Multi-granular Angle Description for Plant Leaf Classification and Retrieval Based on Quotient Space
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Plant leaf classification is a significant application of image processing techniques in modern agriculture. Inthis paper, a multi-granular angle description method is proposed for plant leaf classification and retrieval. Theproposed method can describe leaf information from coarse to fine using multi-granular angle features. In theproposed method, each leaf contour is partitioned first with equal arc length under different granularities. Andthen three kinds of angle features are derived under each granular partition of leaf contour: angle value, anglehistogram, and angular ternary pattern. These multi-granular angle features can capture both local and globeinformation of the leaf contour, and make a comprehensive description. In leaf matching stage, the simple cityblock metric is used to compute the dissimilarity of each pair of leaf under different granularities. And thematching scores at different granularities are fused based on quotient space theory to obtain the final leafsimilarity measurement. Plant leaf classification and retrieval experiments are conducted on two challengingleaf image databases: Swedish leaf database and Flavia leaf database. The experimental results and thecomparison with state-of-the-art methods indicate that proposed method has promising classification andretrieval performance.
Abstract
Plant leaf classification is a significant application of image processing techniques in modern agriculture. Inthis paper, a multi-granular angle description method is proposed for plant leaf classification and retrieval. Theproposed method can describe leaf information from coarse to fine using multi-granular angle features. In theproposed method, each leaf contour is partitioned first with equal arc length under different granularities. Andthen three kinds of angle features are derived under each granular partition of leaf contour: angle value, anglehistogram, and angular ternary pattern. These multi-granular angle features can capture both local and globeinformation of the leaf contour, and make a comprehensive description. In leaf matching stage, the simple cityblock metric is used to compute the dissimilarity of each pair of leaf under different granularities. And thematching scores at different granularities are fused based on quotient space theory to obtain the final leafsimilarity measurement. Plant leaf classification and retrieval experiments are conducted on two challengingleaf image databases: Swedish leaf database and Flavia leaf database. The experimental results and thecomparison with state-of-the-art methods indicate that proposed method has promising classification andretrieval performance.
참고문헌 (23)
- J. Chaki, "Plant leaf recognition using texture and shape features with neural classifiers", Pattern Recognition Letters, 58, pp.61~68 (2015)
- N. Liu, "Improved deep belief networks and multi-feature fusion for leaf identification", Neurocomputing, 216, pp.460~467 (2016)
- 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)
- J. Hu, "A multiscale fusion convolutional neural network for plant leaf recognition", IEEE Signal Processing Letters, 25(6), pp.853~857 (2018)
- J. Cao, "Similarity based leaf image retrieval using multiscale R-angle description", Information Sciences, 374, pp.51~64 (2016)
- C. Zhao, "Plant identification using leaf shapes : a pattern counting approach", Pattern Recognition, 48(10), pp.3203~3215 (2015)
- M. G. Larese, "Automatic classification of legumes using leaf vein image features", Pattern Recognition, 47(1), pp.158~168 (2014)
- J. C. Neto, "Plant species identification using Elliptic Fourier leaf shape analysis", Computers and Electronics in Agriculture, 50(2), pp.121~134 (2006)
- A. Aakif, "Automatic classification of plants based on their leaves", Biosystems Engineering, 139, pp.66~75 (2015)
- M. M. de Souza, "Evolutionary optimization of a multiscale descriptor for leaf shape analysis", Expert Systems with Applications, 63, pp.375~385 (2016)
- B. Wang, "MARCH : multiscale-arch-height description for mobile retrieval of leaf images", Information Sciences, 302, pp.132~148 (2015)
- 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)
- H. Ling, "Shape classification using the inner-distance", IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(2), pp.286~299 (2007)
- R. X. Hu, "Angular pattern and binary angular pattern for shape retrieval", IEEE Transactions on Image Processing, 23(3), pp.1118~1127 (2013)
- I. Kunttu, "Shape-based retrieval of industrial surface defects using angular radius Fourier descriptor", IET Image Processing, 1(2), pp.231~236 (2007)
- G. Wang, "Granular computing with multiple granular layers for brain big data processing", Brain Informatics, 1(1-4), pp.1~10 (2014)
- Y. Yao, "A triarchic theory of granular computing", Granular Computing, 1(2), pp.145~157 (2016)
- R. Yin, "Multi-feature fusion for image segmentation based on granular theory", Proceedings of the 2014 IEEE 18th International Conference on Computer Supported Cooperative Work in Design(CSCWD), pp.186~190 (2014)
- O. Soderkvist, "Computer vision classification of leaves from Swedish trees", M. S., Department of Electrical Engineering, pp.2001
- S. G. Wu, "A leaf recognition algorithm for plant classification using probabilistic neural network", Proceedings of 2007 IEEE International Symposium on Signal Processing and Information Technology, pp.11~16 (2007)
- T. Adamek, "A multiscale representation method for nonrigid shapes with a single closed contour", IEEE Transactions on Circuits and Systems for Video Technology, 14(5), pp.742~753 (2004)
- N. Alajlan, "Shape retrieval using triangle-area representation and dynamic space warping", Pattern Recognition, 40(7), pp.1911~1920 (2007)
- R. Hu, "Multiscale distance matrix for fast plant leaf recognition", IEEE Transactions on Image Processing, 21(11), pp.4667~4672 (2012)