(45-5) 14 * << * >> * Russian * English * Content * All Issues

Classification of plumage images for identifying bird species
A.V. Belko 1, K.S. Dobratulin 1,2, A.V. Kuznetsov 1,3

1 Samara National Research University, 443086, Samara, Russia, Moskovskoye Shosse 34,
2 National University of Science and Technology "MISiS",
119049, Moscow, Russia, Leninsky Prospect 4,
3 IPSI RAS – Branch of the FSRC "Crystallography and Photonics" RAS,
443001, Samara, Russia, Molodogvardeyskaya 151

 PDF, 1438 kB

DOI: 10.18287/2412-6179-CO-836

Pages: 728-735.

Full text of article: Russian language.

Abstract:
This paper studies the possibility of using neural networks to classify plumage images in order to identify bird species. Taxonomic identification of bird plumage is widely used in aviation ornithology to analyze collisions with aircraft and develop methods for their prevention. This article provides a method for bird species identification based on a dataset made up in the previous research. A method for identifying birds from real-world images based on YoloV4 neural networks and DenseNet models is proposed. We present results of the feather classification task. We selected several deep learning architectures (DenseNet based) for a comparison of categorical crossentropy values on the provided dataset. The experimental evaluation has shown that the proposed method allows determining the bird species from a photo of an individual feather with an accuracy of up to 81.03 % for accurate classification, and with an accuracy of 97.09 % for the first five predictions.

Keywords:
machine vision, pattern recognition, neural networks, aviation ornithology.

Citation:
Belko AV, Dobratulin KS, Kuznetsov AV. Classification of plumage images for identifying bird species. Computer Optics 2021; 45(5): 749-755. DOI: 10.18287/2412-6179-CO-836.

References:
  1. Soldatini С, Georgalas V, Torricelli P, Albores-Barajas YV. An ecological approach to birdstrike risk analysis. Eur J Wildl Res 2010; 56(4): 623-632.
  2. Yang R, Wu XB, Yan P, Li XQ. Using DNA barcodes to identify a bird involved in a birdstrike at a Chinese airport. Mol Biol Rep 2010; 37(7): 3517-3523.
  3. Belko A, Dobratulin K, Kuznetsov A.  Feathers dataset for fine-grained visual categorization. Proc SPIE 2020; 11605: 1160518. DOI: 10.1117/12.2588386.
  4. Berg T, Liu J, Lee SW, Alexander ML, Jacobs DW, Belhumeur PN. Birdsnap: Large-scale fine-grained visual categorization of birds. IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2014: 2019-2026.
  5. Fu J, Zheng H, Mei T. Look closer to see better: Recurrent attention convolutional neural network for fine-grained image recognition. 2017 IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2017: 4476-4484.
  6. Araujo VM, Britto AS, Brun AL, Oliveira LES, Koerich AL. Fine-grained hierarchical classification of plant leaf images using fusion of deep models. IEEE 30th Int Conf on Tools with Artificial Intelligence (ICTAI) 2018: 4476-4484.
  7. Yang LJ, Luo P, Loy CC, Tang X. A large-scale car dataset for fine-grained categorization and verification. IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2015: 3973-3981.
  8. Hou SH, Feng YS, Wang ZL. VegFru: A domain-specific dataset for fine-grained visual categorization. IEEE Int Conf on Computer Vision (ICCV) 2017: 541-549.
  9. Dai XY, Southall B, Trinh N, Matei B. Efficient fine-grained classification and part localization using one compact network. IEEE Int Conf on Computer Vision Workshops (ICCVW 2017) 2017: 996-1004.
  10. Zhao B, Feng JS, Wu X, Yan SC. A survey on deep learning-based fine-grained object classification and semantic segmentation. Int J Autom Comput 2017; 14(2): 119-135.
  11. Priyadharshini P, Thilagavathi K. Hyperspectral image classification using MLL and Graph cut methods. Proc 2016 Online Int Conf on Green Engineering and Technologies (IC-GET) 2016: 1-6.
  12. Pandey M, Lazebnik S. Scene recognition and weakly supervised object localization with deformable part-based models. IEEE Int Conf on Computer Vision (ICCV) 2011: 1307-1314.
  13. Silla CN, Freitas AA. A survey of hierarchical classification across different application domains. Data Min Knowl Discov 2011; 22(1-2): 31-72.
  14. Krause J, Leibe B, Matas J. The unreasonable effectiveness of noisy data for fine-grained recognition. In Book: Leibe B, Matas J, Sebe N, Welling M, eds. Computer vision – ECCV 2016, Pt III. Springer International Publishing AG; 2016: 301-320.
  15. Mitchell R. Web scraping with Python: Collecting data from the Modern Web. Sebastopol: O'Reilly Media; 2015.
  16. Glumov NI, Myasnikov VV, Sergeev VV. Detection and recognition of objects in images [In Russian]. Samara: Samara University Publisher; 2010.
  17. Zhu QF, Zheng HF, Wang YB, Cao YG, Guo SX. Study on the evaluation method of sound phase cloud maps based on an improved YOLOv4 algorithm. Sensors 2020; 20(15): 4314.
  18. Redmon J, Divvala S, Girshick R, Farhadi A. You ONLY LOOK ONCE: Unified, real-time object detection. IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2016: 779-788.
  19. Sarkar D, Bali R, Ghosh T. Hands-on transfer learning with Python. Birmingham: Packt Publishing; 2018.
  20. Lin T-Y, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Dollar P, Zitnick CL. Microsoft COCO: common objects in context. In Book: Fleet D, Pajdla T, Schiele B, Tuytelaars T, eds. Computer vision – ECCV 2014, Part V. New York: Springer; 2014: 740-755.
  21. International code of zoological nomenclature. London: I Natural History Museum; 1999.
  22. Huang G, Liu Z, Van Der Maaten L. Densely connected convolutional networks. 30th IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2017: 2261-2269.
  23. Valev K, Schumann A, Sommer L, Beyerer J. A systematic evaluation of recent deep learning architectures for fine-grained vehicle classification. Proc SPIE 2018: 10649: 1064902.
  24. Everingham M, Van Gool L, Williams CKI, Winn J, Zisserman A. The PASCAL Visual Object Classes (VOC) Challenge. Int J Comput Vis 2010; 88: 303-338.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20