What is it about?
Forensic video solution to detect and recognize a specific person like a criminal
Featured Image
Why is it important?
The proposed work is the combination of video synopsis and face recognition based person specific identification. But, the state-of-art algorithms are independent for both video synopsis and face recognition. The algorithm works well even in complicated situations such as expression changes, pose, illumination variations and the face is even partially as well as fully occluded in few frames. The advantage of synoptic video helps to recognize the person who is not occluded in some other frames.
Perspectives
The proposed work is the combination of video synopsis and face recognition based person specific identification. But, the state-of-art algorithms are independent for both video synopsis and face recognition. In existing literature, face recognition by HOG, LBP and OCS-LBP features and SVM classifier is discussed. However, these algorithms are not attempted in synoptic video. Also, the combination of HOG+OCS_LBP is used to recognize the face even under pose, expression and illumination variation conditions. Thus, the proposed solution,Face Recognition based Synoptic Video Footage Record (SVFR) recognizes the specific person at a quicker time (due to video synopsis) which is the core idea of the manuscript.
Dr Yogameena Balasubramanian
Thiagarajar College of Engineering
Read the Original
This page is a summary of: Forensic video solution using facial feature-based synoptic Video Footage Record, IET Computer Vision, June 2016, the Institution of Engineering and Technology (the IET),
DOI: 10.1049/iet-cvi.2015.0238.
You can read the full text:
Contributors
The following have contributed to this page
