Hierarchical K-Nearest Neighbor with GPUs and a High Performance Cluster: application to Handwritten Character Recognition

Hubert Cecotti

    Research output: Contribution to journalArticle

    4 Citations (Scopus)

    Abstract

    The accelerating progress and availability of low cost computers, high speed networks, and software for high performance distributed computing allow us to reconsider computationally expensive techniques in image processing and pattern recognition. We propose a two-level hierarchical k-nearest neighbor classifier where the first level uses graphics processor units (GPUs) and the second level uses a high performance cluster (HPC). The system is evaluated on the problem of character recognition with nine databases (Arabic digits, Indian digits (Bangla, Devnagari, and Oriya), Bangla characters, Indonesian characters, Arabic characters, Farsi characters and digits). Contrary to many approaches that tune the model for different scripts, the proposed image classification method is unchanged throughout the evaluation on the nine databases. We show that a hierarchical combination of decisions based on two distances, using GPUs and a HPC provides state-of-the-art performances on several scripts, and provides a better accuracy than more complex systems.
    LanguageEnglish
    Pages1-24
    Number of pages24
    JournalInternational Journal of Pattern Recognition and Artificial Intelligence
    Volume31
    Issue number2
    DOIs
    Publication statusPublished - 1 Sep 2016

    Fingerprint

    Character recognition
    HIgh speed networks
    Image classification
    Distributed computer systems
    Pattern recognition
    Large scale systems
    Image processing
    Classifiers
    Availability
    Costs

    Keywords

    • image processing
    • character recognition
    • classification
    • image matching

    Cite this

    @article{1600ae760b664481a8b8d8e1ec051f6e,
    title = "Hierarchical K-Nearest Neighbor with GPUs and a High Performance Cluster: application to Handwritten Character Recognition",
    abstract = "The accelerating progress and availability of low cost computers, high speed networks, and software for high performance distributed computing allow us to reconsider computationally expensive techniques in image processing and pattern recognition. We propose a two-level hierarchical k-nearest neighbor classifier where the first level uses graphics processor units (GPUs) and the second level uses a high performance cluster (HPC). The system is evaluated on the problem of character recognition with nine databases (Arabic digits, Indian digits (Bangla, Devnagari, and Oriya), Bangla characters, Indonesian characters, Arabic characters, Farsi characters and digits). Contrary to many approaches that tune the model for different scripts, the proposed image classification method is unchanged throughout the evaluation on the nine databases. We show that a hierarchical combination of decisions based on two distances, using GPUs and a HPC provides state-of-the-art performances on several scripts, and provides a better accuracy than more complex systems.",
    keywords = "image processing, character recognition, classification, image matching",
    author = "Hubert Cecotti",
    year = "2016",
    month = "9",
    day = "1",
    doi = "10.1142/S0218001417500057",
    language = "English",
    volume = "31",
    pages = "1--24",
    journal = "International Journal of Pattern Recognition and Artificial Intelligence",
    issn = "0218-0014",
    number = "2",

    }

    TY - JOUR

    T1 - Hierarchical K-Nearest Neighbor with GPUs and a High Performance Cluster: application to Handwritten Character Recognition

    AU - Cecotti, Hubert

    PY - 2016/9/1

    Y1 - 2016/9/1

    N2 - The accelerating progress and availability of low cost computers, high speed networks, and software for high performance distributed computing allow us to reconsider computationally expensive techniques in image processing and pattern recognition. We propose a two-level hierarchical k-nearest neighbor classifier where the first level uses graphics processor units (GPUs) and the second level uses a high performance cluster (HPC). The system is evaluated on the problem of character recognition with nine databases (Arabic digits, Indian digits (Bangla, Devnagari, and Oriya), Bangla characters, Indonesian characters, Arabic characters, Farsi characters and digits). Contrary to many approaches that tune the model for different scripts, the proposed image classification method is unchanged throughout the evaluation on the nine databases. We show that a hierarchical combination of decisions based on two distances, using GPUs and a HPC provides state-of-the-art performances on several scripts, and provides a better accuracy than more complex systems.

    AB - The accelerating progress and availability of low cost computers, high speed networks, and software for high performance distributed computing allow us to reconsider computationally expensive techniques in image processing and pattern recognition. We propose a two-level hierarchical k-nearest neighbor classifier where the first level uses graphics processor units (GPUs) and the second level uses a high performance cluster (HPC). The system is evaluated on the problem of character recognition with nine databases (Arabic digits, Indian digits (Bangla, Devnagari, and Oriya), Bangla characters, Indonesian characters, Arabic characters, Farsi characters and digits). Contrary to many approaches that tune the model for different scripts, the proposed image classification method is unchanged throughout the evaluation on the nine databases. We show that a hierarchical combination of decisions based on two distances, using GPUs and a HPC provides state-of-the-art performances on several scripts, and provides a better accuracy than more complex systems.

    KW - image processing

    KW - character recognition

    KW - classification

    KW - image matching

    U2 - 10.1142/S0218001417500057

    DO - 10.1142/S0218001417500057

    M3 - Article

    VL - 31

    SP - 1

    EP - 24

    JO - International Journal of Pattern Recognition and Artificial Intelligence

    T2 - International Journal of Pattern Recognition and Artificial Intelligence

    JF - International Journal of Pattern Recognition and Artificial Intelligence

    SN - 0218-0014

    IS - 2

    ER -