Deep Learning Edge Detection for Image Segmentation: Advances and Challenges

Mira Yunisa; Tri Maryani

doi:10.59934/jaiea.v5i3.2456

Authors

Mira Yunisa Universitas Majalengka
Tri Maryani Universitas Majalengka

DOI:

https://doi.org/10.59934/jaiea.v5i3.2456

Keywords:

Edge Detection, Deep Learning, image segmentation, Convolutional Neural Network, Systematic Literature Review

Abstract

This study offers a thorough Systematic Literature Review (SLR) of current advancements in deep learning-based edge detection techniques for picture segmentation. The study is motivated by the shortcomings of conventional edge recognition methods in processing complicated images, especially when there is significant noise, low contrast, and a variety of texture variations. Deep learning techniques are becoming more and more popular because to the growing need for precise picture segmentation in a variety of industries, including autonomous driving and medical imaging. This study examines 32 carefully chosen scientific papers from reliable sources using the PRISMA 2020 technique. The results show a substantial departure from traditional approaches in favor of Transformer-based models, encoder-decoder models like U-Net, and Convolutional Neural Network (CNN)-based architectures that increase edge detection accuracy and consistency. Additionally, it has been demonstrated that combining attention processes with multi-scale feature extraction improves object border accuracy. Nonetheless, issues including the need for sizable labeled datasets, computational complexity, and restricted generalization capacity continue to be major worries. Future trends toward the creation of more effective, flexible, and real-time models are also identified by this study. It is anticipated that the results will be used as a guide for creating more reliable and useful edge detection techniques.

Downloads

Download data is not yet available.

References

B. Tian and W. Wei, “Research Overview on Edge Detection Algorithms Based on Deep Learning and Image Fusion,” Secur. Commun. Networks, vol. 2022, no. 1, 2022, doi: 10.1155/2022/1155814.

Y. Wu and Q. Li, “The Algorithm of Watershed Color Image Segmentation Based on Morphological Gradient,” Sensors, vol. 22, no. 21, 2022, doi: 10.3390/s22218202.

X. Wang, L. Shu, R. Han, F. Yang, T. Gordon, and X. Wang, “A Survey of Farmland Boundary Extraction Technology Based on Remote Sensing Images,” 2023, doi: 10.3390/electronics12051156.

M. Mushtaq, M. U. Akram, N. S. Alghamdi, J. Fatima, and R. F. Masood, “Localization and Edge-Based Segmentation of Lumbar Spine Learning Models,” 2022, doi: 10.3390/s22041547.

R. A. A S and S. Gopalan, “Comparative Analysis of Eight Direction Sobel Edge Detection Algorithm for Brain Tumor MRI Images,” Procedia Comput. Sci., vol. 201, no. C, pp. 487–494, 2022, doi: 10.1016/j.procs.2022.03.063.

J. Agustín Tortolero Osuna and A. Jorge Rosales Silva, “Parallel Peer Group Filter for Impulse Denoising in Digital Images on Gpu,” Comput. Informatics, vol. 38, pp. 1320–1340, 2019, doi: 10.31577/cai.

S. P. Pathak and S. A. Patil, “Evaluation of Effect of Pre-Processing Techniques in Solar Panel Fault Detection,” IEEE Access, vol. 11, no. July, pp. 72848–72860, 2023, doi: 10.1109/ACCESS.2023.3293756.

J. C. Avendaño, J. Leander, and R. Karoumi, “Image-Based Concrete Crack Detection Method Using the Median Absolute Deviation,” Sensors, vol. 24, no. 9, 2024, doi: 10.3390/s24092736.

H. Fang et al., “ADAM Challenge: Detecting Age-Related Macular Degeneration From Fundus Images,” IEEE Trans. Med. Imaging, vol. 41, no. 10, pp. 2828–2847, 2022, doi: 10.1109/TMI.2022.3172773.

Q. Cheng, H. Wang, B. Zhu, Y. Shi, and B. Xie, “A Real-Time UAV Target Detection Algorithm Based on Edge Computing,” Drones, vol. 7, no. 2, 2023, doi: 10.3390/drones7020095.

L. Xiao, B. Zhou, and C. Fan, “Automatic brain MRI tumors segmentation based on deep fusion of weak edge and context features,” Artif. Intell. Rev., vol. 58, no. 5, 2025, doi: 10.1007/s10462-025-11151-8.

S. Umirzakova, S. Ahmad, S. Mardieva, S. Muksimova, and T. K. Whangbo, “Deep learning-driven diagnosis: A multi-task approach for segmenting stroke and Bell’s palsy,” Pattern Recognit., vol. 144, no. July, p. 109866, 2023, doi: 10.1016/j.patcog.2023.109866.

J. Chen et al., “TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation,” pp. 1–13, 2021, doi: 10.48550/arXiv.2102.04306.

L. Tong et al., “LiViT-Net: A U-Net-like, lightweight Transformer network for retinal vessel segmentation,” Comput. Struct. Biotechnol. J., vol. 24, no. February, pp. 213–224, 2024, doi: 10.1016/j.csbj.2024.03.003.

Y. Yin, Y. Guo, L. Deng, and B. Chai, “Improved PSPNet-based water shoreline detection in complex inland river scenarios,” Complex Intell. Syst., vol. 9, no. 1, pp. 233–245, 2023, doi: 10.1007/s40747-022-00793-8.

M. Jahanbakht, W. Xiang, N. J. Waltham, and M. R. Azghadi, “Distributed Deep Learning and Energy-Efficient Real-Time Image Processing at the Edge for Fish Segmentation in Underwater Videos,” IEEE Access, vol. 10, no. July, pp. 117796–117807, 2022, doi: 10.1109/ACCESS.2022.3202975.

A. Dosovitskiy et al., “an Image Is Worth 16X16 Words: Transformers for Image Recognition At Scale,” ICLR 2021 - 9th Int. Conf. Learn. Represent., 2021.

J. Liu et al., “Local Label Point Correction for Edge Detection of Overlapping Cervical Cells,” Front. Neuroinform., vol. 16, no. May, pp. 1–14, 2022, doi: 10.3389/fninf.2022.895290.

S. Yang, B. Ni, W. Du, and T. Yu, “Research on an Improved Segmentation Recognition Algorithm of Overlapping Agaricus bisporus,” Sensors, vol. 22, no. 10, 2022, doi: 10.3390/s22103946.

M. J. Page et al., “The PRISMA 2020 statement: An updated guideline for reporting systematic reviews,” Mar. 29, 2021, BMJ Publishing Group. doi: 10.1136/bmj.n71.

N. R. Haddaway, M. J. Page, C. C. Pritchard, and L. A. McGuinness, “PRISMA2020: An R package and Shiny app for producing PRISMA 2020-compliant flow diagrams, with interactivity for optimised digital transparency and Open Synthesis,” Campbell Syst. Rev., vol. 18, no. 2, pp. 1–12, 2022, doi: 10.1002/cl2.1230.

F. Yuanbin, Guoxiaojie, H. Qiming, L. Di, M. Jiayi, and L. Haibin, “Hierarchical Image Peeling: A Flexible Scale-space Filtering Framework,” 2021, [Online]. Available: http://arxiv.org/abs/2104.01534

H. Zhang, F. Shao, X. He, Z. Zhang, Y. Cai, and S. Bi, “Research on Object Detection and Recognition Method for UAV Aerial Images Based on Improved YOLOv5,” Drones, vol. 7, no. 6, 2023, doi: 10.3390/drones7060402.

M. Mubashar, N. Khan, A. R. Sajid, M. H. Javed, and N. U. Hassan, “Have We Solved Edge Detection? A Review of State-of-the-Art Datasets and DNN Based Techniques,” IEEE Access, vol. 10, no. July, pp. 70541–70552, 2022, doi: 10.1109/ACCESS.2022.3187838.

S. Ben Chaabane and A. Bushnag, “Color Edge Detection Using Multidirectional Sobel Filter and Fuzzy Fusion,” Comput. Mater. Contin., vol. 74, no. 2, pp. 2839–2852, 2023, doi: 10.32604/cmc.2023.032760.

M. Hagara, R. Stojanović, A. Šatka, P. Kubinec, and O. Ondráček, “Modified algorithm of unimodal thresholding for FPGA implementation,” Microprocess. Microsyst., vol. 94, no. February, pp. 4–10, 2022, doi: 10.1016/j.micpro.2022.104669.

N. U. Rehman et al., “Edge of discovery: Enhancing breast tumor MRI analysis with boundary-driven deep learning,” Biomed. Signal Process. Control, vol. 95, no. PA, p. 106291, 2024, doi: 10.1016/j.bspc.2024.106291.

B. Liu, H. Zhu, and W. Zhang, “EDC-UNet: A Pulmonary Nodule Segmentation Method Based on Edge Detail Enhancement.”

L. Zhu, Y. Cai, J. Liao, and F. Wu, “Lung Parenchyma Segmentation Based on U-Net Fused With Shape Stream,” IEEE Access, vol. 12, no. January, pp. 29238–29251, 2024, doi: 10.1109/ACCESS.2024.3365577.

B. Cheng, M. Tian, S. Jiang, W. Liu, and Y. Pang, “Multi-Task Learning and Multimodal Fusion for Road Segmentation,” IEEE Access, vol. 11, no. February 2022, pp. 18947–18959, 2023, doi: 10.1109/ACCESS.2022.3151372.

X. Fang, E. Zhang, B. Li, and B. Zhai, “A Fast and High-Precision Ellipse Detection Method Based on the Candy’s Theorem,” IEEE Access, vol. 11, no. September, pp. 102971–102980, 2023, doi: 10.1109/ACCESS.2023.3315848.

L. Ma, J. Han, C. Dong, T. Fang, W. Liu, and X. He, “Conveyor Belt Deviation Detection for Mineral Mining Applications Based on Attention Mechanism and Boundary Constraints,” Sensors, vol. 25, no. 22, pp. 1–29, 2025, doi: 10.3390/s25226945.

M. Tabb and N. Ahuja, “Multiscale image segmentation by integrated edge and region detection,” IEEE Trans. Image Process., vol. 6, no. 5, pp. 642–655, 1997, doi: 10.1109/83.568922.

T. An, W. Huang, D. Xu, Q. He, J. Hu, and Y. Lou, “A Deep Learning Framework for Boundary-Aware Semantic Segmentation,” 2025 5th Int. Conf. Artif. Intell. Ind. Technol. Appl. AIITA 2025, pp. 886–890, 2025, doi: 10.1109/AIITA65135.2025.11048045.

N. Ofir and Y. Keller, “Multi-scale processing of noisy images using edge preservation losses,” Proc. - Int. Conf. Pattern Recognit., pp. 8751–8758, 2020, doi: 10.1109/ICPR48806.2021.9413325.

X. Ru, Y. Wang, L. Peng, and J. Li, “An Adaptive Extraction Method for Knitted Patterns Based on Bayesian-Optimized Bilateral Filtering,” Appl. Sci., vol. 16, no. 5, pp. 1–24, 2026, doi: 10.3390/app16052526.