Joint Semantic Parts for Fine-Grained Bird Images Recognition

被引：0
|
作者：
Zhao Y. [1 ,2 ]
Xu D. [1 ]
机构：
[1] School of Information, Yunnan University, Kunming
[2] School of Big Data and Intelligent Engineering, Southwest Forestry University, Kunming
来源：
Xu, Dan (danxu@ynu.edu.cn) | 2018年 / Institute of Computing Technology卷 / 30期
关键词：
Convolutional neural net-works; Deep learning; Fine-grained image recognition; Semantic parts detection;
D O I：
10.3724/SP.J.1089.2018.16781
中图分类号：
学科分类号：
摘要：
Fine-grained image recognition is a challenging computer vision problem, due to small inter-class varia-tions caused by highly similar subordinate categories, and the large intra-class variations in poses, scales and ro-tations. In order to perform fine-grained recognition on bird images, this paper proposes a deep convolution neu-ral networks model collaborated with semantic parts detection. The model consists of two modules, one module is a parts detector network, and another module is a three-stream classification network based on deep residual network. In the meantime, a new bird images dataset was collected and labeled to facility the research of fi-ne-grained bird images recognition. Experiment results on YUB-200-2017 and CUB-200-2011 illustrate the proposed model has higher part detection and image classification accuracy comparing with state-of-the-arts fi-ne-grained bird image recognition approaches. © 2018, Beijing China Science Journal Publishing Co. Ltd. All right reserved.
引用
收藏
页码：1522 / 1529
页数：7
相关论文
共 22 条
  • [1] Zhang N., Donahue J., Girshick R., Et al., Part-based R-CNNs for fine-grained category detection, Proceedings of the European Conference on Computer Vision, 8689, pp. 834-849, (2014)
  • [2] Uijlings J.R., Sande K.E., Gevers T., Et al., Selective search for object recognition, International Journal of Computer Vision, 104, 2, pp. 154-171, (2013)
  • [3] Girshick R., Donahue J., Darrell T., Et al., Rich feature hier-archies for accurate object detection and semantic seg-mentation, Proceedings of IEEE Conference on Com-puter Vision and Pattern Recognition, pp. 580-587, (2014)
  • [4] Branson S., Van-Horn G., Belongie S., Et al., Bird species categorization using pose normalized deep convolutional nets, Proceedings of British Machine Vision Conference, pp. 1-14, (2014)
  • [5] Lin D., Shen X.Y., Lu C.W., Et al., Deep LAC: deep localization, alignment and classification for fine-grained recognition, Proceedings of IEEE International Conference on Com-puter Vision and Pattern Recognition, pp. 1666-1674, (2015)
  • [6] Zhang H., Xu T., Elhoseiny M., Et al., SPDA-CNN: unifying semantic part detection and abstraction for fine-grained recognition, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1143-1152, (2016)
  • [7] Girshick R., Fast R-CNN, Proceedings of International Conference on Computer Vision, pp. 1440-1448, (2015)
  • [8] Huang S.L., Xu Z., Tao D.C., Et al., Part-stacked CNN for fi-ne-grained visual categorization, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1173-1182, (2016)
  • [9] Wei X.S., Xie C.W., Wu J.X., Et al., Mask-CNN: localizing parts and selecting descriptors for fine-grained bird species categorization, Pattern Recognition, 76, 4, pp. 704-714, (2018)
  • [10] Lin T.Y., Roychowdhury A., Maji S., Bilinear CNN models for fine-grained visual recognition, Proceedings of IEEE International Conference on Computer Vision, pp. 1449-1457, (2015)
123