Subhasis Mandal

Indian Institute of Technology Guwahati | IIT Guwahati · Department of Electronics and Electrical Engineering (EEE)

The segmentation of unconstrained handwriting is an important issue for both recognition and synthesis systems. In this direction, hidden Markov model (HMM) has been the most popular method for segmentation of continuous handwriting. It has been employed in both implicit and explicit segmentation-based recognition systems. The main advantage of HMM...

The task of online handwriting recognition (HR) becomes often challenging due to the presence of confusing characters which are separable by a small region. To address this problem, we propose a “discriminative region (DR) selection” technique which highlights the discriminative region that distinguishes one character from another similar character...

An online handwriting recognition (HR) system is usually developed considering point-based features that describe different geometric attributes of handwriting. Often, due to the wide variations in writing styles, the use of point-based features results in high intra-class variability in feature space. To address this problem, we propose a set of f...

This paper describes an experimental study to compare the various steps involved in Hidden Markov Model (HMM) and Hidden Semi Markov Model (HSMM) approaches for recognition and synthesis, respectively. It presents different aspects of the two systems, bringing up the commonalities and differences among them. Further, to demonstrate the usefulness o...

A frequency count based two stage classification approach is proposed by combining generative and discriminative modeling principles for online handwritten character recognition. The first stage classifier based on Hidden Markov Model (HMM) returns top-K ranking characters out of the total N classes. In the second stage, pairwise classifiers for K(...

This work describes the development of online handwritten isolated Bengali numerals using Deep Autoencoder (DA) based on Multilayer perceptron (MLP) [1]. Autoencoders capture the class specific information and the deep version uses many hidden layers and a final classification layer to accomplish this. DA based on MLP uses the MLP training approach...

Hidden Markov Models (HMMs) and Support Vector Machine (SVM) based classifiers are commonly used in the field of handwriting recognition. In this paper we investigate a technique of recognizing Assamese handwritten characters using HMMs and SVM stroke classifiers in conjunction to each other. The two classifiers are separately trained on same strok...

Hidden Markov Models (HMM) are used in handwritten strokes recognition task. The two design parameters of HMM are the number of states and number of mixtures in each state. There are two approaches for finding the number of states, namely, equal number of states and variable number of states. Since the shape of strokes will be different, variable n...

Hidden Markov Models (HMM) are the widely used modeling techniques for online handwriting recognition. This paper describes both stroke based and character based methods for Assamese handwritten character recognition using HMM classifier. In stroke based method, unique strokes that are used to write the characters are grouped and then HMM modeling...