Feathers and Pixels: A Comparative Analysis of CNN Models for Efficient Bird Species Identification

Pretty Liju  George; R.  Nedunchezhian

Authors

Pretty Liju George Department of Computer Science & Engineering, Coimbatore Institute of Technology, Tamil Nadu, India
R. Nedunchezhian Department of Computer Science & Engineering, Coimbatore Institute of Technology, Tamil Nadu, India

Keywords:

Species Identification, Audio Analytics, Video Analytics, CNN Models, Feature Extraction.

Abstract

Bird species identification is crucial for biodiversity conservation, ecosystem monitoring, and avian research. It helps assess population trends, monitor ecosystem health, and track environmental changes. Birds are key indicators of habitat quality and climate impacts. Accurate identification supports studies on migration, breeding, and foraging, aiding conservation efforts and identifying threatened species. Deep learning technology, specifically Convolutional Neural Networks (CNNs), is used for bird species identification by training models on large labeled datasets of bird images. The CNN architecture is designed to extract features from images, and the model is trained to associate these features with bird species labels. The paper navigates through the nuances of model performance, facilitating a comprehensive understanding of their strengths and limitations. Metrics such as accuracy, recall, and precision are scrutinized, offering valuable insights for researchers and practitioners. The few models that were picked out for performance analysis are VGG16, VGG19, ResNet50, DenseNet, InceptionV3, and EfficientNet. The analysis was performed on 200 sample images, each of 50 different species, taken from Google’s dataset. This comparative study welcomes the reader to the intersection of avian ecology and deep learning, where feathers meet pixels to unlock new dimensions in bird species identification.

Downloads

Download data is not yet available.

References

Xeno-Canto. Sharing Bird Sounds from around the World. 2021. Available online: https://www.xeno-canto.org/about/xeno-canto (accessed on 27th March 2024)

Jessica L. Oliver, Margot Brereton, David M. Watson, and Paul Roe. 2018. Visualisations elicit knowledge to refine citizen science technology design: spectrograms resonate with birders. In Proceedings of the 30th Australian Conference on Computer-Human Interaction (OzCHI '18). Association for Computing Machinery, New York, NY, USA, 133–144. https://doi.org/10.1145/3292147.3292171

Wang H, Xu Y, Yu Y, Lin Y, Ran J. An Efficient Model for a Vast Number of Bird Species Identification Based on Acoustic Features. Animals (Basel). 2022 Sep 15;12(18):2434. doi: 10.3390/ani12182434. PMID: 36139299; PMCID: PMC9495150.

Bardeli, R., Wolff, D., Kurth, F., Koch, M., Tauchert, K. H., & Frommolt, K. H. (2010). Detecting bird sounds in a complex acoustic environment and application to bioacoustic monitoring. Pattern Recognition Letters, 31(12), 1524-1534.

Feld, S. (2012). Sound and Sentiment: Birds, Weeping, Poetics, and Song in Kaluli Expression, with a new introduction by the author. Duke University Press.

Jancovic, Peter & Kokuer, Munevver & Russell, Martin. (2014). Bird species recognition from field recordings using HMM-based modeling of frequency tracks. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings 10.1109/ICASSP.2014. 6855210.

Zhao, Z., Zhang, S., Xu, Z., Bellisario, K., Dai, N., Omrani, H., & Pijanowski, B. C. (2017). Automated bird acoustic event detection and robust species classification. Ecological Informatics, 39, 99-108. https://doi.org/10.1016/j.ecoinf.2017.04.003.

Lasseck, M. (2018). Audio-based Bird Species Identification with Deep Convolutional Neural Networks. Conference and Labs of the Evaluation Forum..

Lee, C.H., Han, C.C. and Chuang, C.C., 2008. Automatic classification of bird species from their sounds using two-dimensional cepstral coefficients. IEEE Transactions on Audio, Speech, and Language Processing, 16(8), pp.1541-1550.

Briggs, F., Raich, R. and Fern, X.Z., 2009, December. Audio classification of bird species: A statistical manifold approach. In 2009 Ninth IEEE International Conference on data mining (pp. 51-60). IEEE.

Neal, L., Briggs, F., Raich, R., and Fern, X.Z., 2011, May. Time-frequency segmentation of bird song in noisy acoustic environments. In 2011 IEEE International Conference on Acoustics, speech and signal processing (ICASSP) (pp. 2012-2015). IEEE.

Lopes, M.T., Gioppo, L.L., Higushi, T.T., Kaestner, C.A., Silla Jr, C.N. and Koerich, A.L., 2011, December. Automatic bird species identification for large number of species. In 2011 IEEE International Symposium on Multimedia (pp. 117-122). IEEE.

Sprengel, E., Jaggi, M., Kilcher, Y., & Hofmann, T. (2016). Audio Based Bird Species Identification using Deep Learning Techniques. Conference and Labs of the Evaluation Forum.

Incze, A., Jancsó, H.B., Szilágyi, Z., Farkas, A. and Sulyok, C., 2018, September. Bird sound recognition using a convolutional neural network. In 2018 IEEE 16th International Symposium on Intelligent Systems and Informatics (SISY) (pp. 000295-000300). IEEE.

Zivkovic, Zoran & Van der Heijden, F.. (2006). Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern Recognition Letters. 27. 773-780. 10.1016/j.patrec.2005.11.005.

Gavves, E., Fernando, B., Snoek, C.G., Smeulders, A.W. and Tuytelaars, T., 2013. Fine-grained categorization by alignments. In Proceedings of the IEEE International Conference on Computer Vision (pp. 1713-1720).

Voulodimos, A., Doulamis, N., Doulamis, A. and Protopapadakis, E., 2018. Deep learning for computer vision: A brief review. Computational intelligence and neuroscience, 2018.

Simons, E. S., & Hinders, M. K. (2019). Automatic counting of birds in a bird deterrence field trial. Ecology and Evolution, 9(20), 11878–11890.

Alter, A.L. and Wang, K.M., 2017. An Exploration of Computer Vision Techniques for Bird Species Classification.

Zheng, H., Fu, J., Mei, T. and Luo, J., 2017. Learning multi-attention convolutional neural network for fine-grained image recognition. In Proceedings of the IEEE International Conference on Computer Vision (pp. 5209-5217).

Weinstein, B.G., 2018. A computer vision for animal ecology. Journal of Animal Ecology, 87(3), pp.533-545.

Huang, Y.P. and Basanta, H., 2019. Bird image retrieval and recognition using a deep learning platform. IEEE Access, 7, pp.66980-66989.

Zhou, B., Deng, B. and Xia, K., BIRD CLASSIFICATION.

Öztürk, A.E. and Erçelebi, E., 2021. Real UAV-bird image classification using CNN with a synthetic dataset. Applied Sciences, 11(9), p.3863.

Biswas, A.A., Rahman, M.M., Rajbongshi, A. and Majumder, A., 2021, January. Recognition of local birds using different cnn architectures with transfer learning. In 2021 International Conference on Computer Communication and Informatics (ICCCI) (pp. 1-6). IEEE.

Belko, A., Dobratulin, K. and Kuznetsov, A., 2021. Two-Stage Classification Model for Feather Images Identification. In Pattern Recognition. ICPR International Workshops and Challenges: Virtual Event, January 10–15, 2021, Proceedings, Part V (pp. 172-181). Springer International Publishing.

Meek, P. D., Fleming, P., & Ballard, G. (2012). An introduction to camera trapping for wildlife surveys in Australia. Canberra, Australia: Invasive Animals Cooperative Research Centre.

Ahumada, J. A., Fegraus, E., Birch, T., Flores, N., Kays, R., O’Brien, T. G., ... & Dancer, A. (2020). Wildlife insights: A platform to maximize the potential of camera trap and other passive sensor wildlife data for the planet. Environmental Conservation, 47(1), 1-6.

Rovero, F., & Kays, R. (2021). Camera trapping for conservation. Conservation Technology; Wich, SA, Piel, AK, Eds.; Oxford University Press: Oxford, UK, 79-101.

Lin, C. W., Chen, Z., & Lin, M. (2022). Video-based bird posture recognition using dual feature-rates deep fusion convolutional neural network. Ecological Indicators, 141, 109141.

Borowiec, M. L., Dikow, R. B., Frandsen, P. B., McKeeken, A., Valentini, G., & White, A. E. (2022). Deep learning as a tool for ecology and evolution. Methods in Ecology and Evolution, 13(8), 1640-1660.

BenAbdelkader, C., Cutler, R., Nanda, H. and Davis, L., 2001. Eigengait: Motion-based recognition of people using image self-similarity. In Audio-and Video-Based Biometric Person Authentication: Third International Conference, AVBPA 2001 Halmstad, Sweden, June 6–8, 2001 Proceedings 3 (pp. 284-294). Springer Berlin Heidelberg.

Ayyildiz, K. and Conrad, S., 2011. Video classification by main frequencies of repeating movements.

Betke, K., 2008. Measurement of wind turbine construction noise at Horns Rev II. Itap Bericht, (1256-08).

Cullinan, V., Duberstein, C. and Matzner, S., 2014. An Automated Way to Extract Wing Beat Frequency and Flap-Glide Patterns from Thermal Imagery.

Matzner, S., Cullinan, V.I. and Duberstein, C.A., 2015. Two-dimensional thermal video analysis of offshore bird and bat flight. Ecological Informatics, 30, pp.20-28.

Hristov, N.I., Betke, M., Theriault, D.E., Bagchi, A. and Kunz, T.H., 2010. Seasonal variation in colony size of Brazilian free-tailed bats at Carlsbad Cavern based on thermal imaging. Journal of Mammalogy, 91(1), pp.183-192

Lazarevic, L., 2010. Improving the efficiency and accuracy of nocturnal bird surveys through equipment selection and partial automation (Doctoral dissertation, Brunel University School of Engineering and Design PhD Theses)

Duberstein, C.A., Matzner, S., Cullinan, V.I., Virden, D.J., Myers, J.R. and Maxwell, A.R., 2012. Automated Thermal Image Processing for Detection and Classification of Birds and Bats-FY2012 Annual Report (No. PNNL-21911). Pacific Northwest National Lab. (PNNL), Richland, WA (United States).

Beyan, C. and Fisher, R.B., 2013, September. Detection of Abnormal Fish Trajectories Using a Clustering-Based Hierarchical Classifier. In BMVC.

Atanbori, J., Duan, W., Appiah, K., Murray, J., & Dickinson, P. (2015). A computer vision approach to classification of birds in flight from video sequences.

Marini, A., Facon, J. and Koerich, A.L., 2013, October. Bird species classification based on color features. In 2013 IEEE International Conference on Systems, Man, and Cybernetics (pp. 4336-4341). IEEE.

Chin, T.W., Ding, R. and Marculescu, D., 2019. Adascale: Towards real-time video object detection using adaptive scaling. Proceedings of Machine Learning and Systems, 1, pp.431-441.

Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition (pp. 248–255).