Abstract
Bird species classification is a challenging task in the field of computer vision because of its fine-grained nature, which in turn can lead to high interclass similarities. An important aspect for many fine-grained categorization problems involves processing of local-level semantics. This highlights the need for accurate part detection/localization. In this work, we propose a two-step approach to address the problem of bird part localization from an input image. In the first step, a Faster RCNN (FRCNN) is learnt to suggest possible bird part regions. However, the part region proposals given by Faster RCNN are not always precise. To refine these, a second step involving a CNN-based part classifier, trained only on bird part segments is used. Both FRCNN and CNN part classifiers are trained separately in a supervised manner. The part classifier effectively builds upon the FRCNN region proposals, as it is trained on more specific data as compared to FRCNN. We evaluate the proposed framework on the standard CUB-200-2011 bird dataset, as well as on a newly collected IIT Mandi bird dataset, where the latter is used only during testing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zhang, X., et al.: Picking deep filter responses for fine-grained image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Zhang, X., et al.: Fused one-vs-all features with semantic alignments for fine-grained visual categorization. IEEE Trans. Image Process. 25(2), 878–892 (2016)
Bay, H., Tuytelaars, T., Gool, L.V.: Surf: Speeded up robust features. In: European Conference on Computer Vision. Springer, Berlin, Heidelberg (2006)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, CVPR 2005, vol. 1. IEEE (2005)
Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell. 24(7), 971–987 (2002)
Huang, S., et al.: Part-stacked CNN for fine-grained visual categorization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)
Zhang, Y., et al.: Weakly supervised fine-grained categorization with part-based image representation. IEEE Trans. Image Process. 25(4), 1713–1725 (2016)
Zeiler, M.D., Taylor, G.W., Fergus, R.: Adaptive deconvolutional networks for mid and high level feature learning. In: 2011 IEEE International Conference on Computer Vision (ICCV). IEEE (2011)
Girshick, R., et al.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)
Girshick, R.: Fast R-CNN. arXiv preprint arXiv:1504.08083 (2015)
Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (2015)
Wah, C., et al.: The Caltech-UCSD birds-200-2011 dataset (2011)
Liu, J., Belhumeur, P.N.: Bird part localization using exemplar-based models with enforced pose and subcategory consistency. In: 2013 IEEE International Conference on Computer Vision (ICCV). IEEE (2013)
Wah, C., et al.: Similarity comparisons for interactive fine-grained categorization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)
Deng, J., Krause, J., Fei-Fei, L.: Fine-grained crowdsourcing for fine-grained recognition. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2013)
Lin, T.-Y., RoyChowdhury, A., Maji, S.: Bilinear CNN models for fine-grained visual recognition. arXiv preprint arXiv:1504.07889 (2015)
Lin, Di, et al.: Deep LAC: deep localization, alignment and classification for fine-grained recognition. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2015)
Elhoseiny, M., et al.: Link the head to the beak: zero shot learning from noisy text description at part precision. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Liu, X., et al.: Fully convolutional attention networks for fine-grained recognition. arXiv preprint arXiv:1603.06765 (2016)
Peng, Y., He, X., Zhao, J.: Object-part attention model for fine-grained image classification. IEEE Trans. Image Process. 27(3), 1487–1500 (2018)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Pankajakshan, A., Bhavsar, A. (2020). Faster RCNN-CNN-Based Joint Model for Bird Part Localization in Images. In: Chaudhuri, B., Nakagawa, M., Khanna, P., Kumar, S. (eds) Proceedings of 3rd International Conference on Computer Vision and Image Processing. Advances in Intelligent Systems and Computing, vol 1024. Springer, Singapore. https://doi.org/10.1007/978-981-32-9291-8_17
Download citation
DOI: https://doi.org/10.1007/978-981-32-9291-8_17
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-32-9290-1
Online ISBN: 978-981-32-9291-8
eBook Packages: EngineeringEngineering (R0)