A Neural Scheme for Robust Detection of Transparent Logos in TV Programs
In this paper, we present a connectionist approach for detecting and precisely localizing transparent logos in TV programs. Our system automatically synthesizes simple problem-specific feature extractors from a training set of logo images, without making any assumptions or using any hand-made design concerning the features to extract or the areas of the logo pattern to analyze. We present in detail the design of our architecture, our learning strategy and the resulting process of logo detection. We also provide experimental results to illustrate the robustness of our approach, that does not require any local preprocessing and leads to a straightforward real time implementation.
KeywordsFalse Alarm Convolutional Neural Network Generalize Regression Neural Network Robust Detection Convolutional Layer
Unable to display preview. Download preview PDF.
- 1.den Hollander, R.J.M., Hanjalic, A.: Logo recognition in video stills by string matching. In: Proceedings of International Conference on Image Processing (ICIP), pp. 517–520 (2003)Google Scholar
- 4.Pan, H., Li, B., Ibrahim Sezan, M.: Automatic detection of replay segments in broadcast sports programs by detection of logos in scene transitions. In: Proceedings of International Conference on Acoustics, Speech, and Signal Processing, ICASSP (2002)Google Scholar
- 6.Sanson, H.: Video indexing: Myth and reality. In: Proceedings of International Workshop on Content-Based Multimedia Indexing (2005)Google Scholar
- 7.Snoek, C.G.M., Worring, M.: A state-of-the-art review on multimodal video indexing. In: Proceedings of the 8th Annual Conference of the Advanced School for Computing and Imaging (2002)Google Scholar
- 9.Veltkamp, R.C., Tanase, M.: Content-based image retrieval systems: A survey. IEEE Image Processing 1(1), 100–148 (2001)Google Scholar
- 11.Zyga, K., Price, R., Williams, B.: A generalized regression neural network for logo recognition. In: Proceedings of International Conference on Knowledge-Based Engineering Systems and Allied Technologies (2000)Google Scholar