no code implementations • 20 Feb 2021 • Shuvayan Ghosh Dastidar, Kalpita Dutta, Nibaran Das, Mahantapas Kundu, Mita Nasipuri
In this paper, we explore dark knowledge transfer approach using long short-term memory(LSTM) and CNN based assistant model and various deep neural networks as the teacher model, with a simple CNN based student network, in this domain of multi-script identification from natural scene text images.
1 code implementation • 27 Apr 2020 • Animesh Singh, Ritesh Sarkhel, Nibaran Das, Mahantapas Kundu, Mita Nasipuri
Finding local invariant patterns in handwrit-ten characters and/or digits for optical character recognition is a difficult task.
Optical Character Recognition Optical Character Recognition (OCR)
1 code implementation • 28 Dec 2019 • Animesh Singh, Sandip Saha, Ritesh Sarkhel, Mahantapas Kundu, Mita Nasipuri, Nibaran Das
Deep neural network-based architectures give promising results in various domains including pattern recognition.
no code implementations • 2 Feb 2018 • Saikat Roy, Nibaran Das, Mahantapas Kundu, Mita Nasipuri
In this work, a novel deep learning technique for the recognition of handwritten Bangla isolated compound character is presented and a new benchmark of recognition accuracy on the CMATERdb 3. 1. 3. 3 dataset is reported.
no code implementations • 22 Jan 2015 • Nibaran Das, Subhadip Basu, Punam Kumar Saha, Ram Sarkar, Mahantapas Kundu, Mita Nasipuri
In the current work we have developed a two-pass approach where the first pass classifier performs a coarse classification, based on some global features of the input pattern by restricting the possibility of classification decisions within a group of classes, smaller than the number of classes considered initially.
no code implementations • 22 Jan 2015 • Nibaran Das, Subhadip Basu, Ram Sarkar, Mahantapas Kundu, Mita Nasipuri, Dipak Kumar Basu
Appropriate feature set for representation of pattern classes is one of the most important aspects of handwritten character recognition.
no code implementations • 22 Jan 2015 • Nibaran Das, Sandip Pramanik, Subhadip Basu, Punam Kumar Saha, Ram Sarkar, Mahantapas Kundu
In this work, 25 features are extracted based on different bays attributes of the convex hull of the digit patterns.
no code implementations • 15 Oct 2014 • Subhadip Basu, Mahantapas Kundu, Mita Nasipuri, Dipak Kumar Basu
In this approach, an unknown pattern is classified by refining possible classification decisions obtained through coarse classification of the same.
no code implementations • 2 Oct 2014 • Nibaran Das, Sandip Pramanik, Subhadip Basu, Punam Kumar Saha, Ram Sarkar, Mahantapas Kundu, Mita Nasipuri
The current research aims to evaluate the performance of the convex hull based feature set, i. e. 125 features in all computed over different bays attributes of the convex hull of a pattern, for effective recognition of isolated handwritten Bangla basic characters and digits.
no code implementations • 5 Dec 2013 • Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu, Mita Nasipuri, Mahantapas Kundu
Finally the best fitted Hough peaks are extracted from the Hough transformed significant blocks for efficient face recognition.
no code implementations • 5 Dec 2013 • Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu, Mita Nasipuri, Mahantapas Kundu
In this paper, we present a novel Gabor wavelet based Kernel Entropy Component Analysis (KECA) method by integrating the Gabor wavelet transformation (GWT) of facial images with the KECA method for enhanced face recognition performance.
no code implementations • 5 Dec 2013 • Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu, Mita Nasipuri, Mahantapas Kundu
Firstly, the new morphological features i. e., features based on number of runs of pixels in four directions (N, NE, E, NW) are extracted, together with the GLCM based statistical features and LDP features that are less sensitive to the noise and non-monotonic illumination changes, are extracted from the significant blocks of the gradient image.
no code implementations • 5 Dec 2013 • Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu, Mita Nasipuri, Mahantapas Kundu
Unlike the traditional zigzag scanning method for feature extraction a continuous scanning method from top-left corner to right then top-down and right to left and so on until right-bottom of the image i. e. a spiral scanning technique has been proposed for better feature selection.
no code implementations • 5 Dec 2013 • Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu, Mita Nasipuri, Mahantapas Kundu
This paper exploits the feature extraction capabilities of the discrete cosine transform (DCT) together with an illumination normalization approach in the logarithm domain that increase its robustness to variations in facial geometry and illumination.
no code implementations • 5 Dec 2013 • Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu, Mita Nasipuri, Mahantapas Kundu
Secondly, the nonlinear discriminating features are analyzed and extracted from the selected low-energized blocks by the generalized Kernel Discriminative Common Vector (KDCV) method.
no code implementations • 17 Jun 2011 • Arindam Kar, Debotosh Bhattacharjee, Dipak Kumar Basu, Mita Nasipuri, Mahantapas Kundu
In this paper, we present a technique by which high-intensity feature vectors extracted from the Gabor wavelet transformation of frontal face images, is combined together with Independent Component Analysis (ICA) for enhanced face recognition.
no code implementations • 5 Jul 2010 • Mrinal Kanti Bhowmik, Debotosh Bhattacharjee, Mita Nasipuri, Dipak Kumar Basu, Mahantapas Kundu
This paper investigates the multiresolution level-1 and level-2 Quotient based Fusion of thermal and visual images.
no code implementations • 5 Jul 2010 • Mrinal Kanti Bhowmik, Debotosh Bhattacharjee, Mita Nasipuri, Dipak Kumar Basu, Mahantapas Kundu
In this paper we present a technique for fusion of optical and thermal face images based on image pixel fusion approach.
no code implementations • 5 Jul 2010 • Mrinal Kanti Bhowmik, Debotosh Bhattacharjee, Mita Nasipuri, Dipak Kumar Basu, Mahantapas Kundu
The main advantage of using wavelet transform is that it is well-suited to manage different image resolution and allows the image decomposition in different kinds of coefficients, while preserving the image information.
no code implementations • 5 Jul 2010 • Mrinal Kanti Bhowmik, Debotosh Bhattacharjee, Mita Nasipuri, Dipak Kumar Basu, Mahantapas Kundu
Here, we have used thermal face images as those are capable to minimize the affect of illumination changes and occlusion due to moustache, beards, adornments etc.
no code implementations • 5 Jul 2010 • Santanu Halder, Debotosh Bhattacharjee, Mita Nasipuri, Dipak Kumar Basu, Mahantapas Kundu
This paper aims at determining the characteristics of a face image by extracting its components.
no code implementations • 21 May 2010 • Santanu Halder, Debotosh Bhattacharjee, Mita Nasipuri, Dipak Kumar Basu, Mahantapas Kundu
This paper aims at generating a new face based on the human like description using a new concept.
no code implementations • 21 May 2010 • Mrinal Kanti Bhowmik, Debotosh Bhattacharjee, Mita Nasipuri, Dipak Kumar Basu, Mahantapas Kundu
This paper presents a novel approach to handle the challenges of face recognition.