Leaf Image Recognition Based on Bag of Features
Abstract
:1. Introduction
2. Theory for Plant Recognition
2.1. Dual-Output Pulse-Coupled Neural Network
2.2. Bag of Feature
- (1)
- Extract features from different scales and combine them together.
- (2)
- Convert features of different lengths into fixed-length features.
3. Feature Extraction
3.1. Dictionary Learning
3.2. Shape Feature Extractions
3.3. Texture Feature Extractions
4. Proposed Recognition Method
4.1. Image Preprocessing
- a.
- Image denoising: If the leaf image has some background information, the background should be deleted, which will decrease the calculations of features extraction. Because most leaf image datasets are built using optical scanners, the background is simple and easy to be removed by an adaptive threshold segmentation method.
- b.
- Image segmentation: Sometimes the obtained leaf image has a complex background, and it needs to be separated from the background by segmentation. Since most leaf images contain some regions without value, the target region is extracted by a morphology method. Then, a quadrilateral is used to surround the target region. The quadrilateral is obtained from the original image and rotated to horizontal.
- c.
- Image enhancement: Sometimes it is essential to enhance the contrast and texture of the image. Histogram equalization and linear stretching are adopted in this method. Then, high-pass filter is employed to enhance the edge and texture of the leaf image (gray image). Finally, texture feature is extracted from this gray image.
4.2. Feature Fusion
4.3. Classification
5. Experiments and Analysis
5.1. Datasets
5.2. Length of DPCNN
5.3. Effect and Stability Analysis
5.4. Comparison of Features
5.5. Comparison of Different Methods
6. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Dev, S.; Lee, Y.H.; Winkler, S. Categorization of cloud image patches using an improved texton-based approach. In Proceedings of the 2015 IEEE International Conference on Image Processing (ICIP), Quebec City, QC, Canada, 27–30 September 2015; pp. 422–426. [Google Scholar]
- Kristin, J.D.; Gerard, M.; Sven, D. Computational Texture and Patterns: From Textons to Deep Learning. Synth. Lect. Comput. Vis. 2018, 8, 1–113. [Google Scholar]
- Kumar, N.; Belhumeur, P.N.; Biswas, A.; Jacobs, D.W.; Kress, W.J.; Lopez, I.C.; Soares, J.V.B. Leafsnap: A computer vision system for automatic plant species identification. In Proceedings of the European Conference on Computer Vision, Florence, Italy, 7 October 2012; pp. 502–516. [Google Scholar]
- Hasim, A.; Herdiyeni, Y.; Douady, S. Leaf Shape Recognition using Centroid Contour Distance. IOP Conf. Ser. Earth Environ. Sci. 2016, 31, 012002. [Google Scholar] [CrossRef] [Green Version]
- Wu, S.G.; Bao, F.S.; Xu, E.Y.; Wang, Y.-X.; Chang, Y.-F.; Xiang, Q.-L. A leaf recognition algorithm for plant classification using probabilistic neural network. In Proceedings of the 2007 IEEE International Symposium on Signal Processing and Information Technology, Cairo, Egypt, 15–18 December 2007; pp. 11–16. [Google Scholar]
- Singh, K.; Gupta, I.; Gupta, S. SVM-BDT PNN and Fourier moment technique for classification of leaf shape. Int. J. Signal Process. Image Process. Pattern Recognit. 2010, 3, 67–78. [Google Scholar]
- Ling, H.B.; Jacobs, D.W. Shape classification using the inner-distance. IEEE Trans. Pattern Anal 2007, 29, 286–299. [Google Scholar] [CrossRef]
- Kala, J.; Viriri, S. Plant specie classification using sinuosity coefficients of leaves. Image Anal. Stereol. 2018, 37, 119. [Google Scholar] [CrossRef]
- Yu, X.; Gao, Y.; Xiong, S.; Yuan, X. Multiscale Contour Steered Region Integral and Its Application for Cultivar Classification. IEEE Access 2019, 7, 69087–69100. [Google Scholar] [CrossRef]
- Wang, Z.; Sun, X.; Ma, Y.; Zhang, H.; Ma, Y.; Xie, W.; Zhang, Y. Plant recognition based on intersecting cortical model. In Proceedings of the 2014 International Joint Conference on Neural Networks (IJCNN), Beijing, China, 6–11 July 2014; pp. 975–980. [Google Scholar]
- Tsolakidis, D.G.; Kosmopoulos, D.I.; Papadourakis, G. Plant leaf recognition using Zernike moments and histogram of oriented gradients. In Proceedings of the Hellenic Conference on Artificial Intelligence, Ioannina, Greece, 15–17 May 2014; pp. 406–417. [Google Scholar]
- Kulkarni, A.H.; Rai, H.M.; Jahagirdar, K.A.; Upparamani, P.S. A leaf recognition technique for plant classification using RBPNN and Zernike moments. Int. J. Adv. Res. Comput. Commun. Eng. 2013, 2, 984–988. [Google Scholar]
- Nilsback, M.-E.; Zisserman, A. Automated flower classification over a large number of classes. In Proceedings of the Indian Conference on Computer Vision, Graphics & Image Processing, Bhubaneswar, India, 16–19 December 2008; pp. 722–729. [Google Scholar]
- Hsiao, J.-K.; Kang, L.-W.; Chang, C.-L.; Lin, C.-Y. Comparative study of leaf image recognition with a novel learning-based approach. In Proceedings of the IEEE Science and Information Conference, London, UK, 27–29 August 2014; pp. 389–393. [Google Scholar]
- Tang, Z.; Su, Y.; Er, M.J.; Qi, F.; Zhang, L.; Zhou, J. A local binary pattern based texture descriptors for classification of tea leaves. Neurocomputing 2015, 168, 1011–1023. [Google Scholar] [CrossRef]
- Fu, B.; Mao, M.; Zhao, X.; Shan, Z.; Yang, Z.; He, L.; Wang, Z. Recognition of Plants with Complicated Background by Leaf Features. J. Phys. Conf. Ser. 2019, 1176, 032053. [Google Scholar] [CrossRef]
- Saleem, G.; Akhtar, M.; Ahmed, N.; Qureshi, W.S. Automated analysis of visual leaf shape features for plant classification. Comput. Electron. Agric. 2019, 157, 270–280. [Google Scholar] [CrossRef]
- Chaki, J.; Parekh, R.; Bhattacharya, S. Plant leaf recognition using texture and shape features with neural classifiers. Pattern Recognit. Lett. 2015, 58, 61–68. [Google Scholar] [CrossRef]
- Shao, Y. Supervised global-locality preserving projection for plant leaf recognition. Comput. Electron. Agric. 2019, 158, 102–108. [Google Scholar] [CrossRef]
- Chaki, J.; Dey, N.; Moraru, L.; Fuqian, S. Fragmented plant leaf recognition: Bag-of-features, fuzzy-color and edge-texture histogram descriptors with multi-layer perceptron. Opt. Int. J. Light Electron Opt. 2019, 181, 639–650. [Google Scholar] [CrossRef]
- Lin, F.-Y.; Zheng, C.-H.; Wang, X.-F.; Man, Q.-K. Multiple classification of plant leaves based on gabor transform and lbp operator. In Proceedings of the International Conference on Intelligent Computing, Shanghai, China, 15–18 September 2008; pp. 432–439. [Google Scholar]
- Zheru, C.; Li, H.; Wang, C. Plant species recognition based on bark patterns using novel Gabor filter banks. In Proceedings of the International Conference on Neural Networks and Signal Processing, Nanjing, China, 14–17 December 2003; Volume 1032, pp. 1035–1038. [Google Scholar]
- Fuentes, S.; Hernández-Montes, E.; Escalona, J.M.; Bota, J.; Gonzalez Viejo, C.; Poblete-Echeverría, C.; Tongson, E.; Medrano, H. Automated grapevine cultivar classification based on machine learning using leaf morpho-colorimetry, fractal dimension and near-infrared spectroscopy parameters. Comput. Electron. Agric. 2018, 151, 311–318. [Google Scholar] [CrossRef]
- Zhang, S.W.; Lei, Y.K.; Dong, T.B.; Zhang, X.P. Label propagation based supervised locality projection analysis for plant leaf classification. Pattern Recogn 2013, 46, 1891–1897. [Google Scholar] [CrossRef]
- Valliammal, N.; Geethalakshmi, S. An optimal feature subset selection for leaf analysis. Int. J. Comput. Commun. Eng. 2012, 6, 440–445. [Google Scholar]
- Wang, X.G.; Feng, B.; Bai, X.; Liu, W.Y.; Latecki, L.J. Bag of contour fragments for robust shape classification. Pattern Recogn. 2014, 47, 2116–2125. [Google Scholar] [CrossRef]
- Nguyen Thanh, T.K.; Truong, Q.B.; Truong, Q.D.; Huynh Xuan, H. Depth Learning with Convolutional Neural Network for Leaves Classifier Based on Shape of Leaf Vein. In Proceedings of the Intelligent Information and Database Systems, Dong Hoi City, Vietnam, 19–21 March 2018; pp. 565–575. [Google Scholar]
- Li, X.J.; Ma, Y.D.; Wang, Z.B.; Yu, W.R. Geometry-Invariant Texture Retrieval Using a Dual-Output Pulse-Coupled Neural Network. Neural Comput 2012, 24, 194–216. [Google Scholar] [CrossRef]
- Lazebnik, S.; Schmid, C.; Ponce, J. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In Proceedings of the IEEE Computer Society Conference on Computer Vision & Pattern Recognition, New York, NY, USA, 17–22 June 2006; pp. 2169–2178. [Google Scholar]
- Wang, J.; Yang, J.; Yu, K.; Lv, F.; Huang, T.; Gong, Y. Locality-constrained linear coding for image classification. In Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, USA, 13–18 June 2010; pp. 3360–3367. [Google Scholar]
- Yu, H.; Yang, J. A direct LDA algorithm for high-dimensional data—With application to face recognition. Pattern Recogn. 2001, 34, 2067–2070. [Google Scholar] [CrossRef] [Green Version]
- Novotny, P.; Suk, T. Leaf recognition of woody species in Central Europe. Biosyst. Eng. 2013, 115, 444–452. [Google Scholar] [CrossRef]
- Hall, D.; McCool, C.; Dayoub, F.; Sunderhauf, N.; Upcroft, B. Evaluation of features for leaf classification in challenging conditions. In Proceedings of the IEEE Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA, 5–9 January 2015; pp. 797–804. [Google Scholar]
- Fan, R.E.; Chang, K.W.; Hsieh, C.J.; Wang, X.R.; Lin, C.J. LIBLINEAR: A Library for Large Linear Classification. J. Mach. Learn Res. 2008, 9, 1871–1874. [Google Scholar]
- Chang, C.C.; Lin, C.J. LIBSVM: A Library for Support Vector Machines. Acm Trans. Intel. Syst. Tec. 2011, 2, 1–27. [Google Scholar] [CrossRef]
- Alvarsson, J.; Lampa, S.; Schaal, W.; Andersson, C.; Wikberg, J.E.; Spjuth, O. Large-scale ligand-based predictive modelling using support vector machines. J. Cheminformatics 2016, 8, 39. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Hu, R.X.; Jia, W.; Ling, H.B.; Huang, D.S. Multiscale Distance Matrix for Fast Plant Leaf Recognition. IEEE Trans. Image Process. 2012, 21, 4667–4672. [Google Scholar] [PubMed]
- Söderkvist, O. Computer vision classification of leaves from swedish trees. Master’s Thesis, Linkoping University, Linkoping, Sweden, 2001; p. 74. [Google Scholar]
- Demisse, G.G.; Aouada, D.; Ottersten, B. Deformation Based Curved Shape Representation. IEEE Trans. Pattern Anal. Mach. Intell. 2018, 40, 1338–1351. [Google Scholar] [CrossRef] [Green Version]
- Tharwat, A.; Gaber, T.; Hassanien, A.E. One-dimensional vs. two-dimensional based features: Plant identification approach. J. Appl. Log. 2017, 24, 15–31. [Google Scholar] [CrossRef]
- Kadir, A.; Nugroho, L.E.; Susanto, A.; Insap Santosa, P. Experiments of zernike moments for leaf identification. J. Theor. Appl. Inf. Technol. 2012, 41, 82–93. [Google Scholar]
- Pearline, A.; Kumar, S.; Harini, S. A study on plant recognition using conventional image processing and deep learning approaches. J. Intell. Fuzzy Syst. 2019, 36, 1997–2004. [Google Scholar] [CrossRef]
- Kolivand, H.; Bong, M.F.; Rahim, M.; Sulong, G.; Baker, T.; Tully, D. An expert botanical feature extraction technique based on phenetic features for identifying plant species. PLoS ONE 2018, 13, e0191447. [Google Scholar] [CrossRef] [Green Version]
- Naresh, Y.G.; Nagendraswamy, H.S. Classification of medicinal plants: An approach using modified LBP with symbolic representation. Neurocomputing 2016, 173, 1789–1797. [Google Scholar] [CrossRef]
- Turkoglu, M.; Hanbay, D. Leaf-based plant species recognition based on improved local binary pattern and extreme learning machine. Phys. A Statal Mech. Appl. 2019, 527, 121297. [Google Scholar] [CrossRef]
- Yousefi, E.; Baleghi, Y.; Sakhaei, S.M. Rotation invariant wavelet descriptors, a new set of features to enhance plant leaves classification. Comput. Electron. Agric. 2017, 140, 70–76. [Google Scholar] [CrossRef]
- Kheirkhah, F.M.; Asghari, H. Plant Leaf Classification Using GIST Texture Features. IET Comput. Vis. 2018, 13, 369–375. [Google Scholar] [CrossRef]
- Wang, B.; Wang, D. Plant Leaves Classification: A Few-Shot Learning Method Based on Siamese Network. IEEE Access 2019, 7, 151754–151763. [Google Scholar] [CrossRef]
- Zhang, X.; Zhao, W.; Luo, H.; Chen, L.; Peng, J.; Fan, J. Plant recognition via leaf shape and margin features. Multimed. Tools Appl. 2019, 78, 27463–27489. [Google Scholar] [CrossRef]
- Yang, C.; Yu, Q. Multiscale Fourier descriptor based on triangular features for shape retrieval. Signal Process. Image Commun. 2018, 71. [Google Scholar] [CrossRef]
- Wang, B.; Brown, D.; Gao, Y.; Salle, J.L. MARCH: Multiscale-arch-height description for mobile retrieval of leaf images. Inf. Sci. 2015, 302, 132–148. [Google Scholar] [CrossRef]
- Wang, B.; Gao, Y. Hierarchical String Cuts: A Translation, Rotation, Scale, and Mirror Invariant Descriptor for Fast Shape Retrieval. IEEE Trans. Image Process. Publ. IEEE Signal Process. Soc. 2014, 23. [Google Scholar] [CrossRef] [Green Version]
- Zhao, C.; Chan, S.S.F.; Cham, W.K.; Chu, L.M. Plant identification using leaf shapes—A pattern counting approach. Pattern Recognit. 2015, 48, 3203–3215. [Google Scholar] [CrossRef]
- Zeng, J.; Liu, M.; Fu, X.; Gu, R.; Leng, L. Curvature Bag of Words Model for Shape Recognition. IEEE Access 2019, 7, 57163–57171. [Google Scholar] [CrossRef]
- Kalyoncu, C.; Toygar, N. GTCLC: Leaf classification method using multiple descriptors. IET Comput. Vis. 2017, 10, 700–708. [Google Scholar] [CrossRef]
- Liu, N.; Kan, J.-M. Improved deep belief networks and multi-feature fusion for leaf identification. Neurocomputing 2016, 216, 460–467. [Google Scholar] [CrossRef]
- Zhang, S.; Zhang, C.; Zhu, Y.; You, Z. Discriminant WSRC for Large-Scale Plant Species Recognition. Comput. Intell. Neurosci. 2017, 2017. [Google Scholar] [CrossRef] [Green Version]
- Prasad, S.; Peddoju, S.K.; Ghosh, D. An adaptive plant leaf mobile informatics using RSSC. Multimed. Tools Appl. 2017, 76, 21339–21363. [Google Scholar] [CrossRef]
- Wang, Z.; Xiaoguang, S.; Zhang, Y.; Ying, Z.; Ma, Y. Leaf recognition based on PCNN. Neural Comput. Appl. 2015. [Google Scholar] [CrossRef]
Method | Species | Total Images | Training/Testing Images | Accuracy (%) |
---|---|---|---|---|
BOW + SC [14] | 32 | 1907 | 945/962 | 94.76 |
BOW + SIFT [14] | 32 | 1907 | 945/962 | 94.38 |
DBCS [39] | 32 | -- | --/-- | 94.07 |
MEW [32] | 32 | 1907 | 945/962 | 93.66 |
LLC + SIFT [29] | 32 | 1907 | 945/962 | 95.00 |
2DPCA [40] | 33 | -- | --/-- | 93.50 |
BOF_DP | 32 | 1907 | 945/962 | 96.34 |
Dataset | Swedish | Flavia | MEW2012 | ICL |
---|---|---|---|---|
Total number | 1125 | 1907 | 9745 | 16848 |
Training/testing | 555/570 | 945/962 | 4839/4906 | 8397/8451 |
Species | 15 | 32 | 153 | 220 |
Method | Species | Total Images | Training/Testing Images | Accuracy (%) |
---|---|---|---|---|
ZRM [41] | 32 | 1600 | 1280/320 | 93.40 |
Z&H [11] | 32 | 1600 | 1280/320 | 97.18 |
VGG16 [42] | 32 | 1600 | --/-- | 95.00 |
VGG19 [42] | 32 | 1600 | --/-- | 96.25 |
MLAB [43] | 32 | 1907 | 1280/627 | 94.76 |
MLBP [44] | 33 | 1907 | --/-- | 97.55 |
RM-LBP [45] | -- | -- | --/-- | 97.94 |
OM-LBP [45] | -- | -- | --/-- | 97.89 |
RIWD [46] | -- | -- | --/-- | 97.50 |
GIST [47] | 32 | 1907 | --/-- | 95.50 |
S-Inception [48] | n | -- | 20n/-- | 95.32 |
SSV [17] | 32 | 1600 | 1280/320 | 98.75 |
Proposed Method | 32 | 1907 | 945/962 | 98.53 |
Method | Species | Total Images | Training/Testing Images | Accuracy (%) |
---|---|---|---|---|
SMF [49] | 15 | 1125 | 375/750 | 95.82 |
Z&H [11] | 15 | 1125 | 375/750 | 95.86 |
15 | 1125 | 750/375 | 98.13 | |
MF [50] | 15 | 1125 | 375/750 | 97.60 |
MARCH [51] | 15 | 1125 | --/-- | 96.21 |
MLBP [44] | 15 | 1125 | --/-- | 96.83 |
HSCs [52] | 15 | 1125 | 375/750 | 96.91 |
CSD [53] | 15 | 1125 | --/-- | 97.07 |
MEW [32] | 15 | 1125 | 555/570 | 96.53 |
CBOW [54] | 15 | 1125 | --/-- | 97.23 |
S-Inception [48] | n | -- | 20n/-- | 91.37 |
Proposed Method | 15 | 1125 | 555/570 | 97.93 |
Method | Species | Total Images | Training/Testing Images | Accuracy (%) |
---|---|---|---|---|
SC [14] | 220 | 16,848 | 8397/8451 | 53.93 |
SIFT [14] | 220 | 16,848 | 8397/8451 | 72.26 |
DPCNN[28] | 220 | 16,848 | 8397/8451 | 94.07 |
MEW[32] | 220 | 16,848 | 8397/8451 | 84.62 |
GTCLC[55] | 42 | -- | --/-- | 86.80 |
SMF[49] | 50 | 1500 | 750/750 | 84.32 |
DBNs[56] | 50 | -- | --/-- | 96.00 |
220 | -- | --/-- | 93.90 | |
MARCH[51] | 220 | 5720 | 2860/2860 | 86.03 |
ROM-LBP[45] | -- | -- | --/-- | 83.71 |
DWSRC[57] | 220 | 16,846 | 15,746/1100 | 91.12 |
220 | 16,846 | 14,846/2000 | 90.64 | |
RSSC[58] | 220 | -- | --/-- | 92.94 |
Proposed Method | 220 | 16,848 | 8397/8451 | 94.22 |
Method | Species | Total Images | Training/Testing Images | Accuracy (%) |
---|---|---|---|---|
SC [14] | 153 | 9745 | 4839/4906 | 60.44 |
SIFT [14] | 153 | 9745 | 4839/4906 | 82.52 |
DPCNN [28] | 153 | 9745 | 4839/4906 | 92.81 |
MEW [32] | 153 | 9745 | 4839/4906 | 84.92 |
PCNN [59] | 153 | -- | --/-- | 91.20 |
Proposed Method | 153 | 9745 | 4839/4906 | 94.19 |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhang, Y.; Cui, J.; Wang, Z.; Kang, J.; Min, Y. Leaf Image Recognition Based on Bag of Features. Appl. Sci. 2020, 10, 5177. https://doi.org/10.3390/app10155177
Zhang Y, Cui J, Wang Z, Kang J, Min Y. Leaf Image Recognition Based on Bag of Features. Applied Sciences. 2020; 10(15):5177. https://doi.org/10.3390/app10155177
Chicago/Turabian StyleZhang, Yaonan, Jing Cui, Zhaobin Wang, Jianfang Kang, and Yufang Min. 2020. "Leaf Image Recognition Based on Bag of Features" Applied Sciences 10, no. 15: 5177. https://doi.org/10.3390/app10155177
APA StyleZhang, Y., Cui, J., Wang, Z., Kang, J., & Min, Y. (2020). Leaf Image Recognition Based on Bag of Features. Applied Sciences, 10(15), 5177. https://doi.org/10.3390/app10155177