Convolutional Neural Network Committees for Handwritten Character Classification

@article{Ciresan2011ConvolutionalNN,
  title={Convolutional Neural Network Committees for Handwritten Character Classification},
  author={D. Ciresan and U. Meier and L. Gambardella and J. Schmidhuber},
  journal={2011 International Conference on Document Analysis and Recognition},
  year={2011},
  pages={1135-1139}
}
In 2010, after many years of stagnation, the MNIST handwriting recognition benchmark record dropped from 0.40% error rate to 0.35%. Here we report 0.27% for a committee of seven deep CNNs trained on graphics cards, narrowing the gap to human performance. We also apply the same architecture to NIST SD 19, a more challenging dataset including lower and upper case letters. A committee of seven CNNs obtains the best results published so far for both NIST digits and NIST letters. The robustness of… Expand
Beyond human recognition: A CNN-based framework for handwritten character recognition
TLDR
In the experiments, the proposed CNN-based handwritten character recognition framework performed even better than human on handwritten digit (MNIST) and Chinese character (CASIA) recognition. Expand
Recognition of Handwritten Characters in Chinese Legal Amounts by Stacked Autoencoders
TLDR
A novel way by combining multiple Neural Networks in doing the work is proposed which proves to be able to improve the recognition rate significantly and outperforms traditional methods using hand-crafted features and convolutional neural network committees, narrowing the gap to human performance. Expand
Handwritten Tifinagh Characters Recognition Using Deep Convolutional Neural Networks
TLDR
A new offline recognition system based on deep convolutional neural networks (CNNs) is designed that uses CNNs to extract features from raw pixels which makes the proposed technique more flexible than the other conventional ones that require a set of additional preprocessing steps to extract the desired invariants features. Expand
Unconstrained handwritten Devanagari character recognition using convolutional neural networks
TLDR
A novel offline strategy for recognition of online handwritten Devanagari characters entered in an unconstrained manner, based on CNN, that allows writers to enter characters in any number or order of strokes and is also robust to certain amount of overwriting. Expand
Multi-Column Deep Neural Networks for offline handwritten Chinese character classification
  • D. Ciresan, U. Meier
  • Computer Science
  • 2015 International Joint Conference on Neural Networks (IJCNN)
  • 2015
Multi-Column Deep Neural Networks achieve state of the art recognition rates on Chinese characters from the ICDAR 2011 and 2013 offline handwriting competitions, approaching human accuracy. ThisExpand
Combining additive input noise annealing and pattern transformations for improved handwritten character recognition
TLDR
Using a modest sized ANN, the proposed combination of input data transformations enables the achievement of a test error as low as 0.43%, which is up to standard compared to other more complex neural architectures like Convolutional or Deep Neural Networks. Expand
AN OPTIMIZED CONVOLUTIONAL NEURAL NETWORK FOR HANDWRITTEN DIGITAL RECOGNITION CLASSIFICATION
A Convolutional Neural Network (CNN) is a deep learning algorithm that designed to demonstrate a high capability of object recognition in image data. This paper has developed a prediction model forExpand
Using a Synthetic Character Database for Training Deep Learning Models Applied to Offline Handwritten Recognition
TLDR
The proposed system is based on training a deep Convolutional Neural Network to recognize handwritten characters, using a new synthetic character database derived from UNIPEN dataset, inspired in some successfully-used neural architectures for image classification. Expand
Handwritten Digit Recognition with Pattern Transformations and Neural Network Averaging
TLDR
A relatively modest sized Neural Network trained with standard Back Propagation and combined with a set of input pattern transformations is proposed, giving an encouraging error rate of 0.34% measured on the MNIST dataset. Expand
Handwritten Digit Recognition using Double Convolution Neural Network
Because of the wide range of applications and ambiguity in learning approaches, character identification from handwritten images has gotten more interest in the pattern recognition research field.Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 35 REFERENCES
Flexible, High Performance Convolutional Neural Networks for Image Classification
We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in aExpand
Handwritten Digit Recognition with a Committee of Deep Neural Nets on GPUs
TLDR
Another substantial improvement is reported: 0.31% obtained using a committee of MLPs using simple but deep MLPs, outperforming all the previous more complex methods. Expand
High-Performance Neural Networks for Visual Object Classification
We present a fast, fully parameterizable GPU implementation of Convolutional Neural Network variants. Our feature extractors are neither carefully designed nor pre-wired, but rather learned in aExpand
A committee of neural networks for traffic sign classification
We describe the approach that won the preliminary phase of the German traffic sign recognition benchmark with a better-than-human recognition rate of 98.98%.We obtain an even better recognition rateExpand
ICDAR 2011 Chinese Handwriting Recognition Competition
  • C. Liu, Fei Yin, Qiu-Feng Wang, Da-Han Wang
  • Computer Science
  • 2011 International Conference on Document Analysis and Recognition
  • 2011
In the Chinese handwriting recognition competition organized with the ICDAR 2011, four tasks were evaluated: offline and online isolated character recognition, offline and online handwritten textExpand
Unconstrained handwritten character recognition using metaclasses of characters
TLDR
Four multilayer perceptron classifiers were built and used into three different classification strategies: combination of two 26-class classifiers; 26-metaclass classifier; 52- class classifier. Expand
Deep, Big, Simple Neural Nets for Handwritten Digit Recognition
Good old online backpropagation for plain multilayer perceptrons yields a very low 0.35 error rate on the MNIST handwritten digits benchmark. All we need to achieve this best result so far are manyExpand
Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition
TLDR
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. Expand
GradientBased Learning Applied to Document Recognition
TLDR
Various methods applied to handwritten character recognition are reviewed and compared and Convolutional Neural Networks, that are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Expand
Gradient-based learning applied to document recognition
TLDR
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. Expand
...
1
2
3
4
...