A neural-based architecture for spot-noisy logo recognition

Much attention has recently been paid to the recognition of graphical objects, such as company logos and trademarks. Recognizing these objects facilitates the recognition of document classes. Some promising results have been achieved by using autoassociator-based artificial neural networks (AANN) in the presence of homogeneously distributed noise. However, the performance drops significantly when dealing with spot-noisy logos, where strips or blobs produce a partial obstruction of the pictures. We propose a new approach for training AANNs especially conceived for dealing with spot noise. The basic idea is to introduce new metrics for assessing the reproduction error in AANNs. The proposed algorithm, referred to as spot-backpropagation (S-BP), is significantly more robust with respect to spot-noise than classical Euclidean norm-based backpropagation (BP). Our experimental results are based on a database of 88 real logos that are artificially corrupted by spot-noise.

[1]  Morton Nadler,et al.  Pattern recognition engineering , 1993 .

[2]  Giovanni Soda,et al.  Autoassociator-based models for speaker verification , 1996, Pattern Recognit. Lett..

[3]  Abhijit S. Pandya,et al.  Pattern Recognition with Neural Networks in C++ , 1995 .

[4]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[5]  Gian Antonio Mian,et al.  Trademark shapes description by string-matching techniques , 1994, Pattern Recognit..

[6]  Robert M. Haralick,et al.  Global and local document degradation models , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[7]  Henry S. Baird,et al.  Document image defect models , 1995 .

[8]  Francesca Cesarini,et al.  A Hybrid System for Locating and Recognizing Low Level Graphic Items , 1995, GREC.

[9]  Ehud Rivlin,et al.  Logo recognition using geometric invariants , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[10]  Giovanni Soda,et al.  Logo Recognition by Recursive Neural Networks , 1997, GREC.