Title :
Video clip recognition using joint audio-visual processing model
Author :
Kulesh, Victor ; Petrushin, Valery A. ; Sethi, Ishwar K.
Author_Institution :
Dept. of Comput. Sci. & Eng., Oakland Univ., Rochester, MI, USA
Abstract :
The automatic recognition of video clips is an important capability with applications in broadcast monitoring for content theft and adherence to advertisement campaign. We present an approach for video clip recognition based on HMM and Gaussian mixture modeling for modeling video and audio streams respectively. The approach is used to model TV commercials. The recognition results of using single stream and joint models are compared The error rate of 0.01% is achieved when the joint audiovisual processing model is employed.
Keywords :
audio signal processing; hidden Markov models; image colour analysis; image recognition; image sequences; matrix algebra; probability; video signal processing; Gaussian mixture modeling; HMM; TV commercials; advertisement campaign; audio streams; broadcast monitoring; content theft; joint audio-visual processing model; video clip recognition; video streams; Broadcasting; Error analysis; Hidden Markov models; Laboratories; Multimedia communication; Production; Spatial databases; Streaming media; TV; Video sequences;
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
Print_ISBN :
0-7695-1695-X
DOI :
10.1109/ICPR.2002.1044776
