Abstract
Due to the presence of various types of factors, such as illumination, viewpoint, intra-class complexity, and inter-class similarity, which make plant leaf recognition still a challenging research problem. In this paper, we present a very simple, yet effective feature representation method for plant leaf recognition. Concretely, it comprises four stages. Firstly, each leaf image is fed into an imagenet pre-trained CNN model to extract activated feature maps in a specified layer. Secondly, inspired by 1\(\times\)1 convolution, we exploit principle component analysis to learn the 1\(\times\)1 convolution filters. As a result, it not only eliminates the redundant information, reduces the feature dimension adaptively that is beneficial to the subsequent high order pooling, but also increases classification accuracy. Thirdly, kernel pooling is employed to capture second order statistics between each pair of features with the purpose of learning more discriminative information. Finally, matrix sqrt and upper triangle are performed to obtain the final leaf representation, which is utilized for classification and retrieval by the euclidean distance based nearest neighbor classifier. Extensive experiments are conducted on four representative plant leaf datasets, Flavia, Swedish, MEW2012, ICL, to validate the effectiveness of our method. For classification task, our method achieves outstanding and better average classification accuracies than the comparative state-of-the-art baselines. For retrieval task, our method gets significant higher or competitive MAP scores. Our implementation code will be available at https://github.com/fengshu666666/leafrecognition.
Similar content being viewed by others
Notes
download link: http://flavia.sourceforge.net
download link: http://zoi.utia.cas.cz/node/662
download link: https://download.csdn.net/download/qq_21175275/12011744
References
Adamek T, O’Connor NE (2004) A multiscale representation method for nonrigid shapes with a single closed contour. IEEE Transactions on Circuits and Systems for Video Technology 14(5):742–753
Alajlan N, El Rube I, Kamel MS, Freeman G (2007) Shape retrieval using triangle-area representation and dynamic space warping. Pattern Recognition 40(7):1911–1920
Araujo VM, Jr, ASB, Oliveira LES, Koerich AL (2020) Two-view fine-grained classification of plant species
Arribas JI, Sánchez-Ferrero GV, Ruiz-Ruiz G, Gómez-Gil J (2011) Leaf classification in sunflower crops by computer vision and neural networks. Computers and Electronics in Agriculture 78(1):9–18
Bai X, Wang B, Yao C, Liu W, Tu Z (2012) Co-transduction for shape retrieval. IEEE Transactions on Image Processing 21(5):2747–2757
Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(4):509–522
Carreira J, Caseiro R, Batista J, Sminchisescu C (2015) Free-form region description with second-order pooling. IEEE Transactions on Pattern Analysis and Machine Intelligence 37(6):1177–1189
Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: Delving deep into convolutional nets. In: Proceedings of the british machine vision conference (BMVC), pp 1–12
Chen X, Wang B (2020) Invariant leaf image recognition with histogram of gaussian convolution vectors. Computers and Electronics in Agriculture 178:105714
Dyrmann M, Karstoft H, Midtiby HS (2016) Plant species classification using deep convolutional neural network. Biosystems Engineering 151:72–80
Engin M, Wang L, Zhou L, Liu X (2018) Deepkspd: Learning kernel-matrix-based spd representation for fine-grained image recognition. In: European conference on computer vision (ECCV), pp 629–645
Gao Y, Beijbom O, Zhang N, Darrell T (2016) Compact bilinear pooling. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 317–326
Gao Z, Xie J, Wang Q, Li P (2019) Global second-order pooling convolutional networks. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 3019–3028
Grinblat GL, Uzal LC, Larese MG, Granitto PM (2016) Deep learning for plant identification using vein morphological patterns. Computers and Electronics in Agriculture 127:418–424
Gupta A, Prakash D (2020) A fast and efficient color model for automatic monitoring of plants based on leaf images. Journal of Critical Reviews 7(17):2398–2404
Haykin S (1998) Neural networks: A comprehensive foundation. Prentice Hall PTR, USA, 2nd edn
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 770–778
He N, Fang L, Li S, Plaza A, Plaza J (2018) Remote sensing scene classification using multilayer stacked covariance pooling. IEEE Transactions on Geoscience and Remote Sensing 56(12):6899–6910
Horaisová K, Kukal J (2016) Leaf classification from binary image via artificial intelligence. Biosystems Engineering 142:83–100
Hu J, Chen Z, Yang M, Zhang R, Cui Y (2018) A multiscale fusion convolutional neural network for plant leaf recognition. IEEE Signal Processing Letters 25(6):853–857
Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-excitation networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 42(8):2011–2023
Hu R, Jia W, Ling H, Huang D (2012) Multiscale distance matrix for fast plant leaf recognition. IEEE Transactions on Image Processing 21(11):4667–4672
Ionescu C, Vantzos O, Sminchisescu C (2015) Matrix backpropagation for deep networks with structured layers. In: IEEE International conference on computer vision (ICCV), pp 2965–2973
Kaya A, Keceli AS, Catal C, Yalic HY, Temucin H, Tekinerdogan B (2019) Analysis of transfer learning for deep neural network based plant classification models. Computers and Electronics in Agriculture 158:20–29
Koniusz P, Tas Y, Porikli F (2017) Domain adaptation by mixture of alignments of second-or higher-order scatter tensors. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 7139–7148
Koniusz P, Yan F, Gosselin P, Mikolajczyk K (2017) Higher-order occurrence pooling for bags-of-words: Visual concept detection. IEEE Transactions on Pattern Analysis and Machine Intelligence 39(2):313–326
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutionalneural networks. Advances in neural information processing systems 25:1097–1105
Laga H, Kurtek S, Srivastava A, Golzarian M, Miklavcic SJ (2012) A riemannian elastic metric for shape-based plant leaf classification. In: International conference on digital image computing techniques and applications (DICTA), pp 1–7
Latecki LJ, Lakamper R, Eckhardt T (2000) Shape descriptors for non-rigid shapes with a single closed contour. Proceedings IEEE conference on computer vision and pattern recognition (CVPR) 1:424–429
Lee SH, Chan CS, Remagnino P (2018) Multi-organ plant classification based on convolutional and recurrent neural networks. IEEE Transactions on Image Processing 27(9):4287–4301
Lee SH, Chan CS, Wilkin P, Remagnino P (2015) Deep-plant: Plant identification with convolutional neural networks. In: IEEE International conference on image processing (ICIP), pp 452–456
Lee SH, Chan CS, Mayo SJ, Remagnino P (2017) How deep learning extracts and learns leaf features for plant classification. Pattern Recognition 71:1–13
Li P, Xie J, Wang Q, Gao Z (2018) Towards faster training of global covariance pooling networks by iterativematrix square root normalization. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 947–955
Lin T, RoyChowdhury A, Maji S (2018) Bilinear convolutional neural networks for fine-grained visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 40(6):1309–1322
Lin TY, Maji S (2017) Improved bilinear pooling with cnns. In: British machinevision conference (BMVC), pp 1–12
Ling H, Jacobs DW (2007) Shape classification using the inner-distance. IEEE Transactions on Pattern Analysis and Machine Intelligence 29(2):286–299
Liu N, Kan J (2016) Improved deep belief networks and multi-feature fusion for leaf identification. Neurocomputing 216:460–467
Mehdipour Ghazi M, Yanikoglu B, Aptoula E (2017) Plant identification using deep neural networks via optimization of transfer learning parameters. Neurocomputing 235:228–235
Novotny P, Suk T (2013) Leaf recognition of woody species in central europe. Biosystems Engineering 115(4):444–452
Raina S, Gupta A (2021) A study on various techniques for plant leaf disease detection using leaf image. In: International conference on artificial intelligence and smart systems (ICAIS), pp 900–905
Sachar S, Kumar A (2021) Survey of feature extraction and classification techniques to identify plant through leaves. Expert Systems with Applications 167:114181
Shah MP, Singha S, Awate SP (2017) Leaf classification using marginalized shape context and shape+texture dual-path deep convolutional neural network. In: IEEE International conference on image processing (ICIP), pp 860–864
Shao Y (2019) Supervised global-locality preserving projection for plant leaf recognition. Computers and Electronics in Agriculture 158:102–108
Sharma S, Gupta A (2020) A review for the automatic methods of plant’s leaf image segmentation. International Journal of Intelligence and Sustainable Computing 1(1):101–114
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations (ICLR), pp 1–14
Soderkvist OJO (2001) Computer vision classifcation of leaves from swedish trees. Master’s thesis, Linkoping University
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 1–9
Trivedi M, Gupta A (2021) Automatic monitoring of the growth of plants using deep learning-based leaf segmentation. International Journal of Applied Science and Engineering 18(2):1–9
Turkoglu M, Hanbay D (2019) Recognition of plant leaves: An approach with hybrid features produced by dividing leaf images into two and four parts. Applied Mathematics and Computation 352:1–14
Tuzel O, Porikli F, Meer P (2006) Region covariance: A fast descriptor for detection and classification. European conference on computer vision (ECCV). Springer, Berlin, pp 589–600
Vedaldi A, Lenc K (2015) Matconvnet convolutional neural networks for matlab. In: Proceedings of the 23rd ACM international conference on multimedia, pp 689–692
Wang B, Gao Y (2014) Hierarchical string cuts: A translation, rotation, scale, and mirror invariant descriptor for fast shape retrieval. IEEE Transactions on Image Processing 23(9):4101–4111
Wang B, Gao Y, Sun C, Blumenstein M, La Salle J (2017) Can walking and measuring along chord bunches better describe leaf shapes? In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 2047–2056
Wang B, Wang D (2019) Plant leaves classification: A few-shot learning method based on siamese network. IEEE Access 7:151754–151763
Wang B, Brown D, Gao Y, Salle JL (2015) March: Multiscale-arch-height description for mobile retrieval of leaf images. Information Sciences 302:132–148
Wang J, Bai X, You X, Liu W, Latecki LJ (2012) Shape matching and classification using height functions. Pattern Recognition Letters 33(2):134–143
Wang X, Du W, Guo F, Hu S (2020) Leaf recognition based on elliptical half gabor and maximum gap local line direction pattern. IEEE Access 8:39175–39183
Wang X, Feng B, Bai X, Liu W, Jan Latecki L (2014) Bag of contour fragments for robust shape classification. Pattern Recognition 47(6):2116–2125
Wang Z, Sun X, Yang Z, Zhang Y, Zhu Y, Ma Y (2018) Leaf recognition based on dpcnn and bow. Neural Processing Letters 47(1):99–115
Wu SG, Bao FS, Xu EY, Wang Y, Chang Y, Xiang Q (2007) A leaf recognition algorithm for plant classification using probabilistic neural network. In: IEEE International symposium on signal processing and information technology, pp 11–16
Yang C (2021) Plant leaf recognition by integrating shape and texture features. Pattern Recognition 112:107809
Yang C, Wei H, Yu Q (2016) Multiscale triangular centroid distance for shape-based plant leaf recognition. In: Proceedings of the twenty-second european conference on artificial intelligence (ECAI), pp 269–276
Yang C, Yu Q (2019) Multiscale fourier descriptor based on triangular features for shape retrieval. Signal Processing: Image Communication 71:110–119
Yousefi E, Baleghi Y, Sakhaei SM (2017) Rotation invariant wavelet descriptors, a new set of features to enhance plant leaves classification. Computers and Electronics in Agriculture 140:70–76
Zeng S, Zhang B, Du Y (2017) Joint distances by sparse representation and locality-constrained dictionary learning for robust leaf recognition. Computers and Electronics in Agriculture 142:563–571
Zhang J, Wang L, Zhou L, Li W (2021) Beyond covariance: Sice and kernel based visual feature representation. International Journal of Computer Vision 129(2):300–320
Zhang S, Huang W, an Huang Y, Zhang C (2020) Plant species recognition methods using leaf image: Overview. Neurocomputing 408:246–272
Zhang S, Lei Y, Zhang C, Hu Y (2016) Semi-supervised orthogonal discriminant projection for plant leaf classification. Pattern Analysis and Applications 19:953–961
Zhang S, Zhang C, Wang X (2020) Plant species recognition based on global-local maximum margin discriminant projection. Knowledge-Based Systems 200:105998
Zhang X, Zhao W, Luo H, Chen L, Peng J, Fan J (2019) Plant recognition via leaf shape and margin features. Multimedia Tools and Applications 78(19):27463–27489
Zhao C, Chan SS, Cham WK, Chu L (2015) Plant identification using leaf shapes - a pattern counting approach. Pattern Recognition 48(10):3203–3215
Zhou J, Qi H, Chen Y, Wang H (2021) Progressive principle component analysis for compressing deep convolutional neural networks. Neurocomputing 440:197–206
Funding
The work described in this paper was partially supported by the National Natural Science Foundation of China (Grant No. 62101376), Science and Technology Innovation Foundation Project of Shanxi Agricultural University (Grant Number 2018021), Natural Science Foundation of Shanxi Province of China (Grant No. 201901D211078), Scientific and Technologial Innovation Programs of Higher Education Institutions in Shanxi (Grant No. 2019L0350).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
We declare that there have no conflicts of interest to this work.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Feng, S. Kernel pooling feature representation of pre-trained convolutional neural networks for leaf recognition. Multimed Tools Appl 81, 4255–4282 (2022). https://doi.org/10.1007/s11042-021-11769-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-021-11769-0