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
Proceedings ArticleDOI
Gesture and Sign Language Recognition with Temporal Residual Networks
TL;DR: This work approaches Gesture and sign language recognition in a continuous video stream as a framewise classification problem using temporal convolutions and recent advances in the deep learning field like residual networks, batch normalization and exponential linear units.
Journal Article
Convolutional Neural Network for Face Recognition with Pose and Illumination Variation
TL;DR: A robust 4-layer Convolutional Neural Network architecture is proposed for the face recognition problem, with a solution that is capable of handling facial images that contain occlusions, poses, facial expressions and varying illumination.
Posted Content
Fine-Grained Representation Learning and Recognition by Exploiting Hierarchical Semantic Embedding
TL;DR: This work investigates simultaneously predicting categories of different levels in the hierarchy and integrating this structured correlation information into the deep neural network by developing a novel Hierarchical Semantic Embedding (HSE) framework.
Proceedings ArticleDOI
Shape driven kernel adaptation in Convolutional Neural Network for robust facial trait recognition
TL;DR: This paper explores how the shape information can be explicitly deployed into the popular Convolutional Neural Network architecture to disentangle such irrelevant non-rigid appearance variations, and proposes a kernel adaptation method to dynamically determine the convolutional kernels according to the spatial distribution of facial landmarks, which helps learning more robust features.
Posted Content
Learning Structure and Strength of CNN Filters for Small Sample Size Training
TL;DR: SSF-CNN is proposed which focuses on learning the "structure" and "strength" of filters and significantly reduces the number of parameters required for training while providing high accuracies on the test databases.