Learning to Read L’Infinito: Handwritten Text Recognition with Synthetic Training Data

Self-training for Handwritten Text Line Recognition

Off-line handwriting recognition deals with the task of automatically recognizing handwritten text from images, for example from scanned sheets of paper. Due to the tremendous variations of writing styles encountered between different individuals, this is a very challenging task. Traditionally, a recognition system is trained by using a large corpus of handwritten text that has to be transcribe...

Active Learning for Historic Handwritten Text Recognition

This thesis examines the use of active learning for the task of handwritten text recognition in historical documents. Active learning is a machine learning paradigm which enables the learner to select the data that is being trained on. In domains where procuring annotated data is expensive but there are large amounts of unlabelled data available, active learning can lead to better models with t...

Using a Synthetic Character Database for Training Deep Learning Models Applied to Offline Handwritten Recognition

We present our current work on building a deep learning architecture for the offline handwritten character recognition problem. The proposed system is based on training a deep Convolutional Neural Network (CNN) to recognize handwritten characters, using a new synthetic character database derived from UNIPEN dataset. The presented approach is inspired in some successfully-used neural architectur...

Modeling and training options for handwritten Arabic text recognition

Generating Synthetic Data for Text Recognition

Generating synthetic images is an art which emulates the natural process of image generation in a closest possible manner. In this work, we exploit such a framework for data generation in handwritten domain. We render synthetic data using open source fonts and incorporate data augmentation schemes. As part of this work, we release 9M synthetic handwritten word image corpus which could be useful...