Abstract:
Handwritten Text Recognition (HTR) of Hindi Documents is a challenging research problem of interest which could enable digitization of millions of official documents. Due...Show MoreMetadata
Abstract:
Handwritten Text Recognition (HTR) of Hindi Documents is a challenging research problem of interest which could enable digitization of millions of official documents. Due to challenges in character segmentation, Segmentation-free Word Recognition is the preferred approach. Lack of a large, diverse Hindi Handwritten Word dataset for pre-training deep learning architectures is a pressing issue. In this paper, we propose a novel way of generating diverse Handwritten Hindi Word images using only Handwritten Hindi Characters and further analyze its effectiveness in enabling Few Instance Learning of Handwritten Hindi Documents.
Date of Conference: 19-24 July 2020
Date Added to IEEE Xplore: 28 August 2020
ISBN Information:
ISSN Information:
Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Word Generation ,
- Deep Learning ,
- Word Recognition ,
- Deep Learning Architectures ,
- Optical Character Recognition ,
- Training Set ,
- Connective ,
- Large Datasets ,
- Solid Line ,
- Training Images ,
- Final Performance ,
- Gaussian Blur ,
- Synthetic Images ,
- Realistic Images ,
- Individual Words ,
- Combination Of Characters ,
- Real Words ,
- Synthetic Methodology ,
- Recognition Network ,
- Synthetic Generation ,
- Character Images ,
- Segmentation Pipeline ,
- Word Segmentation ,
- WordNet ,
- Word Meaning ,
- Lack Of Datasets
Contents Keywords assist with retrieval of results and provide a means to discovering other relevant content. Learn more.
- IEEE Keywords
- Index Terms
- Word Generation ,
- Deep Learning ,
- Word Recognition ,
- Deep Learning Architectures ,
- Optical Character Recognition ,
- Training Set ,
- Connective ,
- Large Datasets ,
- Solid Line ,
- Training Images ,
- Final Performance ,
- Gaussian Blur ,
- Synthetic Images ,
- Realistic Images ,
- Individual Words ,
- Combination Of Characters ,
- Real Words ,
- Synthetic Methodology ,
- Recognition Network ,
- Synthetic Generation ,
- Character Images ,
- Segmentation Pipeline ,
- Word Segmentation ,
- WordNet ,
- Word Meaning ,
- Lack Of Datasets
