Abstract: The study proposes a novel approach to detecting surface cracks in iron rods by integrating deep learning with image processing techniques. It emphasizes the importance of collecting a diverse dataset comprising images of both damaged and undamaged metallic rods across various environments. Preprocessing steps.
Subsequently, image segmentation is utilized to isolate the iron rod's region of interest from the background. Feature extraction methods, including texture analysis and edge detection, are then applied to capture distinctive characteristics of cracked surfaces. A deep learning model, such as a convolutional neural network (CNN), is trained on the segmented.....
Keywords— Crack detection, CNN, Image processing, Deep learning, Accuracy
[1]
A. Prasetyo, E. M. Yuniarto, P. Suprobo And A. Tambusay, "Application Of Edge Detection Technique For Concrete Surface Crack Detection," 2022 International Seminar On Intelligent Technology And Its Applications (Isitia), Surabaya, Indonesia, 2022, Pp. 209-213, Doi: 10.1109/Isitia56226.2022.9855280.
[2]
D. K. K, S. A, S. P And V. C. Maha Vishnu, "Detection Of Cracks In High Rise Buildings Using Drones," 2022 3rd International Conference On Electronics And Sustainable Communication Systems
[3]
(Icesc), Coimbatore, India, 2022, Pp. 318-324, Doi: 10.1109/Icesc54411.2022.9885251.
[4]
J. Liu, J. Gu And S. Luo, "Research On Road Crack Detection Based On Machine Vision," 2022 Ieee 6th Advanced Information Technology, Electronic And Automation Control Conference (Iaeac), Beijing, China, 2022, Pp. 543-547,
Doi: 10.1109/Iaeac54830.2022.9929645.
[5]
L. Fan, S. Li, Y. Li, B. Li, D. Cao And F. -Y. Wang, "Pavement Cracks Coupled With Shadows: A New Shadow-Crack Dataset And A Shadow-Removal-Oriented Crack Detection Approach," In Ieee/Caa Journal Of Automatica Sinica, Vol. 10, No. 7, Pp. 1593-1607, July 2023, Doi: 10.1109/Jas.2023.123447