The surface-shape operator based shading-tolerant method for multiscale image analysis

This paper proposes a method of multiscale image analysis through an operator called the "surface-shape operator". By considering an image function as a surface function, the surface-shape operator describes shape of each pixel in terms of the topographic structure such as hill, dale, ridge, valley, etc. The surface-shape operator is used as a pre-processing for extracting the multiscale topographic structures of images in scale-space representation. Then, image features are extracted from the transformed images instead of the original ones. The surface-shape operator has invariant properties under monotonic and linear gray tone transformations, and is insensitive to additive noise modelled by linear functions, so the proposed method has a robustness with brightness variations and shading effects. We illustrate the usefulness of the proposed method with an application to image classification, and also demonstrate performances concerning the robustness with brightness variations and shading effects. The multiresolution simultaneous autoregressive (MRSAR) method is selected as a representative method of multiscale approaches for image classification used to-date for comparison purposes. Results show that the proposed method performs better and has much more robustness with brightness variations and shading effects than the MRSAR method.