Proceedings of the 4th International Conference on Vocational Education and Technology, IConVET 2021, 27 November 2021, Singaraja, Bali, Indonesia

Research Article

Benchmarking a New Dataset of Traditional Balinese Carving Ornaments for Image Classification Task

Download481 downloads
  • @INPROCEEDINGS{10.4108/eai.27-11-2021.2315534,
        author={Made Windu Antara  Kesiman and I Gede Mahendra  Darmawiguna and I Gede Rusdy Mahayana  Putra and Ni Luh Putu  Kurniawati},
        title={Benchmarking a New Dataset of Traditional Balinese Carving Ornaments for Image Classification Task},
        proceedings={Proceedings of the 4th International Conference on Vocational Education and Technology, IConVET 2021, 27 November 2021, Singaraja, Bali, Indonesia},
        publisher={EAI},
        proceedings_a={ICONVET},
        year={2022},
        month={2},
        keywords={benchmark dataset image classification balinese carving ornament},
        doi={10.4108/eai.27-11-2021.2315534}
    }
    
  • Made Windu Antara Kesiman
    I Gede Mahendra Darmawiguna
    I Gede Rusdy Mahayana Putra
    Ni Luh Putu Kurniawati
    Year: 2022
    Benchmarking a New Dataset of Traditional Balinese Carving Ornaments for Image Classification Task
    ICONVET
    EAI
    DOI: 10.4108/eai.27-11-2021.2315534
Made Windu Antara Kesiman1,*, I Gede Mahendra Darmawiguna1, I Gede Rusdy Mahayana Putra1, Ni Luh Putu Kurniawati1
  • 1: Universitas Pendidikan Ganesha
*Contact email: antara.kesiman@undiksha.ac.id

Abstract

In the framework of the development of an automatic Balinese carving ornament recognition application, a valid image dataset is needed. This paper describes the improved new dataset of traditional Balinese carving ornaments and presents the benchmarking results in an image classification task. The improvement of the new dataset involves the increased number of image samples and involves the validation and addition of the number of ornament classes. Some frequently used feature extraction methods, for example, Gabor Filter, Zoning, Histogram of Gradient, Neighborhood Pixels Weights, and Kirsch edge, were tested to benchmark the image classification task for this new dataset. The benchmark results showed that this new dataset has a fairly high technical challenge for feature extraction methods in the pattern recognition field. The new proposed dataset will support further research steps in building a classification and recognition system for Balinese carving ornaments.