Abstract
In this paper, a flower species recognition system combining object detection and Attention Mechanism is proposed. In order to strengthen the ability of the model to process images under complex backgrounds, we apply the method of object detection to locate flowers that we want to recognize. For less time of training, object detection and classification are Integrate into an end-to-end network stacked attention modules to generate attention-aware features.
Experiments are conducted on Flower 102, our method can recognize flower species against a complex background. With model owning attention module and transfer learning, we increase mAP from 73.8% to 74.7% and training time is reduced by about 15%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Redmon, J., et al.: You Only Look Once: Unified Real-Time Object Detection (2015)
Redmon, J., Farhadi, A.: IEEE 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) - Honolulu, HI (2017.7.21-2017.7.26). In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) - YOLO9000: Better, Faster, Stronger, pp. 6517–6525 (2017)
Ren, S., et al.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137–1149 (2017)
Wang, F., et al.: Residual Attention Network for Image Classification (2017)
Hong, K.S., Lee, H.H., Kim, J.H.: Mobile-based flower species recognition in the natural environment. Electron. Lett. 51(11), 826–828 (2015)
Guan, Y.: Flower species recognition system based on residual network transfer learning. Comput. Eng. Appl. 55(1), 174–179 (2019)
Gogul, I., Kumar, V.S.: Flower species recognition system using convolution neural networks and transfer learning. In: 2017 Fourth International Conference on Signal Processing, Communication and Networking (ICSCN). IEEE (2017)
Chai, Y.: Recognition between a large numbers of flower species. Masters’ thesis at the Swiss Federal Institute of Technology Zurich (2011)
Mnih, V., Heess, N., Graves, A., Kavukcuoglu, K.: Recurrent models of visual attention. In: NIPS (2014)
Neubeck, A., Gool, L.J.V.: Efficient Non-Maximum Suppression (2006)
Huang, D.S.: Systematic Theory of Neural Networks for Pattern Recognition. Publishing House of Electronic Industry of China, May 1996. (in Chinese)
Huang, D.S., Du, J.-X.: A constructive hybrid structure optimization methodology for radial basis probabilistic neural networks. IEEE Trans. Neural Netw. 19(12), 2099–2115 (2008)
Huang, D.S.: Radial basis probabilistic neural networks: model and application. Int. J. Pattern Recognit. Artif. Intell. 13(7), 1083–1101 (1999)
Huang, D.S., Jiang, W.: A general CPL-AdS methodology for fixing dynamic parameters in dual environments. IEEE Trans. Syst. Man Cybern. Part B 42(5), 1489–1500 (2012)
Wang, X.F., Huang, D.S., Xu, H.: An efficient local Chan-Vese model for image segmentation. Pattern Recogn. 43(3), 603–618 (2010)
Wang, X.-F., Huang, D.S.: A novel density-based clustering framework by using level set method. IEEE Trans. Knowl. Data Eng. 21(11), 1515–1531 (2009)
Huang, D.S., Ip, H.H.S., Chi, Z.-R.: A neural root finder of polynomials based on root moments. Neural Comput. 16(8), 1721–1762 (2004)
Huang, D.S.: A constructive approach for finding arbitrary roots of polynomials by neural networks. IEEE Trans. Neural Netw. 15(2), 477–491 (2004)
Huang, D.S., Ip, H.H.S., Law, K.C.K., Chi, Z.: Zeroing polynomials using modified constrained neural network approach. IEEE Trans. Neural Netw. 16(3), 721–732 (2005)
Zhao, Z.Q., Glotin, H., Xie, Z., Gao, J., Wu, X.: Cooperative sparse representation in two opposite directions for semi-supervised image annotation. IEEE Trans. Image Process. (TIP) 21(9), 4218–4231 (2012)
Zhu, L., Huang, D.S.: Efficient optimally regularized discriminant analysis. Neurocomputing 117, 12–21 (2013)
Zhu, L., Huang, D.S.: A rayleigh–ritz style method for large-scale discriminant analysis. Pattern Recogn. 47(4), 1698–1708 (2014)
Acknowledgements
This work was supported by the grants of the National Science Foundation of China, Nos. 61672203, 61572447, 61772357, 31571364, 61861146002, 61520106006, 61772370, 61702371, 61672382, and 61732012, China Post-doctoral Science Foundation Grant, No. 2017M611619, and supported by “BAGUI Scholar” Program and the Scientific & Technological Base and Talent Special Program, GuiKe AD18126015 of the Guangxi Zhuang Autonomous Region of China.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Qin, W. et al. (2019). Flower Species Recognition System Combining Object Detection and Attention Mechanism. In: Huang, DS., Huang, ZK., Hussain, A. (eds) Intelligent Computing Methodologies. ICIC 2019. Lecture Notes in Computer Science(), vol 11645. Springer, Cham. https://doi.org/10.1007/978-3-030-26766-7_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-26766-7_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-26765-0
Online ISBN: 978-3-030-26766-7
eBook Packages: Computer ScienceComputer Science (R0)