Principal directions for local independent components analysis
NN'08 Proceedings of the 9th WSEAS International Conference on Neural Networks
| Hi-index | 0.00 |
A new affine invariant curve normalization method using Independent Component Analysis (ICA) is presented. First, Principal Component Analysis (PCA) is used for translation, scale and shear normalization. ICA and the third order moments are then employed for rotation and reflection normalization. It is shown that all affine transformed versions of an object have a unique or canonical representation. Experiments are conducted to asses the robustness of our approach. Proposed normalization technique can be used as a pre-processing for object modelling and recognition.