RNN-based bitstream feature extraction method for codec classification

Wee, S.; Jeong, Je chang

doi:10.1117/12.2521425

상세 보기

RNN-based bitstream feature extraction method for codec classification

Wee, S.;
Jeong, Je chang

Citations

SCOPUS

0

초록

In this paper, we propose codec classification algorithm based on recurrent neural network (RNN) model. In video compression, codecs, such as MPEG2 and H.264/AVC, have their own distinctive data structure. These unique structures which are almost shown in header can be considered their feature. The proposed algorithm exploits that characteristics for classifying unknown bitstreams into specific codec. According to the fact that RNN is appropriate to time series data for learning to classification/recognition, the feature of an encoded bitstream can be extracted. We constitute the encoded bitstream as an input and give the bitstream its label indicating codec index. Two standard codecs, MPEG2 and H.264/AVC, are used in experiment. Experimental results show that the proposed RNN model classified bitstreams into corresponding codecs to some extent.

키워드

bitstream feature extraction; Classification; recurrent neural network; Binary sequences; Data mining; Extraction; Feature extraction; Image compression; Motion Picture Experts Group standards; Recurrent neural networks; Bit stream; Bitstreams; Classification algorithm; Feature extraction methods; H.264/AVC; Recurrent neural network (RNN); Time-series data; Classification (of information)

제목: RNN-based bitstream feature extraction method for codec classification

저자: Wee, S.; Jeong, Je chang

DOI: 10.1117/12.2521425

발행일: 2019-00

유형: Conference Paper

저널명: Proceedings of SPIE - The International Society for Optical Engineering

권: 11049