Support Vector Machine based Logo Detection in Broadcast Soccer Videos Hossam M. Zawbaa, Nashwa El-Bendary, Aboul Ella Hassanien, Gerald Schaefer, and Sang-Soo Yeo Abstract In this paper, we present a support vector machine based system for au- tomatic logo detection in broadcast soccer (football) videos. Our proposed system is composed of three phases: (1) a pre-processing phase which segments the video stream into video shots, (2) a shot processing phase that applies two types of classi- fication to the video shots, and (3) a replay detection phase that uses support vector machines (SVMs) for emphasising important segments with logo appearance. The proposed system greatly reduces workload and is shown to provide accurate logo detection. Key words: video analysis, logo detection, replay detection, classification, support vector machine Hossam M. Zawbaa, Aboul Ella Hassanien Cairo University, Faculty of Computers and Information; Blind Center of Technology, Cairo, Egypt; ABO Research Laboratory, Cairo, Egypt; e-mail: hossam.zawba3a@gmail.com, aboitcairo@gmail.com Nashwa El-Bendary Arab Academy for Science, Technology, and Maritime Transport, Cairo, Egypt; ABO Research Laboratory, Cairo, Egypt; e-mail: nashwa m@aast.edu Gerald Schaefer Department of Computer Science, Loughborough University, U.K.; e-mail: gerald.schaefer@ieee.org Sang-Soo Yeo Division of Computer Engineering, Mokwon University, Daejeon 302-729, Korea; e-mail: sangsooyeo@gmail.com 1