International Conference on Frontiers in Handwriting Recognition 

About: International Conference on Frontiers in Handwriting Recognition is an academic conference. The conference publishes majorly in the area(s): Handwriting recognition & Intelligent character recognition. Over the lifetime, 991 publications have been published by the conference receiving 19366 citations.

High Performance Convolutional Neural Networks for Document Processing

Abstract: Convolutional neural networks (CNNs) are well known for producing state-of-the-art recognizers for document processing [1]. However, they can be difficult to implement and are usually slower than traditional multi-layer perceptrons (MLPs). We present three novel approaches to speeding up CNNs: a) unrolling convolution, b) using BLAS (basic linear algebra subroutines), and c) using GPUs (graphic processing units). Unrolled convolution converts the processing in each convolutional layer (both forward-propagation and back-propagation) into a matrix-matrix product. The matrix-matrix product representation of CNNs makes their implementation as easy as MLPs. BLAS is used to efficiently compute matrix products on the CPU. We also present a pixel shader based GPU implementation of CNNs. Results on character recognition problems indicate that unrolled convolution with BLAS produces a dramatic 2.4X−3.0X speedup. The GPU implementation is even faster and produces a 3.1X−4.1X speedup.

Dropout Improves Recurrent Neural Networks for Handwriting Recognition

Abstract: Recurrent neural networks (RNNs) with Long Short-Term memory cells currently hold the best known results in unconstrained handwriting recognition. We show that their performance can be greatly improved using dropout - a recently proposed regularization method for deep architectures. While previous works showed that dropout gave superior performance in the context of convolutional networks, it had never been applied to RNNs. In our approach, dropout is carefully used in the network so that it does not affect the recurrent connections, hence the power of RNNs in modeling sequences is preserved. Extensive experiments on a broad range of handwritten databases confirm the effectiveness of dropout on deep architectures even when the network mainly consists of recurrent and shared connections.

Online handwriting recognition with support vector machines - a kernel approach

Abstract: In this paper we describe a novel classification approach for online handwriting recognition. The technique combines dynamic time warping (DTW) and support vector machines (SVMs) by establishing a new SVM kernel. We call this kernel Gaussian DTW (GDTW) kernel. This kernel approach has a main advantage over common HMM techniques. It does not assume a model for the generative class conditional densities. Instead, it directly addresses the problem of discrimination by creating class boundaries and thus is less sensitive to modeling assumptions. By incorporating DTW in the kernel function, general classification problems with variable-sized sequential data can be handled. In this respect the proposed method can be straightforwardly applied to all classification problems, where DTW gives a reasonable distance measure, e.g., speech recognition or genome processing. We show experiments with this kernel approach on the UNIPEN handwriting data, achieving results comparable to an HMM-based technique.

“One Against One” or “One Against All”: Which One is Better for Handwriting Recognition with SVMs?

Abstract: The “one against one” and the “one against all” are the two most popular strategies for multi-class SVM; however, according to the literature review, it seems impossible to conclude which one is better for handwriting recognition. Thus, we compared these two classical strategies on two different handwritten character recognition problems. Several post-processing methods for estimating posterior probability were also evaluated and the results were compared with the ones obtained using MLP. Finally, the “one against all” strategy appears significantly more accurate for digit recognition, while the difference between the two strategies is much less obvious with upper-case letters. Besides, the “one against one” strategy is substantially faster to train and seems preferable for problems with a very large number of classes. To conclude, SVMs allow significantly better estimation of probabilities than MLP, which is promising from the point of view of their incorporation into handwriting recognition systems.

H-DIBCO 2010 - Handwritten Document Image Binarization Competition

Abstract: H-DIBCO 2010 is the International Document Image Binarization Contest which is dedicated to handwritten document images organized in conjunction with ICFHR 2010 conference. The general objective of the contest is to identify current advances in handwritten document image binarization using meaningful evaluation performance measures. This paper reports on the contest details including the evaluation measures used as well as the performance of the 17 submitted methods along with a short description of each method.