Neural Techniques in Logo Recognition
A novel scheme is presented to detect and recognise a logo in a given document(s). Another area of interest will be dealing with distorted logos. This refers to logos, which are scaled, rotated, and have a brightness or contrast variation from the original logo. The system recognises these logos and makes correct judgements regarding their identity. The success rate for this system is about 75 to 80 percent
KeywordsNeural Network Histogram Analysis Contrast Variation Recognition Network Logo Recognition
Unable to display preview. Download preview PDF.
- K. Zyga, R. Price and B.Williams. Price and B.Williams, “A Generalized Regression Neural Network for Logo Recognition”, Proceedings of the Fourth International Conference on Knowledge Based Intelligent Systems and Allied Technologies, Brighton, U.K, pp. 475–478, 2000.Google Scholar
- U.Seiffert, “Extracting Features from Logos-First Suggestions” University of Magdeburg, Germany (2000).Google Scholar
- U.Seiffert, “Logo Feature Extraction of Region based properties”, Release 1. 0, University of Magdeburg, Germany (2000).Google Scholar
- U.Seiffert, “Logo Feature Extraction of statistical properties”, Release 1. 0, University of Magdeburg, Germany (2000).Google Scholar
- Christopher M Bishop, “Neural Networks for Pattern recognition”, Oxford University Press, 1995.Google Scholar
- C. Stergiou, D. Siganos, “Neural Networks”, http://www.doc.ic.ac.uk./-nd/surprise96/journal/vol4/cs11/report.html Surprise 96 Journal.
- Doermann, S. D., Rivlin, E. and Weiss, I., “Logo Recognition Using Geometric Invariants”, Proceedings of Second International Conference on Diagram Analysis and Recognition, Tsukuba, Japan, 894–897, October 1993.Google Scholar
- Caprari R. S., “Logo Recognition by literal binary pattern matching”, Defence Science and Technology Organisation, South Australia, September 1998.Google Scholar