Crack Image Detection and Edge Feature Detection by Introducing Lightweight Network

Authors

  • Quanyi Guo
  • Chen Chong

DOI:

https://doi.org/10.62051/sqz1zk59

Keywords:

Lightweight network; Crack image detection; Edge features; Multi-scale supervision; Convolutional Neural Network.

Abstract

In order to optimize the crack image detection technology and realize edge feature detection, an edge detection model based on Visual Geometry Group (VGG) algorithm is constructed based on multi-scale supervised model and convolutional neural network (CNN). Then, a lightweight network is introduced to optimize the model, and a significant analysis is made with the classical algorithm. Compared with the mean absolute error (MAE), the performance advantage of the optimization algorithm is further verified. The research results show that the edge detection algorithm of multi-scale supervised model proposed in this study is superior to the traditional algorithm in all datasets. The F-measure values in four different datasets are 0.86, 0.93, 0.93 and 0.88 respectively, which shows the superior performance of the algorithm. Meanwhile, the MAE values of the algorithm based on lightweight network optimization in four different datasets are 0.04, 0.03, 0.03 and 0.06 respectively. Compared with other classical algorithms, the optimization algorithm has achieved the lowest MAE values, which proves that the optimization algorithm has significant advantages and higher accuracy in edge detection tasks. This study improves the accuracy and efficiency of crack image detection, which is of great significance to promote the development and application of crack image detection technology.

Downloads

Download data is not yet available.

References

Khan M A M, Kee S H, Pathan A S K, et al. Image Processing Techniques for Concrete Crack Detection: A Scientometrics Literature Review[J]. Remote Sensing, 2023, 15(9): 2400.

Chen D, Huang B, Kang F. A review of detection technologies for underwater cracks on concrete dam surfaces[J]. Applied Sciences, 2023, 13(6): 3564.

Shim S. Self‐training approach for crack detection using synthesized crack images based on conditional generative adversarial network[J]. Computer‐Aided Civil and Infrastructure Engineering, 2024, 39(7): 1019-1041.

Taye M M. Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions[J]. Computation, 2023, 11(3): 52.

Tabrizchi H, Parvizpour S, Razmara J. An improved VGG model for skin cancer detection[J]. Neural Processing Letters, 2023, 55(4): 3715-3732.

Shah S R, Qadri S, Bibi H, et al. Comparing inception V3, VGG 16, VGG 19, CNN, and ResNet 50: a case study on early detection of a rice disease[J]. Agronomy, 2023, 13(6): 1633.

Aiadi O, Khaldi B, Saadeddine C. MDFNet: An unsupervised lightweight network for ear print recognition[J]. Journal of Ambient Intelligence and Humanized Computing, 2023, 14(10): 13773-13786.

Alansari M, Hay O A, Javed S, et al. Ghostfacenets: Lightweight face recognition model from cheap operations[J]. IEEE Access, 2023, 11(1): 35429-35446.

Zhang D, Hao X, Wang D, et al. An efficient lightweight convolutional neural network for industrial surface defect detection[J]. Artificial Intelligence Review, 2023, 56(9): 10651-10677.

Chen N, Li Y, Yang Z, et al. LODNU: lightweight object detection network in UAV vision[J]. The Journal of Supercomputing, 2023, 79(9): 10117-10138.

Lin S L. Research on tire crack detection using image deep learning method[J]. Scientific reports, 2023, 13(1): 8027.

Zhu Z, Huang D, Zhou X, et al. Image quality evaluation method for surface crack detection based on standard test chart[J]. Computer‐Aided Civil and Infrastructure Engineering, 2024, 39(9): 1294-1317.

Salehi A W, Khan S, Gupta G, et al. A study of CNN and transfer learning in medical imaging: Advantages, challenges, future scope[J]. Sustainability, 2023, 15(7): 5930.

Lu S, Xia K, Wang S H. Diagnosis of cerebral microbleed via VGG and extreme learning machine trained by Gaussian map bat algorithm[J]. Journal of ambient intelligence and humanized computing, 2023, 14(5): 5395-5406.

Sui B, Cao Y, Bai X, et al. BIBED-Seg: Block-in-block edge detection network for guiding semantic segmentation task of high-resolution remote sensing images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, 16(1): 1531-1549.

Lawal O M. YOLOv5-LiNet: A lightweight network for fruits instance segmentation[J]. Plos one, 2023, 18(3): e0282297.

Cen H. Target location detection of mobile robots based on R-FCN deep convolutional neural network[J]. International Journal of System Assurance Engineering and Management, 2023, 14(2): 728-737.

Zhao Y, Zou J, Liu S, et al. Terrace Extraction Method Based on Remote Sensing and a Novel Deep Learning Framework[J]. Remote Sensing, 2024, 16(9): 1649.

Mazzia F, Chan R. Alma Collections as a promotional tool for government documents: By Faye Mazzia and Robin Chan, University of Central Florida[J]. Journal of Electronic Resources Librarianship, 2022, 34(4): 341-344.

Aranguren C, Aguilera R. Application of self-learning enhancing Huff and Puff gas injection optimization in shale reservoirs through sequence-based proxy reservoir simulation and reinforcement learning[J]. Geoenergy Science and Engineering, 2024, 234(1): 212676.

Downloads

Published

06-08-2024