Summary of Concrete Surface Crack Detection with Convolutional-based Deep Learning Models, by Sara Shomal Zadeh et al.
Concrete Surface Crack Detection with Convolutional-based Deep Learning Models
by Sara Shomal Zadeh, Sina Aalipour birgani, Meisam Khorshidi, Farhad Kooban
First submitted to arxiv on: 13 Jan 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG); Image and Video Processing (eess.IV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The detection of cracks in buildings is crucial for structural health monitoring and inspection. However, this task poses significant challenges to computer vision techniques due to the subtle nature of cracks, which can be easily confused with background textures or irregularities. To overcome these hurdles, convolutional neural networks (CNNs) have emerged as a promising framework for crack detection, offering high levels of accuracy and precision. The ability to adapt pre-trained networks through transfer learning provides a valuable tool for users, eliminating the need for an in-depth understanding of algorithm intricacies. In this paper, we employ fine-tuning techniques on pre-trained deep learning architectures: VGG19, ResNet50, Inception V3, and EfficientNetV2. We compare these models using precision, recall, and F1 scores. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding tiny cracks in buildings that can be hard to see. It’s important to find these cracks before they become big problems. Computers have a hard time seeing these small cracks because they often look like the background or other things. To solve this problem, scientists use special computer programs called convolutional neural networks (CNNs). These programs are good at finding patterns in pictures and can be used to detect tiny cracks. The scientists in this paper use four different kinds of CNNs: VGG19, ResNet50, Inception V3, and EfficientNetV2. They compare how well each one works. |
Keywords
* Artificial intelligence * Deep learning * Fine tuning * Precision * Recall * Transfer learning
