Zobrazeno 1 - 10
of 181
pro vyhledávání: '"Kundu, Mahantapas"'
Multi-lingual script identification is a difficult task consisting of different language with complex backgrounds in scene text images. According to the current research scenario, deep neural networks are employed as teacher models to train a smaller
Externí odkaz:
http://arxiv.org/abs/2102.10335
Finding local invariant patterns in handwrit-ten characters and/or digits for optical character recognition is a difficult task. Variations in writing styles from one person to another make this task challenging. We have proposed a non-explicit featu
Externí odkaz:
http://arxiv.org/abs/2004.12769
Autor:
Singh, Animesh, Saha, Sandip, Sarkhel, Ritesh, Kundu, Mahantapas, Nasipuri, Mita, Das, Nibaran
Deep neural network-based architectures give promising results in various domains including pattern recognition. Finding the optimal combination of the hyper-parameters of such a large-sized architecture is tedious and requires a large number of labo
Externí odkaz:
http://arxiv.org/abs/1912.12405
Publikováno v:
Pattern Recognition Letters, Elsevier, Vol. 90, Pages 15-21, 2017
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. Greedy layer wise training of De
Externí odkaz:
http://arxiv.org/abs/1802.00671
Publikováno v:
Multimedia Tools & Applications; Sep2024, Vol. 83 Issue 32, p77945-77966, 22p
Publikováno v:
Network Modeling & Analysis in Health Informatics & Bioinformatics; 8/7/2024, Vol. 13 Issue 1, p1-13, 13p
Autor:
Dutta, Kalpita, Bal, Malyaban, Basak, Arpita, Ghosh, Swarnendu, Das, Nibaran, Kundu, Mahantapas, Nasipuri, Mita
Publikováno v:
In Pattern Recognition Letters July 2020 135:64-71
Autor:
Das, Nibaran, Basu, Subhadip, Sarkar, Ram, Kundu, Mahantapas, Nasipuri, Mita, Basu, Dipak kumar
Appropriate feature set for representation of pattern classes is one of the most important aspects of handwritten character recognition. The effectiveness of features depends on the discriminating power of the features chosen to represent patterns of
Externí odkaz:
http://arxiv.org/abs/1501.05497
Autor:
Das, Nibaran, Basu, Subhadip, Saha, Punam Kumar, Sarkar, Ram, Kundu, Mahantapas, Nasipuri, Mita
Soft computing approaches are mainly designed to address the real world ill-defined, imprecisely formulated problems, combining different kind of novel models of computation, such as neural networks, genetic algorithms (GAs. Handwritten digit recogni
Externí odkaz:
http://arxiv.org/abs/1501.05495
Autor:
Das, Nibaran, Pramanik, Sandip, Basu, Subhadip, Saha, Punam Kumar, Sarkar, Ram, Kundu, Mahantapas
In this paper, convex hull based features are used for recognition of isolated Roman numerals using a Multi Layer Perceptron (MLP) based classifier. Experiments of convex hull based features for handwritten character recognition are few in numbers. C
Externí odkaz:
http://arxiv.org/abs/1501.05494