A Comparative Study of Neural Network Architectures for Surface Crack Detection: Performance Evolution from FFNN to Transfer Learning

Introduction / Main Floor: A Comparative Study of Neural Network Architectures for Surface Crack Detection: Performance Evolution from FFNN to Transfer Learning

This article provides an in-depth analysis of a deep learning research project on surface crack detection. It compares the performance of four architectures—FFNN, LSTM-RNN, CNN, and ResNet18 with transfer learning—on a dataset of approximately 228,000 grayscale images, revealing the advantages and disadvantages of different neural network architectures in industrial visual inspection tasks.