Experimental study of the rotation profile based binary shape descriptor

This paper presents the results of an experimental study of a shape descriptor based on a Rotation Profile for tasks of leaf classification. The descriptor is a sequence of values obtained by rotating the shape around itself with a fixed angular step within the range of 0 to 180 degrees. For each rotation angle, the Jaccard measure, reflecting the similarity between the original and rotated shapes, is calculated. The proposed descriptor is invariant to similarity transformations, ensuring its effectiveness in analyzing objects with varying shapes. Experiments were conducted on four classification tasks using three types of classifiers: Support Vector Machine (SVM), Gradient Boosting (XGBoost), and a simple neural network (NN Simple). The descriptor’s performance was compared with traditional approaches, including Zernike moments, geometric moments, and Hu moments. Additionally, recognition was performed directly on raster images using convolutional neural networks (ResNet50, VGG16, CNN Simple). The results demonstrated high accuracy and stability of the proposed shape descriptor across different classification contexts and confirmed its strong potential for shape analysis tasks in computer vision.

1. Zhang D., Lu G. Shape-Based Image Retrieval Using Generic Fourier Descriptor. Signal Processing: Image Communication. 2002;17(10):825–848. https://doi.org/10.1016/S0923-5965(02)00084-X

2. Kuhl F.P., Giardina Ch.R. Elliptic Fourier Features of a Closed Contour. Computer Graphics and Image Processing. 1982;18(3):236–258. https://doi.org/10.1016/0146-664X(82)90034-X

3. Dudek G., Tsotsos J.K. Shape Representation and Recognition from Multiscale Curvature. Computer Vision and Image Understanding. 1997;68(2):170–189. https://doi.org/10.1006/cviu.1997.0533

4. Zhang D., Lu G. A Comparative Study of Three Region Shape Descriptors. In: DICTA2002: Digital Image Computing Techniques and Applications, 21–22 January 2002, Melbourne, Australia. 2002. P. 86–91.

5. Li E., Li H. Reflection Invariant and Symmetry Detection. arXiv. URL: https://arxiv.org/abs/1705.10768 [Accessed 21st May 2025].

6. Seredin O., Lomov N., Liakhov D., et al. Rotation Profile-Based Binary Shape Descriptor. The Visual Computer. 2025;41:8911–8933. https://doi.org/10.1007/s00371-025-03906-9

7. Qi Sh., Zhang Yu., Wang Ch., Zhou J., Cao X. A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation. ACM Computing Surveys. 2021;55(1). https://doi.org/10.1145/3479428

8. Xiao B., Ma J.-F., Wang X. Image Analysis by Bessel-Fourier Moments. Pattern Recognition. 2010;43(8):2620–2629. https://doi.org/10.1016/j.patcog.2010.03.013

9. Teague M.R. Image Analysis via the General Theory of Moments. Journal of the Optical Society of America. 1980;70(8):920–930. https://doi.org/10.1364/JOSA.70.000920

10. Bedratyuk L. On Complete System of Invariants for the Binary Form of Degree 7. arXiv. URL: https://arxiv.org/abs/math/0611122 [Accessed 21st May 2025].

11. Rogov A.A., Bystrov M.Yu. Strukturnoe raspoznavanie binarnykh izobrazhenii s ispol'zovaniem skeletov. Matematicheskie metody raspoznavaniya obrazov. 2011;15(1):420–423. (In Russ.).

12. Kervadec H., Bahig H., Létourneau-Guillon L., Dolz J., Ayed I.B. Beyond Pixel-Wise Supervision for Segmentation: A Few Global Shape Descriptors Might Be Surprisingly Good! In: Medical Imaging with Deep Learning, 07–09 July 2021, Lübeck, Germany. PMLR; 2021. P. 354–368.

13. Jaccard P. Étude comparative de la distribution florale dans une portion des Alpes et du Jura. Bulletin de la Société Vaudoise des Sciences Naturelles. 1901;37(142):547–579. https://doi.org/10.5169/seals-266450

14. Seredin O., Liakhov D., Kushnir O., Lomov N. Jaccard Index-Based Detection of Order 2 Rotational Quasi-Symmetry Focus for Binary Images. Pattern Recognition and Image Analysis. 2022;32(3):672–681. https://doi.org/10.1134/S1054661822030403

15. Lomov N., Seredin O., Kushnir O., Liakhov D. Search for Rotational Symmetry of Binary Images via Radon Transform and Fourier Analysis. In: Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications: Volume 4, 19–21 February 2023, Lisbon, Portugal. SCITEPRESS; 2023. P. 280–289. https://doi.org/10.5220/0011679900003417

16. Bradski G. The OpenCV Library. Dr. Dobb's Journal: Software Tools for the Professional Programmer. 2000;25(11):120–123.

17. Coelho L.P. Mahotas: Open Source Software for Scriptable Computer Vision. arXiv. URL: https://arxiv.org/abs/1211.4907 [Accessed 21st May 2025].

18. Chen T., Guestrin C. XGBoost: A Scalable Tree Boosting System. In: KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 13–17 August 2016, San Francisco, CA, USA. New York: Association for Computing Machinery; 2016. P. 785–794. https://doi.org/10.1145/2939672.2939785

19. Senin A.N., Tiras K.P., Mestetskiy L.M. Shape Feature Generation for Bioindication Using Leaf Images. Ecology. Economy. Informatics. System Analysis and Mathematical Modeling of Ecological and Economic Systems. 2022;1(7):66–75. (In Russ.). https://doi.org/10.23885/2500-395X-2022-1-7-66-75

20. Liakhov D.V., Mityugov N.S., Gracheva I.A., Kopylov A.V., Seredin O.S., Tiras Kh.P. Scanned Plant Leaves Boundary Detection in the Presence of a Colored Shadow. Pattern Recognition and Image Analysis. 2022;32(3):575–585. https://doi.org/10.1134/S1054661822030221

21. Sitarz M. Extending F1 Metric, Probabilistic Approach. Advances in Artificial Intelligence and Machine Learning. 2023;3(2):1025–1038. https://doi.org/10.54364/aaiml.2023.1161

22. Sitarz M. Extending F1 Metric, Probabilistic Approach. arXiv. URL: https://arxiv.org/abs/2210.11997 [Accessed 21st May 2025].

23. Seredin O.S., Kopylov A.V. Harmonic Averaging in Classifier Quality Assessment. Pattern Recognition and Image Analysis. 2024;34(4):1160–1171. https://doi.org/10.1134/S1054661824701220

24. Wu S.G., Bao F.Sh., Xu E.Y., Wang Yu-X., Chang Y.-F., Xiang Q.-L. A Leaf Recognition Algorithm for Plant Classification Using Probabilistic Neural Network. In: 2007 IEEE International Symposium on Signal Processing and Information Technology, 15–18 December 2007, Giza, Egypt. IEEE; 2007. P. 11–16. https://doi.org/10.1109/ISSPIT.2007.4458016

25. Meyer M., Spruyt J. BEN: Using Confidence-Guided Matting for Dichotomous Image Segmentation. arXiv. URL: https://arxiv.org/abs/2501.06230 [Accessed 21st May 2025].