Thermography-based material classification using machine learning

Tamas Aujeszky, Georgios Korres, Mohamad Eid

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Infrared thermography has been widely used today for nondestructive evaluation and testing of materials and other qualitative approaches. However, the field of thermography is much less developed. Most of the existing research uses a relatively simple model, while more realistic models are currently in development. One interesting scenario for thermography is determining the material composition of objects based on their thermal response to excitation, which could lead to applications such as multimodal human-computer interaction, teleoperation and non-contact haptic mapping. This paper presents a system that is capable of classification between a range of different materials in real time, using laser excitation step thermography and a set of machine learning classifiers. Experimental results demonstrate a consistently high accuracy in determining the label of the material, even when the dataset is composed of multiple different sessions of data acquisition.

    Original languageEnglish (US)
    Title of host publicationHAVE 2017 - IEEE International Symposium on Haptic, Audio-Visual Environments and Games, Proceedings
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages1-6
    Number of pages6
    Volume2017-December
    ISBN (Electronic)9781538609798
    DOIs
    StatePublished - Dec 26 2017
    Event15th IEEE International Symposium on Haptic, Audio-Visual Environments and Games, HAVE 2017 - Abu Dhabi, United Arab Emirates
    Duration: Oct 22 2017Oct 23 2017

    Other

    Other15th IEEE International Symposium on Haptic, Audio-Visual Environments and Games, HAVE 2017
    CountryUnited Arab Emirates
    CityAbu Dhabi
    Period10/22/1710/23/17

    Fingerprint

    Learning systems
    Laser excitation
    Human computer interaction
    Remote control
    Labels
    Data acquisition
    Classifiers
    Testing
    Chemical analysis

    Keywords

    • haptic mapping
    • Laser thermography
    • machine learning
    • material characterization

    ASJC Scopus subject areas

    • Human-Computer Interaction
    • Media Technology

    Cite this

    Aujeszky, T., Korres, G., & Eid, M. (2017). Thermography-based material classification using machine learning. In HAVE 2017 - IEEE International Symposium on Haptic, Audio-Visual Environments and Games, Proceedings (Vol. 2017-December, pp. 1-6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HAVE.2017.8240344

    Thermography-based material classification using machine learning. / Aujeszky, Tamas; Korres, Georgios; Eid, Mohamad.

    HAVE 2017 - IEEE International Symposium on Haptic, Audio-Visual Environments and Games, Proceedings. Vol. 2017-December Institute of Electrical and Electronics Engineers Inc., 2017. p. 1-6.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Aujeszky, T, Korres, G & Eid, M 2017, Thermography-based material classification using machine learning. in HAVE 2017 - IEEE International Symposium on Haptic, Audio-Visual Environments and Games, Proceedings. vol. 2017-December, Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 15th IEEE International Symposium on Haptic, Audio-Visual Environments and Games, HAVE 2017, Abu Dhabi, United Arab Emirates, 10/22/17. https://doi.org/10.1109/HAVE.2017.8240344
    Aujeszky T, Korres G, Eid M. Thermography-based material classification using machine learning. In HAVE 2017 - IEEE International Symposium on Haptic, Audio-Visual Environments and Games, Proceedings. Vol. 2017-December. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1-6 https://doi.org/10.1109/HAVE.2017.8240344
    Aujeszky, Tamas ; Korres, Georgios ; Eid, Mohamad. / Thermography-based material classification using machine learning. HAVE 2017 - IEEE International Symposium on Haptic, Audio-Visual Environments and Games, Proceedings. Vol. 2017-December Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1-6
    @inproceedings{ee9b785b372c4e4fb89bb1911618c9d0,
    title = "Thermography-based material classification using machine learning",
    abstract = "Infrared thermography has been widely used today for nondestructive evaluation and testing of materials and other qualitative approaches. However, the field of thermography is much less developed. Most of the existing research uses a relatively simple model, while more realistic models are currently in development. One interesting scenario for thermography is determining the material composition of objects based on their thermal response to excitation, which could lead to applications such as multimodal human-computer interaction, teleoperation and non-contact haptic mapping. This paper presents a system that is capable of classification between a range of different materials in real time, using laser excitation step thermography and a set of machine learning classifiers. Experimental results demonstrate a consistently high accuracy in determining the label of the material, even when the dataset is composed of multiple different sessions of data acquisition.",
    keywords = "haptic mapping, Laser thermography, machine learning, material characterization",
    author = "Tamas Aujeszky and Georgios Korres and Mohamad Eid",
    year = "2017",
    month = "12",
    day = "26",
    doi = "10.1109/HAVE.2017.8240344",
    language = "English (US)",
    volume = "2017-December",
    pages = "1--6",
    booktitle = "HAVE 2017 - IEEE International Symposium on Haptic, Audio-Visual Environments and Games, Proceedings",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Thermography-based material classification using machine learning

    AU - Aujeszky, Tamas

    AU - Korres, Georgios

    AU - Eid, Mohamad

    PY - 2017/12/26

    Y1 - 2017/12/26

    N2 - Infrared thermography has been widely used today for nondestructive evaluation and testing of materials and other qualitative approaches. However, the field of thermography is much less developed. Most of the existing research uses a relatively simple model, while more realistic models are currently in development. One interesting scenario for thermography is determining the material composition of objects based on their thermal response to excitation, which could lead to applications such as multimodal human-computer interaction, teleoperation and non-contact haptic mapping. This paper presents a system that is capable of classification between a range of different materials in real time, using laser excitation step thermography and a set of machine learning classifiers. Experimental results demonstrate a consistently high accuracy in determining the label of the material, even when the dataset is composed of multiple different sessions of data acquisition.

    AB - Infrared thermography has been widely used today for nondestructive evaluation and testing of materials and other qualitative approaches. However, the field of thermography is much less developed. Most of the existing research uses a relatively simple model, while more realistic models are currently in development. One interesting scenario for thermography is determining the material composition of objects based on their thermal response to excitation, which could lead to applications such as multimodal human-computer interaction, teleoperation and non-contact haptic mapping. This paper presents a system that is capable of classification between a range of different materials in real time, using laser excitation step thermography and a set of machine learning classifiers. Experimental results demonstrate a consistently high accuracy in determining the label of the material, even when the dataset is composed of multiple different sessions of data acquisition.

    KW - haptic mapping

    KW - Laser thermography

    KW - machine learning

    KW - material characterization

    UR - http://www.scopus.com/inward/record.url?scp=85048745295&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85048745295&partnerID=8YFLogxK

    U2 - 10.1109/HAVE.2017.8240344

    DO - 10.1109/HAVE.2017.8240344

    M3 - Conference contribution

    VL - 2017-December

    SP - 1

    EP - 6

    BT - HAVE 2017 - IEEE International Symposium on Haptic, Audio-Visual Environments and Games, Proceedings

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -