Book ChapterDOI
GradientBased Learning Applied to Document Recognition
Simon Haykin,Bart Kosko +1 more
- pp 306-351
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.Abstract:
Multilayer Neural Networks trained with the backpropagation algorithm constitute the best example of a successful Gradient-Based Learning technique. Given an appropriate network architecture, Gradient-Based Learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional Neural Networks, that are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation, recognition, and language modeling. A new learning paradigm, called Graph Transformer Networks (GTN), allows such multi-module systems to be trained globally using Gradient-Based methods so as to minimize an overall performance measure. Two systems for on-line handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of Graph Transformer Networks. A Graph Transformer Network for reading bank check is also described. It uses Convolutional Neural Network character recognizers combined with global training techniques to provides record accuracy on business and personal checks. It is deployed commercially and reads several million checks per day.read more
Citations
More filters
Posted Content
Graph-based Isometry Invariant Representation Learning
Renata Khasanova,Pascal Frossard +1 more
TL;DR: A novel Transformation Invariant Graph-based Network (TIGraNet), which learns graph-based features that are inherently invariant to isometric transformations such as rotation and translation of input images.
Posted Content
Style Augmentation: Data Augmentation via Style Randomization
TL;DR: In this paper, a new form of data augmentation based on random style transfer is introduced for improving the robustness of convolutional neural networks (CNNs) over both classification and regression based tasks.
Detecting Human Actions in Surveillance Videos.
Ming Yang,Shuiwang Ji,Wei Xu,Jinjun Wang,Fengjun Lv,Kai Yu,Yihong Gong,Mert Dikmen,Dennis Lin,Thomas S. Huang +9 more
TL;DR: This notebook paper summarizes Team NEC-UIUC’s approaches for TRECVid 2009 Evaluation of Surveillance Event Detection by combining 3D convolutional neural networks (CNN) and SVM classifiers based on bag-ofwords local features to detect the presence of events of inte rests.
Journal ArticleDOI
Continual learning for recurrent neural networks: An empirical evaluation.
TL;DR: In this article, the authors organize the literature on continuous learning for sequential data processing by providing a categorization of the contributions and a review of the benchmarks, and propose two new benchmarks for CL with sequential data based on existing datasets, whose characteristics resemble real world applications.
Posted Content
Kornia: an Open Source Differentiable Computer Vision Library for PyTorch
TL;DR: Kornia as mentioned in this paper is an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems, such as image transformations, camera calibration, epipolar geometry, and low level image processing techniques.