Database of Wild Animal Images and a Trial of Recognition by Deep Learning

DOI
  • MIYASHITA Kodai
    College of Science and Engineering, Ritsumeikan University
  • HATSUDA Shinya
    Graduate School of Science and Engineering, Ritsumeikan University
  • MENG Lin
    College of Science and Engineering, Ritsumeikan University Graduate School of Science and Engineering, Ritsumeikan University
  • IZUMI Tomonori
    College of Science and Engineering, Ritsumeikan University Graduate School of Science and Engineering, Ritsumeikan University Institute of Disaster Mitigation for Urban Cultural Heritage, Ritsumeikan University

Bibliographic Information

Other Title
  • 野生動物自動認識のためのデータベース構築と深層学習の試行

Abstract

Wild animals such as deer and boars cause serious troubles on the agriculture and the amount of damage in FY2017 is reported to be 16.4 billion yen nationwide. Aiming at the development of countermeasures against damage by wild animals based on the image recognition technology, we construct a dataset of animal images for machine learning and perform a trial of recognition by deep learning. By clipping and labeling the images taken by field cameras, a dataset of totally 14,226 animal images is constructed and disclosed for public use. Classifiers by deep learning are constructed and trained with images of deer, boars, and monkeys from the dataset together with images of raccoons and raccoon dogs taken in a zoo and with images of CIFAR-10. Experiments demonstrate that the classifiers achieve about 80% of recognition accuracy.

Journal

Keywords

Details 詳細情報について

  • CRID
    1390848250133965440
  • NII Article ID
    130007884340
  • DOI
    10.11371/wiieej.18.03.0_66
  • Text Lang
    ja
  • Data Source
    • JaLC
    • CiNii Articles
  • Abstract License Flag
    Disallowed

Report a problem

Back to top