Assessment of Convolutional Neural Network Pre-Trained Models for Detection and Orientation of Cracks

Abstract

Failure due to cracks is a major structural safety issue for engineering constructions. Human examination is the most common method for detecting crack failure, although it is subjective and time-consuming. Inspection of civil engineering structures must include crack detection and categorization as a key component of the process. Images can automatically be classified using convolutional neural networks (CNNs), a subtype of deep learning (DL). For image categorization, a variety of pre-trained CNN architectures are available. This study assesses seven pre-trained neural networks, including GoogLeNet, MobileNet-V2, Inception-V3, ResNet18, ResNet50, ResNet101, and ShuffleNet, for crack detection and categorization. Images are classified as diagonal crack (DC), horizontal crack (HC), uncracked (UC), and vertical crack (VC). Each architecture is trained with 32,000 images equally divided among each class. A total of 100 images from each category are used to test the trained models, and the results are compared. Inception-V3 outperforms all the other models with accuracies of 96%, 94%, 92%, and 96% for DC, HC, UC, and VC classifications, respectively. ResNet101 has the longest training time at 171 min, while ResNet18 has the lowest at 32 min. This research allows the best CNN architecture for automatic detection and orientation of cracks to be selected, based on the accuracy and time taken for the training of the model.

A Deep Learning Approach for Surface Crack Classification and Segmentation in Unmanned Aerial Vehicle Assisted Infrastructure Inspections

“…The accuracy of the suggested architecture for crack detection was benchmarked against existing feature-extraction CNN architectures by leveraging transfer learning. Pre-trained models employed in the previous literature, including Densenet201 [ 38 ], Xception [ 39 ], Mobile-netV2 [ 40 ], Resnet50 [ 41 ], and VGG19 [ 42 ], were used as the base feature-extraction CNN. The last layers of these pre-trained models were modified to suit the binary classification task by the addition of a flattened layer followed by two dense layers with ReLU activation.…”

Assessment of Deep Learning Models for Cutaneous Leishmania Parasite Diagnosis Using Microscopic Images

“…This pre-trained model can classify images into over 1000 different object categories, including keyboards, mice, pencils, and several animal species. Notably, the network operates with picture inputs of 224 by 224 pixels [ 43 ].…”

Exploring the Depths of Visual Understanding: A Comprehensive Review on Real-Time Object of Interest Detection Techniques

“…While CNN has recorded great success for image classification problems, it has struggled to replicate the same success on small datasets due to issues such as over-fitting, slow convergence, poor generalized model, Shit invariance, and bias [54,55] and hence presents the need for pertained models. These are pre-trained as a heterogeneous CNN architecture trained with a large corpus of datasets to form the building block when developing new models and hence address these aforementioned traditional CNN challenges [56]. Popular CNN-based pre-trained models are Alex.Net, ResNet, Mobile.Net, and DenseNet [57], while many other pre-trained models are GoogleNet [58], Inception-V3 [59], VGG16 [60] and VGG19 [61], Inception-ResNet [62], DarkNet [63], Xception [64], ShuffleNet [65], and SqueezeNet [66].…”