Adaptive graphical pattern recognition for the classification of company logos

Abstract When dealing with a pattern recognition task two major issues must be faced: firstly, a feature extraction technique has to be applied to extract useful representations of the objects to be recognized; secondly, a classification algorithm must be devised in order to produce a class hypothesis once a pattern representation is given. Adaptive graphical pattern recognition is proposed as a new approach to face these two issues when neither a purely symbolic nor a purely sub-symbolic representation seems adequate for the patterns. This approach is based on appropriate structured representations of patterns which are, subsequently, processed by recursive neural networks, that can be trained to perform the given classification task using connectionist-based learning algorithms. In the proposed framework, the joint role of the structured representation and learning makes it possible to face tasks in which input patterns are affected by many different sources of noise. We report some results that show how the proposed scheme can produce a very promising performance for the classification of company logos corrupted by noise.

[1]  Alessandro Sperduti,et al.  Learning Distributed Representations for the Classification of Terms , 1995, IJCAI.

[2]  King-Sun Fu,et al.  Syntactic Pattern Recognition And Applications , 1968 .

[3]  Alessandro Sperduti,et al.  Supervised neural networks for the classification of structures , 1997, IEEE Trans. Neural Networks.

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

[5]  Michael G. Thomason,et al.  Syntactic Pattern Recognition, An Introduction , 1978, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[7]  Francesca Cesarini,et al.  A neural-based architecture for spot-noisy logo recognition , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[8]  Alessandro Sperduti,et al.  A general framework for adaptive processing of data structures , 1998, IEEE Trans. Neural Networks.

[9]  Carl F. R. Weiman,et al.  Tracking Algorithms Using Log-Polar Mapped Image Coordinates , 1990, Other Conferences.

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

[11]  Christoph Goller,et al.  Inductive Learning in Symbolic Domains Using Structure-Driven Recurrent Neural Networks , 1996, KI.

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

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