Image retrieval using the curvature scale space (CSS) technique and the self-organizing map (SOM) model under rotation

In a previous work (de Almeida), we presented an approach for shape-based image retrieval using the curvature scale space (CSS) and self-organizing map (SOM) methods. Here, we examine the robustness of the representation with images under variations of rotation. Moreover, the CSS images extracted from a database are processed and represented by median vectors that constitutes the training data set for a SOM neural network. This way of representation improves the accuracy of image retrieval in comparison with the previous work (de Almeida) that used the first principal component of the PCA technique. A benchmark database is used to demonstrate the usefulness of the proposed methodology.