Translation and Rotation Invariant Histogram Features for Series of Images.
Ana Pérez Grassi, Fernando Puente León · 2007
Abstract: Some surfaces, like metallic and varnished ones, can only be properly con-trolled, if they are inspected under different illumination directions. This requires a three-dimensional input signal: a series of images, where each image shows the same surface but is illuminated from a different angle. This paper presents a method to ex-tract translation and rotation invariant features from such a series to detect and classify topographic irregularities on the inspected surfaces. Invariant features are represented by 3D fuzzy histograms and classified by a support vector machine (SVM). The pro-posed method performs successfully on varnished wooden surfaces to detect and clas-sify defects on the varnish film. This sort of defects is extremely difficult to recognize, which makes it appropriate to demonstrate the robustness of the method. 1