Keypoints (junctions) provide important information for focus-of-attention (FoA) and object categorization/recognition. In this paper we analyze the multi-scale keypoint representation, obtained by applying a linear and quasi-continuous scaling to an optimized model of cortical end-stopped cells, in order to study its importance and possibilities for developing a visual, cortical architecture. We show that keypoints, especially those which are stable over larger scale intervals, can provide a hierarchically structured saliency map for FoA and object recognition. In addition, the application of non-classical receptive field inhibition to keypoint detection allows to distinguish contour keypoints from texture (surface) keypoints. © Springer-Verlag Berlin Heidelberg 2005.
CITATION STYLE
Rodrigues, J., & Du Buf, H. (2005). Multi-scale cortical keypoint representation for attention and object detection. In Lecture Notes in Computer Science (Vol. 3523, pp. 255–262). Springer Verlag. https://doi.org/10.1007/11492542_32
Mendeley helps you to discover research relevant for your work.