Education & Career
Research & Publication
Professional Activity
Teaching & Supervision
Awards / Honors
Photo Gallery

Research Areas

Prof. Utpal Garain at present is exploring Deep Learning methods for Language Engineering, Image and Video Processing. The current research topics of Prof. Garain are listed below:

1.  Natural Language Processing (NLP)
2.  Information Retrieval (IR)
3.  Document Image Analysis (DIA)
4.  Computational Forensic (CF)
5.  Other Pattern Recognition (PR) Tasks:

1. Natural Language Processing (NLP) : Under computational linguistics for Indic languages, two issues are being researched: (i) anaphora resolution and (ii) lemmatization. Rule-based, MaxEnt, CRF and RNN-based approaches are being explored. Stanford POS tagger and MaltParser (dependency parser) have been retrained for Bengali language. A new initiative has been taken in the field of BioNLP. A novel probabilistic framework is being tried for event extraction for cancer genetics. In another context, artificial intelligence (AI) and NLP tools are nicely integrated to solve a text-to-diagram conversion problem. In this research, machine is involved to draw the diagram described in a piece of text (e.g. geometric/physics problems). This research has been extended for the Blind and a system for drawing geometry shapes using Braille has been developed.

2. Information Retrieval (IR): This work concerns with retrieval of OCR'd text. Unlike English OCRs, Indic OCRs are not very matured in producing high quality output and therefore, managing good information retrieval (IR) efficiency is a challenge while dealing with low quality OCR'd data. A probabilistic method has been developed to model the OCR errors to help the IR engines. The framework has been tested on a large dataset of Bengali and Hindi (Devanagari) OCR'd text. Because of this research a new initiative called RISOT (retrieval of Indic script OCR'd text) has been started under FIRE (Forum for Information Retrieval Evaluation) from 2011. IR from OCR'd text is now exploring cross language information retrieval (CLIR) issues where the queries are given in English and documents are in Bengali OCR'd text. A statistical transliteration module has been developed for transliterating out-of-vocabulary words. In another initiative, retrieval of imaged documents is also being explored with an emphasis on retrieval of document images from compressed domain.

3. Document Image Analysis (DIA): Research on Indic Script OCR is still continued. A finite-state transducer (FST) based post-processing module has been developed for handwriting recognition. A novel method for automatic algorithm selection has been proposed for document image binarization. Recognition of handwritten mathematical expressions is being investigated. The CROHME (competition on recognition of handwritten mathematical expressions) initiative is still on and the third CROHME is organized along with ICDAR 2013 (Int. Conf. on Document Analysis and Recognition). CROHME dataset is now endorsed by Technical Committee 11 (TC-11) of IAPR (Int. Assoc. for Pattern Recognition). Morphological Component Analysis (MCA) and Super Resolution (SR) techniques are used for robust recognition of historical documents and Video Text.

Computational Forensics(CF):This research is aimed at developing techniques for quick and easy authentication of security paper documents. Image processing and pattern recognition principles form the basis of this authentication technique. The goal is two-fold: (i) to check security features in a document in question in order to establish its authenticity, and at the same time (ii) analysis of security features to grade them according to their vulnerability against counterfeiting effort in order to help the designers for preparing of such security documents in future. Some research has been done for authenticating Indian banknotes. The role of fluorescent pulp for detecting fake banknotes has also been investigated. A method for determination of ink age in old documents has been developed. Handwriting analysis is used for manuscript dating and writer identification and verification.

5. Other PR Tasks: Several others PR tasks like synthetic sample generation, artificial immune system (AIS) for PR tasks, compressed domain document processing, etc. are being studied.