Crack Image Classification: Performance Comparison Among Different Machine Learning Algorithms

• Published in: 2024 8th International Conference on Image and Signal Processing and their Applications (ISPA) pp. 1 - 6
• Main Authors: Okba, Benelmir, Fathi, Dhiabi
• Format: Conference Proceeding
• Language: English
• Published: IEEE 21.04.2024
• Subjects: Classification algorithms; Data mining; deep learning; image classification; machine learning; Machine learning algorithms; Orange data mining; Prediction algorithms; Signal processing algorithms; Support vector machines; surface cracks; Vectors
• DOI: 10.1109/ISPA59904.2024.10536827

Classification of surface crack images is an ever-evolving area of research that aims to develop machine learning models capable of identifying and categorizing cracks in materials. This study concentrates on evaluating and comparing the effectiveness of various machine learning algorithms when employed in the classification of crack images. The objective is to identify the most suitable classification technique for this purpose. To conduct this comparative study, several machine learning algorithms are selected, such as k-nearest neighbors (KNN), decision trees, support vector machines (SVM), random forests and neural networks (NN). Each of these algorithms is trained and evaluated on a dataset of previously annotated crack images.