Fast Leaf Recognition and Retrieval Using Multi-Scale Angular Description Method
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
Recognizing plant species based on leaf images is challenging because of the large inter-class variation andinter-class similarities among different plant species. The effective extraction of leaf descriptors constitutes themost important problem in plant leaf recognition. In this paper, a multi-scale angular description method isproposed for fast and accurate leaf recognition and retrieval tasks. The proposed method uses a novel scalegenerationrule to develop an angular description of leaf contours. It is parameter-free and can capture leaffeatures from coarse to fine at multiple scales. A fast Fourier transform is used to make the descriptor compactand is effective in matching samples. Both support vector machine and k-nearest neighbors are used to classifyleaves. Leaf recognition and retrieval experiments were conducted on three challenging datasets, namelySwedish leaf, Flavia leaf, and ImageCLEF2012 leaf. The results are evaluated with the widely used standardmetrics and compared with several state-of-the-art methods. The results and comparisons show that theproposed method not only requires a low computational time, but also achieves good recognition and retrievalaccuracies on challenging datasets.
Abstract
Recognizing plant species based on leaf images is challenging because of the large inter-class variation andinter-class similarities among different plant species. The effective extraction of leaf descriptors constitutes themost important problem in plant leaf recognition. In this paper, a multi-scale angular description method isproposed for fast and accurate leaf recognition and retrieval tasks. The proposed method uses a novel scalegenerationrule to develop an angular description of leaf contours. It is parameter-free and can capture leaffeatures from coarse to fine at multiple scales. A fast Fourier transform is used to make the descriptor compactand is effective in matching samples. Both support vector machine and k-nearest neighbors are used to classifyleaves. Leaf recognition and retrieval experiments were conducted on three challenging datasets, namelySwedish leaf, Flavia leaf, and ImageCLEF2012 leaf. The results are evaluated with the widely used standardmetrics and compared with several state-of-the-art methods. The results and comparisons show that theproposed method not only requires a low computational time, but also achieves good recognition and retrievalaccuracies on challenging datasets.
참고문헌 (10)
- Y. Shao, "Supervised global-locality preserving projection for plant leaf recognition", Computers and Electronics in Agriculture, 158, pp.102~108 (2019)
- J. Waldchen, "Plant species identification using computer vision techniques : a systematic literature review", Archives of Computational Methods in Engineering, 25(2), pp.507~543 (2018)
- J. W. Tan, "Deep learning for plant species classification using leaf vein morphometric", IEEE, 2020, pp.17(1), 82~90
- T. T. N. Nguyen, "Crowdsourcing for botanical data collection towards to automatic plant identification : a review", Computers and Electronics in Agriculture, 155, pp.412~425 (2018)
- F. M. Kheirkhah, "Plant leaf classification using GIST texture features", IET Computer Vision, 13(4), pp.369~375 (2019)
- G. Xu, "Unified multi-scale method for fast leaf classification and retrieval using geometric information", IET Image Processing, 13(12), pp.2328~2334 (2019)
- S. Zhang, "Plant species recognition methods using leaf image : overview", Neurocomputing, 408, pp.246~272 (2020)
- Guoqing Xu, "Shape Description and Retrieval Using Included-Angular Ternary Pattern", JIPS(Journal of Information Processing Systems), 15(4), pp.737~747 (2019), 한국정보처리학회[DOI]
- C. Yang, "Plant species recognition using triangle-distance representation", IEEE Access, 7, pp.178108~178120 (2019)
- S. Zhang, "Combining sparse representation and singular value decomposition for plant recognition", Applied Soft Computing, 67, pp.164~171 (2018)