Sciweavers

NIPS
1993
14 years 25 days ago
Postal Address Block Location Using a Convolutional Locator Network
This paper describes the use of a convolutional neural network to perform address block location on machine-printed mail pieces. Locating the address block is a dicult object rec...
Ralph Wolf, John C. Platt
NIPS
1997
14 years 26 days ago
A Neural Network Based Head Tracking System
We have constructed an inexpensive, video-based, motorized tracking system that learns to track a head. It uses real time graphical user inputs or an auxiliary infrared detector a...
Daniel D. Lee, H. Sebastian Seung
ESANN
2006
14 years 28 days ago
Visual object classification by sparse convolutional neural networks
Abstract. A convolutional network architecture termed sparse convolutional neural network (SCNN) is proposed and tested on a real-world classification task (car classification). In...
Alexander Gepperth
ICPR
2010
IEEE
14 years 3 months ago
Learning Sparse Face Features : Application to Face Verification
We present a low resolution face recognition technique based on a Convolutional Neural Network approach. The network is trained to reconstruct a reference per subject image. In cl...
Pierre Buyssens, Marinette Revenu
ICDAR
2003
IEEE
14 years 4 months ago
Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis
Neural networks are a powerful technology for classification of visual inputs arising from documents. However, there is a confusing plethora of different neural network methods th...
Patrice Simard, David Steinkraus, John C. Platt
ICDAR
2005
IEEE
14 years 5 months ago
Text Recognition of Low-resolution Document Images
Cheap and versatile cameras make it possible to easily and quickly capture a wide variety of documents. However, low resolution cameras present a challenge to OCR because it is vi...
Charles E. Jacobs, Patrice Y. Simard, Paul A. Viol...
CVPR
1997
IEEE
15 years 1 months ago
Global Training of Document Processing Systems Using Graph Transformer Networks
We propose a new machine learning paradigm called Graph Transformer Networks that extends the applicability of gradient-based learning algorithms to systems composed of modules th...
Léon Bottou, Yoshua Bengio, Yann LeCun