Texture classification-based feature processing for violence-based anomaly detection in crowded environments

作者：

Highlights：

• To increase different face classification accuracy by identifying the texture boundaries using non-dimensional vectors

• To minimize the processing time and violence detection accuracy using effective classifiers

• To reduce the misclassification error rate using the optimized network parameter updating procedure

摘要

•To increase different face classification accuracy by identifying the texture boundaries using non-dimensional vectors•To minimize the processing time and violence detection accuracy using effective classifiers•To reduce the misclassification error rate using the optimized network parameter updating procedure

论文关键词：Anomaly detection,Deep learning,Feature processing,Textural analysis,Video surveillance

论文评审过程：Received 19 February 2022, Revised 27 April 2022, Accepted 13 May 2022, Available online 25 May 2022, Version of Record 31 May 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104488