A neural-based architecture for spot-noisy logo recognitionProceedings of the Fourth International Conference on Document Analysis and Recognition

Much attention has recently been paid on the recognition of graphical objects, like company logos and trademarks. Recognizing these objects facilitates the recognition of document class. 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. In this paper, we propose a new approach for training AANNs especially conceived for dealing with spot noise. The basic idea is that of introducing a new metrics for assessing the reproduction error in AANNs. The proposed algorithm, which is 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.