Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Training Invariant Support Vector Machines
Machine Learning
HLT '01 Proceedings of the first international conference on Human language technology research
On the structure of hidden Markov models
Pattern Recognition Letters
Artificial Neural Networks for Document Analysis and Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Designing human friendly human interaction proofs (HIPs)
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Text Recognition of Low-resolution Document Images
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Fast Convolutional OCR with the Scanning N-Tuple Grid
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Using GPUs for Machine Learning Algorithms
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Ink Normalization and Beautification
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Incremental Nonlinear Dimensionality Reduction by Manifold Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Offline Grammar-Based Recognition of Handwritten Sentences
IEEE Transactions on Pattern Analysis and Machine Intelligence
A fast learning algorithm for deep belief nets
Neural Computation
A trainable feature extractor for handwritten digit recognition
Pattern Recognition
Deformation Models for Image Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence
Support vector regression from simulation data and few experimental samples
Information Sciences: an International Journal
Recognition of Patterns Without Feature Extraction by GRNN
ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part II
ECML '07 Proceedings of the 18th European conference on Machine Learning
Mimicking Go Experts with Convolutional Neural Networks
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Handwritten Digit Classification Based on Alpha-Beta Associative Model
CIARP '08 Proceedings of the 13th Iberoamerican congress on Pattern Recognition: Progress in Pattern Recognition, Image Analysis and Applications
A low-cost attack on a Microsoft captcha
Proceedings of the 15th ACM conference on Computer and communications security
Recent progress on the OCRopus OCR system
Proceedings of the International Workshop on Multilingual OCR
Application perspectives for the convolutional downward spiral architecture
ICS'08 Proceedings of the 12th WSEAS international conference on Systems
Boosting Shift-Invariant Features
Proceedings of the 31st DAGM Symposium on Pattern Recognition
Deformation-Aware Log-Linear Models
Proceedings of the 31st DAGM Symposium on Pattern Recognition
Learning Deep Architectures for AI
Foundations and Trends® in Machine Learning
Neocognitron and the Map Transformation Cascade
Neural Networks
Streamlining attacks on CAPTCHAs with a computer game
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
Slow feature discriminant analysis and its application on handwritten digit recognition
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Detection of articulation disorders using empirical mode decomposition and neural networks
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Robust feature extractions from geometric data using geometric algebra
SMC'09 Proceedings of the 2009 IEEE international conference on Systems, Man and Cybernetics
Hierarchical behavior knowledge space
MCS'07 Proceedings of the 7th international conference on Multiple classifier systems
Multi-dimensional recurrent neural networks
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
A two-tier Arabic offline handwriting recognition based on conditional joining rules
SACH'06 Proceedings of the 2006 conference on Arabic and Chinese handwriting recognition
Micro nucleus detection in human lymphocytes using convolutional neural network
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part I
Accelerating large-scale convolutional neural networks with parallel graphics multiprocessors
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Evaluation of pooling operations in convolutional architectures for object recognition
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Research frontier: deep machine learning--a new frontier in artificial intelligence research
IEEE Computational Intelligence Magazine
Deep, big, simple neural nets for handwritten digit recognition
Neural Computation
From engineering diagrams to engineering models: Visual recognition and applications
Computer-Aided Design
Genre classification and the invariance of MFCC features to key and tempo
MMM'11 Proceedings of the 17th international conference on Advances in multimedia modeling - Volume Part I
Nonlinear dimensionality reduction using a temporal coherence principle
Information Sciences: an International Journal
Proceedings of the 1st ACM International Conference on Multimedia Retrieval
CUDA-enabled implementation of a neural network algorithm for handwritten digit recognition
Optical Memory and Neural Networks
Stacked convolutional auto-encoders for hierarchical feature extraction
ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Image receptive fields neural networks for object recognition
ICANN'11 Proceedings of the 21st international conference on Artificial neural networks - Volume Part II
Technical Section: Neural network-based symbol recognition using a few labeled samples
Computers and Graphics
On fast deep nets for AGI vision
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
Efficiency optimization of trainable feature extractors for a consumer platform
ACIVS'11 Proceedings of the 13th international conference on Advanced concepts for intelligent vision systems
Proceedings of the 2011 Joint Workshop on Multilingual OCR and Analytics for Noisy Unstructured Text Data
Training of sparsely connected MLPs
DAGM'11 Proceedings of the 33rd international conference on Pattern recognition
Character recognition of license plate number using convolutional neural network
IVIC'11 Proceedings of the Second international conference on Visual informatics: sustaining research and innovations - Volume Part I
High performance classifiers combination for handwritten digit recognition
ICAPR'05 Proceedings of the Third international conference on Advances in Pattern Recognition - Volume Part I
A novel hybrid CNN-SVM classifier for recognizing handwritten digits
Pattern Recognition
Building segmentation based human-friendly human interaction proofs (HIPs)
HIP'05 Proceedings of the Second international conference on Human Interactive Proofs
A convolutional neural network tolerant of synaptic faults for low-power analog hardware
ANNPR'06 Proceedings of the Second international conference on Artificial Neural Networks in Pattern Recognition
Combining multiple classifiers for faster optical character recognition
DAS'06 Proceedings of the 7th international conference on Document Analysis Systems
Recognizing natural scene characters by convolutional neural network and bimodal image enhancement
CBDAR'11 Proceedings of the 4th international conference on Camera-Based Document Analysis and Recognition
Flexible, high performance convolutional neural networks for image classification
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Security and usability challenges of moving-object CAPTCHAs: decoding codewords in motion
Security'12 Proceedings of the 21st USENIX conference on Security symposium
Segmentation of CAPTCHAs based on complex networks
AICI'12 Proceedings of the 4th international conference on Artificial Intelligence and Computational Intelligence
Online handwriting recognition using multi convolution neural networks
SEAL'12 Proceedings of the 9th international conference on Simulated Evolution and Learning
Feature representation selection based on Classifier Projection Space and Oracle analysis
Expert Systems with Applications: An International Journal
Sparse activity and sparse connectivity in supervised learning
The Journal of Machine Learning Research
Unconstrained handwritten Devanagari character recognition using convolutional neural networks
Proceedings of the 4th International Workshop on Multilingual OCR
The robustness of hollow CAPTCHAs
Proceedings of the 2013 ACM SIGSAC conference on Computer & communications security
Hierarchical spatiotemporal feature extraction using recurrent online clustering
Pattern Recognition Letters
| Hi-index | 0.02 |
Neural networks are a powerful technology forclassification of visual inputs arising from documents.However, there is a confusing plethora of different neuralnetwork methods that are used in the literature and inindustry. This paper describes a set of concrete bestpractices that document analysis researchers can use toget good results with neural networks. The mostimportant practice is getting a training set as large aspossible: we expand the training set by adding a newform of distorted data. The next most important practiceis that convolutional neural networks are better suited forvisual document tasks than fully connected networks. Wepropose that a simple "do-it-yourself" implementation ofconvolution with a flexible architecture is suitable formany visual document problems. This simpleconvolutional neural network does not require complexmethods, such as momentum, weight decay, structure-dependentlearning rates, averaging layers, tangent prop,or even finely-tuning the architecture. The end result is avery simple yet general architecture which can yieldstate-of-the-art performance for document analysis. Weillustrate our claims on the MNIST set of English digitimages.