Abstract
Many features of leaves, including color, texture, and shape, are used in automated leaf recognition models. The curvature of a leaf is one of the least studied characteristics. This is primarily due to the fact that curvature is not an invariant feature and can fluctuate significantly in a single leaf in its many peripheral positions. The second reason is that if one considers curvature in a pixel-by-pixel manner, it seems entirely inappropriate as a single representative feature. In this study, we focused mostly on curvature and talked about how curvature might be used as a distinguishing feature for identifying leaves. We have provided a step-by-step method for dealing with curvature, starting with the fundamentals like the average curvature of a leaf and working our way up to a fine tuned representation that may be used as a significant feature. To determine whether the new feature is appropriate, we added it to the existing feature sets and fed the data to various standard classification models. The findings show a noticeable improvement in accuracy, demonstrating the usefulness of curvature as a feature.
Similar content being viewed by others
Data availibility
Enquiries about data availability should be directed to the authors.
References
Bao T, Kiet N, Truong Q-D, Huynh H (2019) Plant species identification from leaf patterns using histogram of oriented gradients feature space and convolution neural networks. J Inf Telecommun 4:1–11
di Huang C, Shan MA, Chen L (2011) Local binary patterns and its application to facial image analysis: a survey. IEEE Trans Syst Man Cybern Part C 41:765–781
Fawcett T (2006) An introduction to roc analysis. Pattern Recognit Lett 27(8):861–874
Gedraite ES, Murielle H (2011) Investigation on the effect of a gaussian blur in image filtering and segmentation. Proceedings ELMAR-2011. Springer, Cham, pp 393–396
Hossain J, Amin M (2010) Leaf shape identification based plant biometrics. In: Proceedings of 2010 13th International Conference on Computer and Information Technology, ICCIT 2010, p 12
Hsiao J-K, Li-Wei K, Ching-Long C, Chih-Yang L (2014) Comparative study of leaf image recognition with a novel learning-based approach. Science and information conference. Springer, Cham, pp 389–393
Lavania S, Matey PS (2015) Leaf recognition using contour based edge detection and sift algorithm. In: 2014 IEEE International Conference on Computational Intelligence and Computing Research, IEEE ICCIC 2014, p 09
Nguyen Q-K, Thi-Lan L, Ngoc-Hai P (2013) Leaf based plant identification system for android using surf features in combination with bag of words model and supervised learning. International conference on advanced technologies for communications (ATC 2013). Springer, Cham, pp 404–407
Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans Pattern Anal Mach Intell 24(7):971–987
Prasad S, Kumar PS, Debashis G (2013) Mobile plant species classification: a low computational aproach. IEEE Second Int Conf Image Inf Process 12:405–409
Priya AC, Balasaravanan T, Thanamani AS (2012) An efficient leaf recognition algorithm for plant classification using support vector machine. International conference on pattern recognition, informatics and medical engineering (PRIME-2012). Springer, Cham, pp 428–432
Ren X-M, Xiao-Feng W, Yang Z (2012) An efficient multi-scale overlapped block IBP approach for leaf image recognition. In: De-Shuang H, Jianhua M, Kang-Hyun J, Mchael MG (eds) Intelligent computing theories and applications. Springer, Berlin, pp 237–243
Siravenha A, Carvalho S (2016) Plant classification from leaf textures. In: Proceedings of the 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp. 1-8, Gold Coast, Australia, November 2016
Wäldchen J, Mäder P (2018) Plant species identification using computer vision techniques: a systematic literature review. Arch Comput Methods Eng 25:507–543
Wu GS, Sheng BF, You XE, Yu-Xuan W, Yi-Fan C, Qiao-Liang X (2007) A leaf recognition algorithm for plant classification using probabilistic neural network. IEEE Int Symp Signal Process Inf Technol. https://doi.org/10.1109/ISSPIT.2007.4458016
Funding
The authors have not disclosed any funding.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have not disclosed any competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ghosh, A., Roy, P. & Dutta, P. Suitability of curvature as a feature for image-based pattern recognition: a case study on leaf image classification based on machine learning. Soft Comput 28, 5709–5720 (2024). https://doi.org/10.1007/s00500-023-09366-4
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-023-09366-4