What is it about?
Different systems for handwriting recognition use different features to represent the input text. Even after decades of research, no favorable decision on a best-practice exists and many features are carefully hand-crafted. To facilitate the design phase for on-line handwriting systems, in this paper, we propose an unsupervised feature generation approach.
Featured Image
Why is it important?
This is an important work towards automation of feature design.
Perspectives
We have compared the approach with a state-of-the-art feature extraction method and demonstrated the superiority of proposed unsupervised feature extraction. In future, our method can be applied for recognition of other scripts.
Dr. Nilanjana Bhattacharya
Read the Original
This page is a summary of: Design of Unsupervised Feature Extraction System for On-line Bangla Handwriting Recognition, April 2014, Institute of Electrical & Electronics Engineers (IEEE),
DOI: 10.1109/das.2014.55.
You can read the full text:
Contributors
The following have contributed to this page
