Cracked vs. Non-Cracked Surface Classification

Developed a deep learning-based system for automated concrete surface inspection, classifying images into Cracked and Non-Cracked categories. The project implements and compares three neural network architectures: Feed-Forward Neural Network (FFNN), Convolutional Neural Network (CNN), and LSTM. It involves image preprocessing, model training, hyperparameter optimization, and performance evaluation to explore effective AI-driven solutions for structural damage detection.