SIFT and SURF based feature extraction for the anomaly detection
This is an incremental improvement for image anomaly detection tasks, applying existing feature extraction methods to a specific domain.
The paper tackles anomaly detection in images by using SIFT and SURF algorithms as feature extractors, achieving around 89% accuracy with both semi-supervised and one-class classifiers.
In this paper, we suggest a way, how to use SIFT and SURF algorithms to extract the image features for anomaly detection. We use those feature vectors to train various classifiers on a real-world dataset in the semi -supervised (with a small number of faulty samples) manner with a large number of classifiers and in the one-class (with no faulty samples) manner using the SVDD and SVM classifier. We prove, that the SIFT and SURF algorithms could be used as feature extractors, that they could be used to train a semi-supervised and one-class classifier with an accuracy around 89\% and that the performance of the one-class classifier could be comparable to the semi-supervised one. We also made our dataset and source code publicly available.