The Experts below are selected from a list of 222 Experts worldwide ranked by ideXlab platform

Tanushyam Chattopadhyay - One of the best experts on this subject based on the ideXlab platform.

  • ICDAR - A Weighted Finite-State Transducer (WFST)-Based Language Model for Online Indic Script Handwriting Recognition
    2011 International Conference on Document Analysis and Recognition, 2011
    Co-Authors: Suhan Chowdhury, Utpal Garain, Tanushyam Chattopadhyay
    Abstract:

    Though designing of classifies for Indic script handwriting recognition has been researched with enough attention, use of language model has so far received little exposure. This paper attempts to develop a weighted finite-state transducer (WFST) based language model for improving the current recognition accuracy. Both the recognition hypothesis (i.e. the segmentation lattice) and the lexicon are modeled as two WFSTs. Concatenation of these two FSTs accept a valid word(s) which is (are) present in the recognition lattice. A third FST called error FST is also introduced to retrieve certain words which were missing in the previous Concatenation Operation. The proposed model has been tested for online Bangla handwriting recognition though the underlying principle can equally be applied for recognition of offline or printed words. Experiment on a part of ISI-Bangla handwriting database shows that while the present classifiers (without using any language model) can recognize about 73% word, use of recognition and lexicon FSTs improve this result by about 9% giving an average word-level accuracy of 82%. Introduction of error FST further improves this accuracy to 93%. This remarkable improvement in word recognition accuracy by using FST-based language model would serve as a significant revelation for the research in handwriting recognition, in general and Indic script handwriting recognition, in particular.

  • A Weighted Finite-State Transducer (WFST)-Based Language Model for Online Indic Script Handwriting Recognition
    2011 International Conference on Document Analysis and Recognition, 2011
    Co-Authors: Suhan Chowdhury, Utpal Garain, Tanushyam Chattopadhyay
    Abstract:

    Though designing of classifies for Indic script handwriting recognition has been researched with enough attention, use of language model has so far received little exposure. This paper attempts to develop a weighted finite-state transducer (WFST) based language model for improving the current recognition accuracy. Both the recognition hypothesis (i.e. the segmentation lattice) and the lexicon are modeled as two WFSTs. Concatenation of these two FSTs accept a valid word(s) which is (are) present in the recognition lattice. A third FST called error FST is also introduced to retrieve certain words which were missing in the previous Concatenation Operation. The proposed model has been tested for online Bangla handwriting recognition though the underlying principle can equally be applied for recognition of offline or printed words. Experiment on a part of ISI-Bangla handwriting database shows that while the present classifiers (without using any language model) can recognize about 73% word, use of recognition and lexicon FSTs improve this result by about 9% giving an average word-level accuracy of 82%. Introduction of error FST further improves this accuracy to 93%. This remarkable improvement in word recognition accuracy by using FST-based language model would serve as a significant revelation for the research in handwriting recognition, in general and Indic script handwriting recognition, in particular.

Suhan Chowdhury - One of the best experts on this subject based on the ideXlab platform.

  • ICDAR - A Weighted Finite-State Transducer (WFST)-Based Language Model for Online Indic Script Handwriting Recognition
    2011 International Conference on Document Analysis and Recognition, 2011
    Co-Authors: Suhan Chowdhury, Utpal Garain, Tanushyam Chattopadhyay
    Abstract:

    Though designing of classifies for Indic script handwriting recognition has been researched with enough attention, use of language model has so far received little exposure. This paper attempts to develop a weighted finite-state transducer (WFST) based language model for improving the current recognition accuracy. Both the recognition hypothesis (i.e. the segmentation lattice) and the lexicon are modeled as two WFSTs. Concatenation of these two FSTs accept a valid word(s) which is (are) present in the recognition lattice. A third FST called error FST is also introduced to retrieve certain words which were missing in the previous Concatenation Operation. The proposed model has been tested for online Bangla handwriting recognition though the underlying principle can equally be applied for recognition of offline or printed words. Experiment on a part of ISI-Bangla handwriting database shows that while the present classifiers (without using any language model) can recognize about 73% word, use of recognition and lexicon FSTs improve this result by about 9% giving an average word-level accuracy of 82%. Introduction of error FST further improves this accuracy to 93%. This remarkable improvement in word recognition accuracy by using FST-based language model would serve as a significant revelation for the research in handwriting recognition, in general and Indic script handwriting recognition, in particular.

  • A Weighted Finite-State Transducer (WFST)-Based Language Model for Online Indic Script Handwriting Recognition
    2011 International Conference on Document Analysis and Recognition, 2011
    Co-Authors: Suhan Chowdhury, Utpal Garain, Tanushyam Chattopadhyay
    Abstract:

    Though designing of classifies for Indic script handwriting recognition has been researched with enough attention, use of language model has so far received little exposure. This paper attempts to develop a weighted finite-state transducer (WFST) based language model for improving the current recognition accuracy. Both the recognition hypothesis (i.e. the segmentation lattice) and the lexicon are modeled as two WFSTs. Concatenation of these two FSTs accept a valid word(s) which is (are) present in the recognition lattice. A third FST called error FST is also introduced to retrieve certain words which were missing in the previous Concatenation Operation. The proposed model has been tested for online Bangla handwriting recognition though the underlying principle can equally be applied for recognition of offline or printed words. Experiment on a part of ISI-Bangla handwriting database shows that while the present classifiers (without using any language model) can recognize about 73% word, use of recognition and lexicon FSTs improve this result by about 9% giving an average word-level accuracy of 82%. Introduction of error FST further improves this accuracy to 93%. This remarkable improvement in word recognition accuracy by using FST-based language model would serve as a significant revelation for the research in handwriting recognition, in general and Indic script handwriting recognition, in particular.

Utpal Garain - One of the best experts on this subject based on the ideXlab platform.

  • ICDAR - A Weighted Finite-State Transducer (WFST)-Based Language Model for Online Indic Script Handwriting Recognition
    2011 International Conference on Document Analysis and Recognition, 2011
    Co-Authors: Suhan Chowdhury, Utpal Garain, Tanushyam Chattopadhyay
    Abstract:

    Though designing of classifies for Indic script handwriting recognition has been researched with enough attention, use of language model has so far received little exposure. This paper attempts to develop a weighted finite-state transducer (WFST) based language model for improving the current recognition accuracy. Both the recognition hypothesis (i.e. the segmentation lattice) and the lexicon are modeled as two WFSTs. Concatenation of these two FSTs accept a valid word(s) which is (are) present in the recognition lattice. A third FST called error FST is also introduced to retrieve certain words which were missing in the previous Concatenation Operation. The proposed model has been tested for online Bangla handwriting recognition though the underlying principle can equally be applied for recognition of offline or printed words. Experiment on a part of ISI-Bangla handwriting database shows that while the present classifiers (without using any language model) can recognize about 73% word, use of recognition and lexicon FSTs improve this result by about 9% giving an average word-level accuracy of 82%. Introduction of error FST further improves this accuracy to 93%. This remarkable improvement in word recognition accuracy by using FST-based language model would serve as a significant revelation for the research in handwriting recognition, in general and Indic script handwriting recognition, in particular.

  • A Weighted Finite-State Transducer (WFST)-Based Language Model for Online Indic Script Handwriting Recognition
    2011 International Conference on Document Analysis and Recognition, 2011
    Co-Authors: Suhan Chowdhury, Utpal Garain, Tanushyam Chattopadhyay
    Abstract:

    Though designing of classifies for Indic script handwriting recognition has been researched with enough attention, use of language model has so far received little exposure. This paper attempts to develop a weighted finite-state transducer (WFST) based language model for improving the current recognition accuracy. Both the recognition hypothesis (i.e. the segmentation lattice) and the lexicon are modeled as two WFSTs. Concatenation of these two FSTs accept a valid word(s) which is (are) present in the recognition lattice. A third FST called error FST is also introduced to retrieve certain words which were missing in the previous Concatenation Operation. The proposed model has been tested for online Bangla handwriting recognition though the underlying principle can equally be applied for recognition of offline or printed words. Experiment on a part of ISI-Bangla handwriting database shows that while the present classifiers (without using any language model) can recognize about 73% word, use of recognition and lexicon FSTs improve this result by about 9% giving an average word-level accuracy of 82%. Introduction of error FST further improves this accuracy to 93%. This remarkable improvement in word recognition accuracy by using FST-based language model would serve as a significant revelation for the research in handwriting recognition, in general and Indic script handwriting recognition, in particular.

F. Michel Dekking - One of the best experts on this subject based on the ideXlab platform.

  • Morphisms, Symbolic Sequences, and Their Standard Forms
    2016
    Co-Authors: F. Michel Dekking
    Abstract:

    Morphisms are homomorphisms under the Concatenation Operation of the set of words over a finite alphabet. Changing the elements of the finite alphabet does not change the morphism in an essential way. We propose a method to select a unique representative from all these morphisms. This has applications to the classification of the shift dynamical systems generated by morphisms. In a similar way, we propose the selection of a representing sequence out of the class of symbolic sequences over an alphabet of fixed cardinality. Both methods are useful for the storing of symbolic sequences in databases, such as The On-Line Encyclopedia of Integer Sequences. We illustrate our proposals with the k-symbol Fibonacci sequences.

  • Pure morphic sequences and their standard forms.
    arXiv: Combinatorics, 2015
    Co-Authors: F. Michel Dekking
    Abstract:

    Pure morphic sequences are infinite fixed points of morphisms (under the Concatenation Operation) on finite sets. Changing the elements of the finite set does not essentially change the pure morphic sequence. We propose a way to select a unique representing member out of all these sequences. This has applications to the classification of the shift dynamical systems generated by pure morphic sequences, and to the storing of pure morphic sequences in databases, like the The On-Line Encyclopedia of Integer Sequences.

  • Morphisms, Symbolic sequences, and their Standard Forms
    arXiv: Combinatorics, 2015
    Co-Authors: F. Michel Dekking
    Abstract:

    Morphisms are homomorphisms under the Concatenation Operation of the set of words over a finite set. Changing the elements of the finite set does not essentially change the morphism. We propose a way to select a unique representing member out of all these morphisms. This has applications to the classification of the shift dynamical systems generated by morphisms. In a similar way, we propose the selection of a representing sequence out of the class of symbolic sequences over an alphabet of fixed cardinality. Both methods are useful for the storing of symbolic sequences in databases, like The On-Line Encyclopedia of Integer Sequences. We illustrate our proposals with the $k$-symbol Fibonacci sequences.

Ching-nung Yang - One of the best experts on this subject based on the ideXlab platform.

  • An Efficient Essential Secret Image Sharing Scheme Using Derivative Polynomial
    Symmetry, 2019
    Co-Authors: Zhen Wu, Dong Wang, Ching-nung Yang
    Abstract:

    As a popular technology in information security, secret image sharing is a method to guarantee the secret image’s security. Usually, the dealer would decompose the secret image into a series of shadows and then assign them to a number of participants, and only a quorum of participants could recover the secret image. Generally, it is assumed that every participant is equal. Actually, due to their position in many practical applications, some participants are given special privileges. Therefore, it is desirable to give an approach to generate shadows with different priorities shadows. In this paper, an efficient essential secret image sharing scheme using a derivative polynomial is proposed. Compared with existing related works, our proposed scheme can not only create the same-sized shadows with smaller size but also removes the Concatenation Operation in the sharing phase. Theoretical analysis and simulations confirm the security and effectiveness of the proposed scheme.

  • Essential secret image sharing scheme with the same size of shadows
    Digital Signal Processing, 2016
    Co-Authors: Peng Li, Ching-nung Yang, Zhili Zhou
    Abstract:

    Secret image sharing is a method to decompose a secret image into shadow images (shadows) so that only qualified subset of shadows can be used to reconstruct the secret image. Usually all shadows have the same importance. Recently, an essential SIS (ESIS) scheme with different importance of shadows was proposed. All shadows are divided into two group: essential shadows and non-essential shadows. In reconstruction, the involved shadows should contain at least a required number of shadows, including at least a required number of essential shadows. However, there are two problems in previous ESIS scheme: unequal size of shadows and Concatenation of sub-shadow images. These two problems may lead to security vulnerability and complicate the reconstruction. In this paper, we propose a novel ESIS scheme based on derivative polynomial and Birkhoff interpolation. A single shadow with the same-size is generated for each essential and non-essential participant. The experimental results demonstrate that our scheme can avoid above two problems effectively. An essential secret image sharing scheme is proposed based on derivative polynomial.The essential shadows are more important than non-essential shadows.All shadows have the same size.No Concatenation Operation is needed in generation of shadows.