Title :
Recognition of trademarks with spatial statistics and neural learning
Author_Institution :
Inf. Technol. Div., Defence Sci. & Technol. Organ., Edinburgh, SA, Australia
Abstract :
This paper presents a new approach for extracting spatial features of images based on the theory of regionalized variables. These features can be used for automatic recognition of trademark or logo images using a neural network. Initial results have shown that the approach is invariant to geometrical rotation and robust to noise.
Keywords :
feature extraction; image recognition; image retrieval; learning (artificial intelligence); neural nets; visual databases; geometrical rotation; image retrieval; logo image recognition; neural learning; neural network; noise; regionalized variables; spatial feature extraction; spatial statistics; trademark recognition; Content based retrieval; Feature extraction; Image databases; Image recognition; Image retrieval; Information retrieval; Neural networks; Shape; Statistics; Trademarks;
Conference_Titel :
Artificial Intelligence Systems, 2002. (ICAIS 2002). 2002 IEEE International Conference on
Print_ISBN :
0-7695-1733-1
DOI :
10.1109/ICAIS.2002.1048088
