International Journal of Information Technology and Computer Science (IJITCS)
IJITCS Vol. 18, No. 2, 8 Apr. 2026
Cover page and Table of Contents: PDF (size: 1251KB)
A Study of Using Convolutional Neural Networks in Fractal Dimension Estimation of Grayscale and Color Images
PDF (1251KB), PP.1-18
Views: 0 Downloads: 0
Author(s)
Moheb R. Girgis
1,*
Al Hussien Seddik Saad
1
Mohammed M. Talaat
1
Index Terms
Fractal Dimension, Box-Counting, Differential Box-Counting, Deep Learning, Convolutional Neural Networks
Abstract
Fractal dimension (FD) estimation is widely used to characterize image complexity and self-similarity in image analysis and texture characterization. Traditional FD estimators such as Box-Counting (BC) and Differential Box-Counting (DBC) are simple and efficient but can be sensitive to scale selection, resolution, and noise. This paper investigates the effectiveness of using convolutional neural network (CNN) in FD estimation compared to traditional methods. To this end, we have developed a CNN-based method for FD estimation under a fair and reproducible evaluation design. First, we have included an analytic-fractals benchmark (such as Sierpinski and Koch families) with closed-form FD values for independent evaluation. Second, for large-scale Julia/Mandelbrot images, FD labels are treated as reference estimates computed from multiple BC/DBC parameter settings and reported as mean ± standard deviation to quantify label uncertainty. We additionally assess behavior on an external natural-texture dataset and evaluate robustness under controlled degradations (noise, blur, compression, and downsampling). Performance is reported on large test sets using MAE/RMSE with 95% confidence intervals (bootstrap), together with per-image inference time under clearly specified hardware settings. Results indicate that the proposed CNN-based method provides stable FD estimation and fast inference, particularly under noise and resolution variations.
Cite This Paper
Moheb R. Girgis, Al Hussien Seddik Saad, Mohammed M. Talaat, "A Study of Using Convolutional Neural Networks in Fractal Dimension Estimation of Grayscale and Color Images", International Journal of Information Technology and Computer Science(IJITCS), Vol.18, No.2, pp.1-18, 2026. DOI:10.5815/ijitcs.2026.02.01
Reference
[1]B. B. Mandelbrot, The Fractal Geometry of Nature, 3rd ed., New York, NY, USA: W. H. Freeman, 1983.
[2]H. O. Peitgen, H. Jürgens, and D. Saupe, Chaos and Fractals: New Frontiers of Science, 2nd ed., Springer, 2004.
[3]O. S. Al-Kadi, “Fractals for biomedical texture analysis,” in Biomedical Texture Analysis, A. Depeursinge, O. S. Al-Kadi, and J. R. Mitchell, Eds., Academic Press, 2017, pp. 131–161.
[4]R. Lopes and N. Betrouni, “Fractal and multifractal analysis: A review,” Medical Image Analysis, vol. 13, no. 4, pp. 634–649, 2009.
[5]N. Sarkar and B. B. Chaudhuri, “An efficient differential box-counting approach to compute fractal dimension of image,” IEEE Trans. Syst., Man, Cybern., vol. 24, no. 1, pp. 115–120, Jan. 1994, doi: 10.1109/21.259692.
[6]P. Maragos and F. K. Sun, “Measuring the fractal dimension of signals: Morphological covers and iterative optimization,” IEEE Trans. Signal Process., vol. 41, no. 1, pp. 108–121, Jan. 1993, doi: 10.1109/TSP.1993.193131.
[7]K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in Proc. Int. Conf. Learn. Representations (ICLR), 2015.
[8]Y. Liu, L. Chen, H. Wang, L. Jiang, Y. Zhang, J. Zhao, D. Wang, Y. Zhao, and Y. Song, “An improved differential box-counting method to estimate fractal dimensions of gray-level images,” J. Vis. Commun. Image Represent., vol. 25, no. 7, pp. 1102–1111, 2014.
[9]Y. Li, “Fractal dimension estimation for color texture images,” J. Math. Imaging Vis., vol. 62, pp. 37–53, 2020.
[10]R. Padhy, S. K. Dash, A. Khandual, and J. Mishra, “Image classification in artificial neural network using fractal dimension,” Int. J. Inf. Technol., vol. 15, no. 6, pp. 3003–3013, 2023.
[11]H. Xu, J. Yan, N. Persson, W. Lin, and H. Zha, “Fractal dimension invariant filtering and its CNN-based implementation,” arXiv preprint, arXiv:1603.06036, 2016.
[12]D. Valle, A. Wagemakers, A. Daza, and M. A. F. Sanjuán, “Characterization of fractal basins using deep convolutional neural networks,” arXiv preprint, arXiv:2501.17603, 2025. [Online]. Available: https://arxiv.org/abs/2501.17603
[13]S. Wang, Z. Chen, F. Qi, C. Xu, C. Wang, T. Chen, and H. Guo, “Fractal geometry and convolutional neural networks for the characterization of thermal shock resistances of ultra-high temperature ceramics,” Fractal Fract., vol. 6, no. 11, Art. no. 605, 2022.
[14]G. Zhou, X. Wang, F. Feng, P. Feng, and M. Zhang, “Calculation of fractal dimension based on artificial neural network and its application for machined surfaces,” Fractals, vol. 29, no. 6, 2021.
[15]B. B. Chaudhuri and N. Sarkar, “Texture segmentation using fractal dimension,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 17, no. 1, pp. 72–77, Jan. 1995, doi: 10.1109/34.368149.
[16]H. O. Peitgen, H. Jürgens, and D. Saupe, “Length, area and dimension: measuring complexity and scaling properties,” in Chaos and Fractals: New Frontiers of Science, Springer, 1992, pp. 183–228.
[17]M. Cimpoi, S. Maji, I. Kokkinos, S. Mohamed, and A. Vedaldi, “Describing textures in the wild,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2014, pp. 3606–3613.
[18]D. Hendrycks and T. Dietterich, “Benchmarking neural network robustness to common corruptions and perturbations,” in Proc. Int. Conf. Learn. Representations (ICLR), 2019.
[19] N. Otsu, “A threshold selection method from gray-level histograms,” IEEE Trans. Syst., Man, Cybern., vol. 9, no. 1, pp. 62–66, Jan. 1979, doi: 10.1109/TSMC.1979.4310076.
[20]Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. Chapter 6: Deep Feedforward Networks.
[21]G. F. Roberto, A. Lumini, L. A. Neves, and M. Z. do Nascimento, “Fractal neural network: A new ensemble of fractal geometry and convolutional neural networks for the classification of histology images,” Expert Syst. Appl., vol. 166, Art. no. 114103, pp. 1–11, 2021.