Video forensics is an investigation technique for detecting manipulated(forged) video, and is a key technology for solving various image/video related legal problems.
There are various methods for video forgery.
Video Forgery occurs in a variable ways without visible clues. We detect the forgery of the video by detecting the features of the forged video with some specific models like video coding patterns, frequency domain parameters and detecting whether the video has been compressed only once or not.
Detection of Frame Deletion in HEVC Compressed Domain
We perform forged video classification with machine learning techniques using the features extracted from the verification video.
There is traditionally a forged video classification technique through machine learning. Recently, we have used forged video classification techniques using deep learning techniques which are useful in various fields.
[K. Uddin, Y. Yang, B. T. Oh, “Double Compression Detection in HEVC-coded video with the same coding parameters using picture partitioning information,” Signal Processing: Image Communication, Apr. 2022.]
[J. H. Hong, Y. Yang, and B. T. Oh, “Detection of frame deletion in HEVC-coded video in the compressed domain,” Digital Investigation, Sep. 2019.]
[홍진형, 양윤모, 오병태, “부호화 패턴 분석을 통한 영상 조작 검출 기술,” 방송공학회논문지, Nov. 2017.]