Towards Enhanced Anomaly Object Detection and Face Recognition (EAODFR) in Surveillance Videos using Recurrent Neural Networks

Abstract

In the present decade, anomaly object detection and face recognition from surveillance videos from diverse environments have become interesting and challenging research areas in computer vision. This paper works on developing an Enhanced Anomaly Object Detection and Face Recognition (EAODFR) model using Recurrent Neural Networks (RNN). Moreover, fractional derivative based background separation has been incorporated for framing efficient background subtraction model and foreground segmentation with appropriate pixel definitions on each frame of the surveillance videos. The Region of Interest detection has been done using optimal thresholding and for detecting anomaly objects. Further, efficient face recognition has been accomplished by designing the Recurrent Neural Networks (RNN), which is implemented with Long Short-Term Memory (LSTM). The recurrent NN are trained in terms of determining anomalous objects using the extracted features in the each frame of the video. The obtained results are analyzed in terms of precision, recall and f-measure and compared with some existing face recognition models. The comparative analysis provides better results and outperforms others.