4.6 Article

A Novel Computer-Vision Approach Assisted by 2D-Wavelet Transform and Locality Sensitive Discriminant Analysis for Concrete Crack Detection

期刊

SENSORS
卷 22, 期 22, 页码 -

出版社

MDPI
DOI: 10.3390/s22228986

关键词

deep learning; FastCrackNet; crack classification; noisy data; wavelet; locality sensitive discriminant analysis

向作者/读者索取更多资源

This study proposes an efficient crack-detection method called FastCrackNet, which combines a fully connected network with 2D-wavelet image transform for feature analysis and feature reduction. It outperforms other image classifiers in terms of speed, performance, and resilience.
This study proposes FastCrackNet, a computationally efficient crack-detection approach. Instead of a computationally costly convolutional neural network (CNN), this technique uses an effective, fully connected network, which is coupled with a 2D-wavelet image transform for analyzing and a locality sensitive discriminant analysis (LSDA) for reducing the number of features. The algorithm described here is used to detect tiny concrete cracks in two noisy adverse conditions and image shadows. By combining wavelet-based feature extraction, feature reduction, and a rapid classifier based on deep learning, this technique surpasses other image classifiers in terms of speed, performance, and resilience. In order to evaluate the accuracy and speed of FastCrackNet, two prominent pre-trained CNN architectures, namely GoogleNet and Xception, are employed. Findings reveal that FastCrackNet has better speed and accuracy than the other models. This study establishes performance and computational thresholds for classifying photos in difficult conditions. In terms of classification efficiency, FastCrackNet outperformed GoogleNet and the Xception model by more than 60 and 80 times, respectively. Furthermore, FastCrackNet's dependability was proved by its robustness and stability in the presence of uncertainties produced by network characteristics and input images, such as input image size, batch size, and input image dimensions.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据