Sciweavers

Share
ICDAR
2009
IEEE

Evaluating Retraining Rules for Semi-Supervised Learning in Neural Network Based Cursive Word Recognition

11 years 6 months ago
Evaluating Retraining Rules for Semi-Supervised Learning in Neural Network Based Cursive Word Recognition
Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, including the generation of the ground truth, is tedious and costly. One way of reducing the high cost of labeled training data acquisition is to exploit unlabeled data, which can be gathered easily. Making use of both labeled and unlabeled data is known as semi-supervised learning. One of the most general versions of semi-supervised learning is selftraining, where a recognizer iteratively retrains itself on its own output on new, unlabeled data. In this paper we propose to apply semi-supervised learning, and in particular self-training, to the problem of cursive, handwritten word recognition. The special focus of the paper is on retraining rules that define what data are actually being used in the retraining phase. In a series of experiments it is shown that the performance of a neural network based recognizer...
Volkmar Frinken, Horst Bunke
Added 21 May 2010
Updated 21 May 2010
Type Conference
Year 2009
Where ICDAR
Authors Volkmar Frinken, Horst Bunke
Comments (0)
books