Hardware Implementation of the GVF Approach for Deformable Contour Detection on FPGA
Received: 13 September 2025 | Revised: 13 October 2025 | Accepted: 19 October 2025 | Online: 8 December 2025
Corresponding author: Mohamed Lamine Hamidatou
Abstract
Active contours, or snakes, are widely used in medical image segmentation due to their ability to accurately delineate object boundaries. The Gradient Vector Flow (GVF) model enhances traditional snakes by improving convergence and effectively capturing concave shapes. This paper presents a hardware implementation of the GVF algorithm on a PYNQ-Z2 FPGA using a modular architecture designed to optimize computation and parallelism. The algorithm was first developed and validated in MATLAB to evaluate its accuracy and stability on medical images. This step enabled fine-tuning of key GVF parameters, such as the regularization coefficient and the number of iterations, to ensure reliable convergence and precise contour segmentation. It was then implemented in Vivado HLS and translated into an optimized hardware architecture that leverages FPGA parallelism and pipelining to minimize latency and enhance performance. Experimental results demonstrate real-time operation, high segmentation accuracy, and low latency, confirming the suitability of this approach for embedded medical imaging applications requiring both speed and precision.
Keywords:
medical image segmentation, snakes, Gradient Vector Flow (GVF), FPGA, MATLAB simulationDownloads
References
C. Beitone, C. Tilmant, and F. Chausse, "Fully Automatic Deformable Model Integrating Edge, Texture and Shape - Application to Cardiac Images Segmentation," in 10th International Conference on Computer Vision Theory and Applications, Berlin, Germany, 2025, pp. 517–522. DOI: https://doi.org/10.5220/0005304005170522
C. Xu and J. L. Prince, "Gradient vector flow: a new external force for snakes," in Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Juan, PR, USA, 1997, pp. 66–71.
C. Xu and J. L. Prince, "Snakes, shapes, and gradient vector flow," IEEE Transactions on Image Processing, vol. 7, no. 3, pp. 359–369, Mar. 1998. DOI: https://doi.org/10.1109/83.661186
J. Canny, "A Computational Approach to Edge Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI-8, no. 6, pp. 679–698, Nov. 1986. DOI: https://doi.org/10.1109/TPAMI.1986.4767851
W. Guoqiang and W. Dongxue, "Segmentation of Brain MRI Image with GVF Snake Model," in 2010 First International Conference on Pervasive Computing, Signal Processing and Applications, Harbin, China, 2010, pp. 711–714. DOI: https://doi.org/10.1109/PCSPA.2010.177
C. Xu and J. L. Prince, "Generalized gradient vector flow external forces for active contours1," Signal Processing, vol. 71, no. 2, pp. 131–139, Dec. 1998. DOI: https://doi.org/10.1016/S0165-1684(98)00140-6
P. Perona and J. Malik, "Scale-space and edge detection using anisotropic diffusion," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, no. 7, pp. 629–639, July 1990. DOI: https://doi.org/10.1109/34.56205
Xilinx, "PYNQ: Python productivity for Zynq." PYNQ. http://www.pynq.io/.
Xilinx, Zynq 7000 SoC Technical Reference Manual (UG585), (2023). [Online]. Available: https://docs.amd.com/r/en-US/ug585-zynq-7000-SoC-TRM/Quad-SPI-Controller.
Xilinx, Vitis High-Level Synthesis User Guide (UG1399), (2025). [Online]. Available: https://docs.amd.com/r/en-US/ug1399-vitis-hls.
Xilinx, Vivado Design Suite User Guide: Getting Started (UG910), (2025). [Online]. Available: https://docs.amd.com/r/en-US/ug910-vivado-getting-started/Design-Hubs.
A. Alhomoud et al., "Model-based Design of a High-Throughput Canny Edge Detection Accelerator on Zynq-7000 FPGA," Engineering, Technology & Applied Science Research, vol. 14, no. 2, pp. 13547–13553, Apr. 2024. DOI: https://doi.org/10.48084/etasr.7081
Xilinx, Vivado Design Suite User Guide: Power Analysis and Optimization (UG907), (2025). Accessed: Oct. 30, 2025. [Online]. Available: https://docs.amd.com/r/en-US/ug907-vivado-power-analysis-optimization.
F. Z. Hamadi, M. L. Hamidatou, L. Hamami-Mitiche, S. A. Belkacem, and B. Bouzid, "MATLAB Simulation, and FPGA Implementation of the DRLSE Segmentation Algorithm," Traitement du Signal, vol. 42, no. 2, pp. 719–727, Apr. 2025. DOI: https://doi.org/10.18280/ts.420210
Downloads
How to Cite
License
Copyright (c) 2025 Mohamed Lamine Hamidatou, Fatma Zohra Hamadi, Latifa Hamami, Bouchra Bouzid, Sabrina Ait Belkacem, Fatima Zohra Allam
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
