Assessment of Deep Learning Models for Image Edge Detection

  • Authors

    • Wazir Research Scholar, Department of Electronics & Communication Engineering, Deenbandhu Chhotu Ram University of Science & ‎Technology, Murthal, Haryana (India)-131039 https://orcid.org/0009-0007-5415-7424
    • Rajeshwar Dass Associate Professor, Department of Electronics & Communication Engineering, Deenbandhu Chhotu Ram University of Science & Tech-‎nology, Murthal, Haryana (India)-131039
    https://doi.org/10.14419/zgt6cp83

    Received date: June 24, 2025

    Accepted date: August 23, 2025

    Published date: September 1, 2025

  • Unet; ResNet50-Unet; BSDS500 & BIPED Datasets; Edge Detection; Encoder-

  • Abstract

    Edge detection is a crucial technique in image processing, essential for various applications, including feature extraction, object identification, and segmentation. Conventional methods, such as Sobel and Canny filters, are not suitable for complex image structures and different lighting conditions in the image. Deep learning-based edge detection algorithms perform better in these situations and become an essential component of edge detection. ‎

    This study presented a deep learning-based approach for detecting edges in objects and complex backgrounds using the U-Net and its variants. This study used the BSDS500 dataset to compare eight deep learning-based edge detection algorithms for object and background out-‎lines. The testing outcomes show that the residual structure based on Resnet50-Unet outperformed in detecting the outlines of objects and backgrounds, achieving 95% accuracy, 0.62 precision, 0.89 recall, and 0.71 F1 score without augmentation of the BSDS500 dataset. ‎The performance of Resnet50-Unet is enhanced when the augmented BSDS500 dataset is utilised, and it achieved 97% accuracy, 0.72 precision, 0.98 recall, and 0.83 F1 score. The results obtained are also cross-validated using the BIPED dataset. The proposed algorithm efficiently detects edges and object boundaries in real time.

  • References

    1. N. S. Dagar and P. K. Dahiya, "Edge detection technique using binary particle swarm optimization," Procedia Computer Science, vol. 167, pp. 1421–1436, 2020. https://doi.org/10.1016/j.procs.2020.03.353.
    2. N. S. Dagar and P. K. Dahiya, "A comparative investigation into edge detection techniques based on computational intelligence," Int. J. Image, Graphics and Signal Processing, no. 7, pp. 58–68, 2019. https://doi.org/10.5815/ijigsp.2019.07.05.
    3. R. Maskeliunas, R. Damaševičius, D. Vitkute-Adzgauskiene, and S. Misra, "Pareto optimized large mask approach for efficient and background hu-manoid shape removal," IEEE Access, vol. 11, pp. 33900–33914, 2023. https://doi.org/10.1109/ACCESS.2023.3253206.
    4. Y. Zhao, W. Gui, and Z. Chen, "Edge detection based on multi-structure elements morphology," in Proc. 6th World Congr. Intell. Control Autom., vol. 2, pp. 9795–9798, Jun. 2006. https://doi.org/10.1109/WCICA.2006.1713908.
    5. G. M. H. Amer and A. M. Abushaala, "Edge detection methods," in Proc. 2nd World Symp. Web Appl. Netw. (WSWAN), pp. 1–7, Mar. 2015. https://doi.org/10.1109/WSWAN.2015.7210349.
    6. B. Chander, K. Guravaiah, B. Anoop, and G. Kumaravelan, Eds., Handbook of AI-Based Models in Healthcare and Medicine: Approaches, Theo-ries, and Applications. Boca Raton, FL, USA: CRC Press, 2024. https://doi.org/10.1201/9781003363361.
    7. V. M. Dharampal, "Methods of image edge detection: A review," J. Electr. Electron. Syst., vol. 4, no. 2, pp. 2332–0796, 2015.
    8. R. Sun, T. Lei, Q. Chen, Z. Wang, X. Du, W. Zhao, and A. K. Nandi, "Survey of image edge detection," Frontiers in Signal Processing, vol. 2, p. 826967, 2022. https://doi.org/10.3389/frsip.2022.826967.
    9. N. M. Sáez-Gallego, Y. Segovia, and J. Abellán, "Codesigning a motor story for promoting inclusion and critical thinking in pre-service teachers: A participatory action research approach in physical education," J. Teaching Phys. Educ., vol. 1, no. aop, pp. 1–12, 2024. https://doi.org/10.1123/jtpe.2023-0337.
    10. Y. Lijun, L. Mengbo, W. Tongxin, B. Youfeng, L. Junhui, and J. Yi, "Geo-information mapping improves Canny edge detection method," IET Image Processing, vol. 17, no. 6, pp. 1893–1904, 2023. https://doi.org/10.1049/ipr2.12764.
    11. J. Huang, B. Bai, and F. Yang, “An effective salient edge detection method based on point flow with phase congruency,” Signal, Image and Video Processing, vol. 16, no. 4, pp. 1019–1026, 2022. https://doi.org/10.1007/s11760-021-02048-4.
    12. Z. Wu, X. Lu, and Y. Deng, “Image edge detection based on local dimension: A complex networks approach,” Physica A: Statistical Mechanics and its Applications, vol. 440, pp. 9–18, 2015. https://doi.org/10.1016/j.physa.2015.07.020.
    13. Z. Lv, Z. Lu, K. Xia, L. Zhang, H. Zuo, Y. Xu, and K. Liu, “Real-time detection system for polishing metal surface defects based on convolutional feature concentration and activation network,” Expert Systems with Applications, vol. 257, 125041, 2024. https://doi.org/10.1016/j.eswa.2024.125041.
    14. N. S. Patil and E. Kannan, “An efficient corn leaf disease prediction using Adaptive Color Edge Segmentation with Resnext101 model,” Journal of the Saudi Society of Agricultural Sciences, 2024.
    15. C. Wen, P. Liu, W. Ma, Z. Jian, C. Lv, J. Hong, and X. Shi, “Edge detection with feature re-extraction deep convolutional neural network,” Jour-nal of Visual Communication and Image Representation, vol. 57, pp. 84–90, 2018. https://doi.org/10.1016/j.jvcir.2018.10.017.
    16. N. Xue, T. Wu, S. Bai, F. Wang, G. S. Xia, L. Zhang, and P. H. Torr, “Holistically-attracted wireframe parsing,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pp. 2788–2797, 2020. https://doi.org/10.1109/CVPR42600.2020.00286.
    17. X. S. Poma, E. Riba, and A. Sappa, “Dense extreme inception network: Towards a robust CNN model for edge detection,” in Proc. IEEE/CVF Winter Conf. Appl. Comput. Vis., pp. 1923–1932, 2020.
    18. R. Deng and S. Liu, “Deep structural contour detection,” in Proc. 28th ACM Int. Conf. Multimedia, pp. 304–312, Oct. 2020. https://doi.org/10.1145/3394171.3413750.
    19. M. Zhen, J. Wang, L. Zhou, S. Li, T. Shen, J. Shang, … and L. Quan, “Joint semantic segmentation and boundary detection using iterative pyramid contexts,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., pp. 13666–13675, 2020. https://doi.org/10.1109/CVPR42600.2020.01368.
    20. F. Orujov, R. Maskeliūnas, R. Damaševičius, and W. Wei, “Fuzzy based image edge detection algorithm for blood vessel detection in retinal imag-es,” Applied Soft Computing, vol. 94, 106452, 2020. https://doi.org/10.1016/j.asoc.2020.106452.
    21. Y. Liu, Z. Xie, and H. Liu, "An adaptive and robust edge detection method based on edge proportion statistics," IEEE Transactions on Image Pro-cessing, vol. 29, pp. 5206–5215, 2020. https://doi.org/10.1109/TIP.2020.2980170.
    22. X. Yu, Z. Wang, Y. Wang, and C. Zhang, "Edge detection of agricultural products based on morphologically improved canny algorithm," Mathe-matical Problems in Engineering, vol. 2021, no. 1, p. 6664970, 2021. https://doi.org/10.1155/2021/6664970.
    23. M. Versaci and F. C. Morabito, "Image edge detection: A new approach based on fuzzy entropy and fuzzy divergence," International Journal of Fuzzy Systems, vol. 23, no. 4, pp. 918–936, 2021. https://doi.org/10.1007/s40815-020-01030-5.
    24. H. Zhao, B. Wu, Y. Guo, G. Chen, and D. Ye, "SSWS: An edge detection algorithm with strong semantics and high detectability for spacecraft," Optik, vol. 247, p. 168037, 2021. https://doi.org/10.1016/j.ijleo.2021.168037.
    25. Z. Su, W. Liu, Z. Yu, D. Hu, Q. Liao, Q. Tian, et al., "Pixel difference networks for efficient edge detection," in Proc. IEEE/CVF Int. Conf. Com-puter Vision (ICCV), pp. 5117–5127, 2021. https://doi.org/10.1109/ICCV48922.2021.00507.
    26. O. Elharrouss, Y. Akbari, S. Al-Maadeed, and A. Bouridane, "Edge detection with multi-scale representation and refined network," in IET Conf. Proc. CP816, vol. 2022, no. 14, pp. 247–251, Oct. 2022. https://doi.org/10.1049/icp.2022.2465.
    27. F. Wang and M. Zhang, "Deep learning-based edge detection algorithm for noisy images," in Proc. 2023 6th Int. Conf. Artificial Intelligence and Pattern Recognition (AIPR), pp. 465–472, Sept. 2023. https://doi.org/10.1145/3641584.3641653.
    28. O. Elharrouss, Y. Hmamouche, A. K. Idrissi, B. El Khamlichi, and A. El Fallah-Seghrouchni, "Refined edge detection with cascaded and high-resolution convolutional network," Pattern Recognition, vol. 138, p. 109361, 2023. https://doi.org/10.1016/j.patcog.2023.109361.
    29. D. Jing, B. Li, S. Wang, J. Lin, and Y. Jiao, "Edge detection in dark industrial environments," in Proc. 2023 9th Int. Conf. Computer and Commu-nications (ICCC), pp. 1689–1693, Dec. 2023. https://doi.org/10.1109/ICCC59590.2023.10507668.
    30. A. Al-Amaren, M. O. Ahmad, and M. N. S. Swamy, "A low-complexity residual deep neural network for image edge detection," Applied Intelli-gence, vol. 53, no. 9, pp. 11282–11299, 2023. https://doi.org/10.1007/s10489-022-04062-6.
    31. F. Li and C. Lin, “UHNet: An ultra-lightweight and high-speed edge detection network,” arXiv preprint arXiv:2408.04258, 2024.
    32. J. Zhang, W. Wang, and J. Wang, “Edge detection in colored images using parallel CNNs and social spider optimization,” Electronics, vol. 13, no. 17, p. 3540, 2024. https://doi.org/10.3390/electronics13173540.
    33. F. Abedi, “Dense residual network for image edge detection,” Multimedia Tools and Applications, vol. 83, no. 42, pp. 90227–90242, 2024. https://doi.org/10.1007/s11042-024-19264-y.
    34. Y. An, J. Jing, X. Li, J. Zhang, and J. Bao, “An exclusive U-net for fine and crisp edge detection,” Multimedia Tools and Applications, vol. 83, no. 18, pp. 54657–54672, 2024. https://doi.org/10.1007/s11042-023-17706-7.
    35. K. Muntarina, R. Mostafiz, S. B. Shorif, and M. S. Uddin, “Deep learning-based edge detection for random natural images,” Neuroscience Infor-matics, vol. 5, no. 1, p. 100183, 2025. https://doi.org/10.1016/j.neuri.2024.100183.
    36. M. Wang, “AttnEdge: An enhanced edge detection method based on self-attention mechanism,” in Proc. 4th Int. Conf. Computer Vision, Applica-tion, and Algorithm (CVAA), vol. 13486, pp. 438–446, Jan. 2025. https://doi.org/10.1117/12.3055875.
    37. W. Li, W. Zhang, Y. Liu, C. Liu, and R. Jing, “Pixel-patch combination loss for refined edge detection,” International Journal of Machine Learning and Cybernetics, pp. 1–14, 2024.
    38. X. Chen, W. Yang, W. Wu, X. Tao, and X. Mao, “Sufficient learning: Mining denser high-quality pixel-level labels for edge detection,” Neural Computing and Applications, pp. 1–16, 2025. https://doi.org/10.1007/s00521-024-10661-w.
    39. X. Yang, L. Cheng, G. Yuan, and H. Wu, “Textureness-aware neural network for edge detection,” in Chinese Conf. Pattern Recognition and Com-puter Vision (PRCV), Singapore: Springer, pp. 254–268, Oct. 2024. https://doi.org/10.1007/978-981-97-8505-6_18.
    40. H. Shu, “More precise edge detections,” arXiv preprint arXiv:2407.19992, 2024.
    41. N. Yadav, R. Dass, and J. Virmani, "Assessment of encoder-decoder based segmentation models for thyroid ultrasound images," Medical & Biological Engineering & Computing, vol. 61, pp. 2159–2195, 2023, https://doi.org/10.1007/s11517-023-02849-4.
    42. N. Yadav, R. Dass, and J. Virmani, "Objective assessment of segmentation models for thyroid ultrasound images," Journal of Ultrasound, vol. 26, pp. 673–685, Oct. 2022, https://doi.org/10.1007/s40477-022-00726-8.
    43. N. Yadav, R. Dass, and J. Virmani, "A systematic review of machine learning based thyroid tumor characterisation using ultrasonographic images," Journal of Ultrasound, vol. 27, pp. 209–224, 2024, https://doi.org/10.1007/s40477-023-00850-z.
    44. R. Dass, Priyanka, and S. Devi, "Image segmentation techniques," International Journal of Electrical Communication Technology, vol. 3, no. 1, pp. 1–5, 2012.
    45. O. Ronneberger, P. Fischer, and T. Brox, "U-Net: Convolutional networks for biomedical image segmentation," in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, N. Navab, J. Hornegger, W. Wells, and A. Frangi, Eds. Cham: Springer, 2015, Lecture Notes in Computer Science, vol. 9351, pp. 234–241, https://doi.org/10.1007/978-3-319-24574-4_28.
    46. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, Jun. 2016, pp. 770–778, https://doi.org/10.1109/CVPR.2016.90.
    47. N. Yadav, R. Dass, and J. Virmani, "Deep learning-based CAD system design for thyroid tumor characterization using ultrasound images," Multi-media Tools and Applications*, vol. 83, no. 4, Oct. 2023. https://doi.org/10.1007/s11042-023-17137-4.
    48. N. Yadav, R. Dass, and J. Virmani, "Despeckling filters applied to thyroid ultrasound images: a comparative analysis," *Multimedia Tools and Ap-plications*, vol. 81, no. 6, pp. 8905–8937, 2022, https://doi.org/10.1007/s11042-022-11965-6.

  • Downloads

  • How to Cite

    Wazir, & Dass, R. (2025). Assessment of Deep Learning Models for Image Edge Detection. International Journal of Basic and Applied Sciences, 14(5), 45-57. https://doi.org/10.14419/zgt6cp83