In this paper we propose recognizing logo images hy using an adaptive model referred to as recursive artificial neural network. At first, logo images are converted into a structured representation based on contour trees. Recursive neural networks are then learnt using the contour-trees as inputs to the neural nets. On the other hand, the contour-tree is constructed by associating a node with each exterior or interior contour extracted from the logo instance. Nodes in the tree are labeled by a feature vector, which describes the contour by means of its perimeter, sur rounded area, and a synthetic representation of its curvature plot. The contour-tree representation contains the topological structured information of logo and continuous values pertaining to each contour node. Hence symbolic and sub-symbolic information coexist in the contour-tree representation of logo image. Experimental results are reported on 40 real logos distorted with artificial noise and performance of recursive neural network is compared with another two types of neural approaches.
Francesconi, E., Frasconi, P., Gori, M., Marinai, S., Sheng, J., Soda, G., et al. (1997). Logo recognition by recursive neural networks. In Proceedings of GREC 1997 - Lecture Notes in Computer Science 1389 (pp.104-117). Berlin : SPRINGER-VERLAG BERLIN.
Logo recognition by recursive neural networks
GORI, MARCO;
1997-01-01
Abstract
In this paper we propose recognizing logo images hy using an adaptive model referred to as recursive artificial neural network. At first, logo images are converted into a structured representation based on contour trees. Recursive neural networks are then learnt using the contour-trees as inputs to the neural nets. On the other hand, the contour-tree is constructed by associating a node with each exterior or interior contour extracted from the logo instance. Nodes in the tree are labeled by a feature vector, which describes the contour by means of its perimeter, sur rounded area, and a synthetic representation of its curvature plot. The contour-tree representation contains the topological structured information of logo and continuous values pertaining to each contour node. Hence symbolic and sub-symbolic information coexist in the contour-tree representation of logo image. Experimental results are reported on 40 real logos distorted with artificial noise and performance of recursive neural network is compared with another two types of neural approaches.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11365/38740
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo