A deep learning approach for human face sentiment classification

Dr Chetanpal Singh, Santoso Wibowo, Srimannarayana Grandhi

    Research output: Book chapter/Published conference paperConference paperpeer-review

    Abstract

    This paper presents the development of a deep learning approach for human face sentiment classification. Bidirectional Long-Short Term Memory (Bi-LSTM) and recurrent neural networks (RNNs) are used for object-based segmentation in images, and CNN-RNN model is adopted for non-linear mapping. To test the applicability of this proposed approach, we have trained several deep neural networks to recognize facial expressions in 10,000 images. Our experiments show that the proposed approach can achieve an accuracy of 99.12% in classifying human face sentiment. Moreover, results indicate that the model not only boosts the classification model but also lessen the overhead.
    Original languageEnglish
    Title of host publication2021 21st ACIS International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD-Winter)
    PublisherIEEE
    Number of pages5
    ISBN (Electronic)9781665418430
    ISBN (Print)9781665448260
    DOIs
    Publication statusE-pub ahead of print - 16 Apr 2021
    Event21st ACIS International Semi-Virtual Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD2021-Winter): SNPD 2021 Winter - University of Economics, Ho Chi Minh City, Viet Nam
    Duration: 28 Jan 202130 Jan 2021
    http://acisinternational.org/conferences/snpd-2021-winter/
    https://ieeexplore.ieee.org/xpl/conhome/9403428/proceeding (Conference proceedings)
    http://acisinternational.org/wp-content/uploads/2021/01/SNPD-2021-Winter-ProgramVirtual.pdf (Conference program)

    Conference

    Conference21st ACIS International Semi-Virtual Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD2021-Winter)
    Country/TerritoryViet Nam
    CityHo Chi Minh City
    Period28/01/2130/01/21
    OtherThe 21st ACIS International Semi-Virtual Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD2021-Winter) brings together researchers, scientists, engineers, industry practitioners, and students to discuss, encourage and exchange new ideas, research results, and experiences on all aspects of computer and information science. SNPD2021 Winter aims to facilitate cross-fertilizations among the key technology enabling areas and is soliciting papers in these areas.
    Internet address

    Fingerprint

    Dive into the research topics of 'A deep learning approach for human face sentiment classification'. Together they form a unique fingerprint.

    Cite this