arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.13068cs.CVcs.AI
收藏

基于SIFT和SURF的异常检测特征提取

SIFT and SURF based feature extraction for the anomaly detection

FEEC BUT(布尔诺理工大学电气工程与计算机科学学院)

Simon Bilik, Karel Horak

AI总结:

该研究提出用SIFT和SURF算法提取图像特征做异常检测,在真实数据集上验证了半监督和单类分类器约89%的准确率,且单类性能可比半监督,同时公开了数据集和代码。

摘要:

本文提出了一种利用SIFT(尺度不变特征变换)和SURF(加速稳健特征)算法提取图像特征以用于异常检测的方法。我们使用这些特征向量在真实数据集上训练多种分类器,采用两种训练模式:半监督模式(含少量故障样本)搭配大量分类器,以及单类模式(无故障样本)使用SVDD(支持向量数据描述)和SVM(支持向量机)分类器。研究证明,SIFT和SURF算法可作为特征提取器,用于训练半监督和单类分类器,准确率约为89%,且单类分类器的性能可与半监督分类器相媲美。我们还公开了所用数据集和源代码。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑