S
Swapan K. Parui
Researcher at Indian Statistical Institute
Publications - 126
Citations - 2709
Swapan K. Parui is an academic researcher from Indian Statistical Institute. The author has contributed to research in topics: Handwriting recognition & Artificial neural network. The author has an hindex of 26, co-authored 126 publications receiving 2405 citations. Previous affiliations of Swapan K. Parui include Indian Institute of Engineering Science and Technology, Shibpur.
Papers
More filters
Journal ArticleDOI
YASS: Yet another suffix stripper
Prasenjit Majumder,Mandar Mitra,Swapan K. Parui,Gobinda Kole,Pabitra Mitra,Kalyankumar Datta +5 more
TL;DR: A clustering-based approach to discover equivalence classes of root words and their morphological variants and provides consistent improvements in retrieval performance for French and Bengali, which are currently resource-poor.
Proceedings ArticleDOI
CNN based common approach to handwritten character recognition of multiple scripts
TL;DR: A convolutional neural network trained for a larger class recognition problem towards feature extraction of samples of several smaller class recognition problems of English, Devanagari, Bangla, Telugu and Oriya each of which is an official Indian script.
Proceedings ArticleDOI
Online handwritten Bangla character recognition using HMM
TL;DR: A novel scheme for recognition of online handwritten basic characters of Bangla, an Indian script used by more than 200 million people, is described here, using a database of 24,500 online handwritten isolated character samples written by 70 persons.
Journal ArticleDOI
SVM-based hierarchical architectures for handwritten Bangla character recognition
TL;DR: Three different two-stage hierarchical learning architectures (HLAs) are proposed using the three grouping schemes and the HLA scheme with overlapped groups outperforms the other two HLA schemes.
Journal ArticleDOI
A robust parallel thinning algorithm for binary images
Amitava Datta,Swapan K. Parui +1 more
TL;DR: A new algorithm in the same class of multi-pass iterative thinning algorithms is proposed and is shown, on the basis of experimental results, to be superior to the existing ones with respect to medial axis representation and robustness.