy employed by V1?
3,720 Citations1997Bruno A. Olshausen, David J. Field
These deviations from linearity provide a potential explanation for the weak forms of non-linearity observed in the response properties of cortical simple cells, and they further make predictions about the expected interactions among units in response to naturalistic stimuli.
Nature NeuroscienceHierarchical models of object recognition in cortex
3,404 Citations1999Maximilian Riesenhuber, Tomaso Poggio
A new hierarchical model consistent with physiological data from inferotemporal cortex that accounts for this complex visual task and makes testable predictions is described.
Best practices for convolutional neural networks applied to visual document analysis
2,815 Citations2005P. Simard, Don Steinkraus +1 more
A set of concrete bestpractices that document analysis researchers can use to get good results with neural networks, including a simple "do-it-yourself" implementation of convolution with a flexible architecture suitable for many visual document problems.
Lecture notes in computer scienceEvaluation of Pooling Operations in Convolutional Architectures for Object Recognition
1,518 Citations2010Dominik Scherer, Andreas Müller +1 more
The aim is to gain insight into different functions by directly comparing them on a fixed architecture for several common object recognition tasks, and empirical results show that a maximum pooling operation significantly outperforms subsampling operations.
Gradient Flow in Recurrent Nets: The Difficulty of Learning LongTerm Dependencies
1,261 Citations2009
This chapter contains sections titled: Introduction Exponential Error Decay Dilemma: Avoiding Aradient Decay Prevents Long-Term Latching Remedies and Conclusion.
International Joint Conference on Artificial IntelligenceFlexible, high performance convolutional neural networks for image classification
1,203 Citations2011Dan Cireşan, Ueli Meier +3 more
The German Traffic Sign Recognition Benchmark: A multi-class classification competition
1,074 Citations2011Johannes Stallkamp, Marc Schlipsing +2 more
The “German Traffic Sign Recognition Benchmark” is a multi-category classification competition held at IJCNN 2011, and a comprehensive, lifelike dataset of more than 50,000 traffic sign images has been collected.
Neural ComputationDeep, Big, Simple Neural Nets for Handwritten Digit Recognition
1,064 Citations2010Dan Claudiu Cireşan, Ueli Meier +2 more
Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35 error rate on the MNIST handwritten digits benchmark.
Object Recognition with Features Inspired by Visual Cortex
828 Citations2005T. Serre, Lior Wolf +1 more
The performance of the approach constitutes a suggestive plausibility proof for a class of feedforward models of object recognition in cortex and exhibits excellent recognition performance and outperforms several state-of-the-art systems on a variety of image datasets including many different object categories.
Traffic sign recognition with multi-scale Convolutional Networks
747 Citations2011Pierre Sermanet, Yann LeCun
This work applies Convolutional Networks (ConvNets) to the task of traffic sign classification as part of the GTSRB competition, and yields the 2nd-best accuracy above the human performance.
Convolutional Neural Network Committees for Handwritten Character Classification
536 Citations2011Dan Claudiu Cireşan, Ueli Meier +2 more
This work applies the same architecture to NIST SD 19, a more challenging dataset including lower and upper case letters, and obtains the best results published so far for both NIST digits and NIST letters.
International Journal of Computer VisionObject Class Recognition and Localization Using Sparse Features with Limited Receptive Fields
377 Citations2008Jim Mutch, David Lowe
A committee of neural networks for traffic sign classification
375 Citations2011Dan Cireşan, Ueli Meier +2 more
This work describes the approach that won the preliminary phase of the German traffic sign recognition benchmark with a better-than-human recognition rate, and obtains an even better recognition rate by further training the nets.
A Field Guide to Dynamical Recurrent Networks
339 Citations2009John F. Kolen, Stefan C. Kremer
This book presents the range of dynamical recurrent network (DRN) architectures that will be used in the book and transforms the text from a collection of papers into a coherent book.
The combining classifier: to train or not to train?
328 Citations2003Robert P. W. Duin
An intuitive discussion on the use of trained combiners is presented, relating the question of the choice of the combining classifier to a similar choice in the area of dissimilarity based pattern recognition.
ICDAR 2013 Chinese Handwriting Recognition Competition
318 Citations2013Fei Yin, Qiufeng Wang +2 more
This paper describes the Chinese handwriting recognition competition held at the 12th International Conference on Document Analysis and Recognition (ICDAR 2013), and reports the best results (correct rates) for classification on extracted features, offline character recognition, and online/offline handwritten text recognition.
Network Computation in Neural SystemsIndependent component analysis applied to feature extraction from colour and stereo images
234 Citations2000Patrik O. Hoyer, Aapo Hyvärinen
The similarities between these results and the observed properties of simple cells in the primary visual cortex are further evidence for the hypothesis that visual cortical neurons perform some type of redundancy reduction, which was one of the original motivations for ICA in the first place.
Lecture notes in computer scienceHierarchical Neural Networks for Image Interpretation
222 Citations2003Sven Behnke
The results show clear trends in the direction of improvement in the level of supervised learning in relation to the recognition of meter values and in the application of Matrix Codes.
IEEE Transactions on Pattern Analysis and Machine IntelligenceOptimal linear combination of neural networks for improving classification performance
205 Citations2000N. Ueda
Experimental results show that the proposed method can construct a better combined classifier that outperforms the best single classifier in terms of overall classification errors for test data.
IEEE Transactions on Neural NetworksImproving model accuracy using optimal linear combinations of trained neural networks
178 Citations1995S. Hashem, B.W. Schmeiser
The authors formulate the MSE-OLC problem for trained NN's and derive two closed-form expressions for the optimal combination-weights and examples of significant improvement in model accuracy are included.
Network Computation in Neural SystemsIndependent component analysis applied to feature extraction from colour and stereo images
115 Citations2000Patrik O. Hoyer, Aapo Hyvärinen
ICDAR 2011 Chinese Handwriting Recognition Competition
83 Citations2011Cheng‐Lin Liu, Fei Yin +2 more
In the Chinese handwriting recognition competition organized with the ICDAR 2011, four tasks were evaluated: offline and online isolated character recognition, offline and offline handwritten text recognition, and to enable the training of recognition systems, the large databases CASIA-HWDB/OLHW DB were announced.
Better Digit Recognition with a Committee of Simple Neural Nets
69 Citations2011Ueli Meier, Dan Claudiu Cireşan +2 more
A new method to train the members of a committee of one-hidden-layer neural nets is presented, which obtains a recognition error rate on the MNIST digit recognition benchmark set of 0.39%, on par with state-of-the-art recognition rates of more complicated systems.
Neural ComputationSemilinear Predictability Minimization Produces Well-Known Feature Detectors
48 Citations1996Jürgen Schmidhuber, Martin Eldracher +1 more
This paper applies semilinear PM to static real world images and finds that without a teacher and without any significant preprocessing, the system automatically learns to generate distributed representations based on well-known feature detectors, thus extracting simple features related to those considered useful for image preprocessing and compression.