Shape similarity image retrieval by hypothesis and test

Image retrieval by shape similarity systems usually either focus their attention on images with isolated objects (uniform backgrounds and no occluding objects) or perform time consuming exhaustive initializations to localize the portion of the image possibly containing the searched shape. We propose a content based image retrieval (CBIR) method merging classic alignment techniques for an efficient shape localization with an innovative verification strategy able to deal with an inexact matching between the searched and the found shape.