DeepAI AI Chat
Log In Sign Up

ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation

03/23/2020
by   Sharon Fogel, et al.
Amazon
0

Optical character recognition (OCR) systems performance have improved significantly in the deep learning era. This is especially true for handwritten text recognition (HTR), where each author has a unique style, unlike printed text, where the variation is smaller by design. That said, deep learning based HTR is limited, as in every other task, by the number of training examples. Gathering data is a challenging and costly task, and even more so, the labeling task that follows, of which we focus here. One possible approach to reduce the burden of data annotation is semi-supervised learning. Semi supervised methods use, in addition to labeled data, some unlabeled samples to improve performance, compared to fully supervised ones. Consequently, such methods may adapt to unseen images during test time. We present ScrabbleGAN, a semi-supervised approach to synthesize handwritten text images that are versatile both in style and lexicon. ScrabbleGAN relies on a novel generative model which can generate images of words with an arbitrary length. We show how to operate our approach in a semi-supervised manner, enjoying the aforementioned benefits such as performance boost over state of the art supervised HTR. Furthermore, our generator can manipulate the resulting text style. This allows us to change, for instance, whether the text is cursive, or how thin is the pen stroke.

READ FULL TEXT
05/04/2021

Poisoning the Unlabeled Dataset of Semi-Supervised Learning

Semi-supervised machine learning models learn from a (small) set of labe...
03/29/2022

Self-Contrastive Learning based Semi-Supervised Radio Modulation Classification

This paper presents a semi-supervised learning framework that is new in ...
08/21/2016

Inverting Variational Autoencoders for Improved Generative Accuracy

Recent advances in semi-supervised learning with deep generative models ...
02/12/2022

A multi-task semi-supervised framework for Text2Graph Graph2Text

The Artificial Intelligence industry regularly develops applications tha...
05/20/2022

Swapping Semantic Contents for Mixing Images

Deep architecture have proven capable of solving many tasks provided a s...
11/04/2021

Lexically Aware Semi-Supervised Learning for OCR Post-Correction

Much of the existing linguistic data in many languages of the world is l...