DOI QR코드

DOI QR Code

컬러 영상 색채 강도 엔트로피를 이용한 앙상블 모델 기반의 지능형 나비 영상 인식

Ensemble Model Based Intelligent Butterfly Image Identification Using Color Intensity Entropy

  • Kim, Tae-Hee (Department of Information Security, Dongshin University) ;
  • Kang, Seung-Ho (Department of Information Security, Dongshin University)
  • 투고 : 2022.05.24
  • 심사 : 2022.06.18
  • 발행 : 2022.07.31

초록

영상을 이용한 기계학습 기반의 나비 종 인식 기술은 나비 종의 다양성 및 개체 수, 종의 서식 분포 등을 파악하는데 관련 분야 종사자의 많은 시간과 비용 감소의 효과를 가져온다. 나비 종 분류의 정확성과 시간 효율을 높이기 위해 기계학습 모델의 입력으로 사용되는 여러 가지 특징들이 연구되었다. 그중 엔트로피 개념을 이용한 가지 길이 유사성 엔트로피나 색채 강도 엔트로피 방법이 푸리에 변환이나 웨이블릿 등 다른 특징들에 비해 높은 정확성과 적은 학습 시간을 보여주었다. 본 논문은 나비의 컬러 영상에 대한 RGB 색채 강도 엔트로피를 이용한 특징 추출 알고리즘을 제안한다. 또한 제안한 특징 추출 방법과 대표적인 앙상블 모델들을 결합한 나비 인식 시스템을 개발하고 성능을 평가한다.

The butterfly species recognition technology based on machine learning using images has the effect of reducing a lot of time and cost of those involved in the related field to understand the diversity, number, and habitat distribution of butterfly species. In order to improve the accuracy and time efficiency of butterfly species classification, various features used as the inputs of machine learning models have been studied. Among them, branch length similarity(BLS) entropy or color intensity entropy methods using the concept of entropy showed higher accuracy and shorter learning time than other features such as Fourier transform or wavelet. This paper proposes a feature extraction algorithm using RGB color intensity entropy for butterfly color images. In addition, we develop butterfly recognition systems that combines the proposed feature extraction method with representative ensemble models and evaluate their performance.

키워드

과제정보

This work was supported by the National Research Foundation of Korea under Grant NRF-2020R1I1A3071599.

참고문헌

  1. IPBES, "The IPBES regional assessment report on biodiversity and ecosystem services for Europe and Central Asia," IPBES, Germany, 2018.
  2. G. W. Hopkins and R. P. Freckleton, "Declines in the numbers of amateur and professional taxonomists: implications for conservation," Animal Conservation, vol. 5, no. 3, pp. 245-249, Aug. 2002. https://doi.org/10.1017/S1367943002002299
  3. P. J. D. Weeks and K. J. Gaston, "Image analysis, neural networks, and the taxonomic impediment to biodiversity studies," Biodiversity&Conservation, vol. 6, pp. 263-274, Feb. 1997. https://doi.org/10.1023/A:1018348204573
  4. T. Xi, J. Wang, Y. Han, C. Lin, and L. Ji, "Multiple butterfly recognition based on deep residual learning and image analysis," Entomological Research, vol. 52, no. 1, pp. 44-53, Jan. 2021.
  5. D. Xin, Y. W. Chen, and J. Li, "Fine-Grained Butterfly Classification in Ecological Images Using Squeeze-And-Excitation and Spatial Attention Modules," Applied Sciences, vol. 10, no. 5, p. 1681, Mar. 2020. https://doi.org/10.3390/app10051681
  6. B. A. Bakri, Z. Ahmad, and S. M. Hatim, "Butterfly Family Detection and Identification Using Convolutional Neural Network for Lepidopterology," International Journal of Recent Technology and Engineering (IJRTE), vol. 8, no. 2S11, pp. 635-640, Sep. 2019. https://doi.org/10.35940/ijrte.b1645.078219
  7. P. J. D. Weeks, M. A. O'Neill, K. J. Gaston, and I. D. Gauld, "Automating insect identification: exploring the limitations of a prototype system," Journal of Applied Entomology, vol. 123, pp. 1-8, Jan. 1999. https://doi.org/10.1046/j.1439-0418.1999.00307.x
  8. S. H. Kang, S. H. Song, and S. H. Lee, "Identification of butterfly species using a single neural network system," Journal of Asia-Pacific Entomology, vol. 15, no. 3, pp. 431-435, Sep. 2012. https://doi.org/10.1016/j.aspen.2012.03.006
  9. S. H. Kang, J. H. Cho, and S. H. Lee, "Identification of butterfly based on their shapes when viewed from different angles using an artificial neural network," Journal of Asia-Pacific Entomology, vol. 17, no. 2, pp.143-149, Jun. 2014. https://doi.org/10.1016/j.aspen.2013.12.004
  10. S. H. Kang and T. H. Kim, "A Performance Improvement of Automatic Butterfly Identification Method Using Color Intensity Entropy," The Journal of the Korea Contents Association, vol. 17, no. 5, pp. 624-632, May. 2017. https://doi.org/10.5392/JKCA.2017.17.05.624
  11. T. K. Ho, "Random Decision Forests," in Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal: QC, Canada, pp. 278-282, 1995.
  12. G. Ke, Q. Meng, T. Finley, T. Wang, W. Ma, Q. Ye, and T. -Y. Liu, "LightGBM: A Highly Efficient Gradient Boosting Decision Tree," in Proceedings of 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach: CA, USA, pp. 3149-3157, 2017.
  13. LightGBM [Internet]. Available: https://lightgbm.readthedocs.io/en/latest/index.html.