Query-Adaptive logo search using shape-Aware descriptors

We propose a graph-based optimization framework to lever-age category independent object proposals (candidate object regions) for logo search in a large scale image database. The proposed contour-based feature descriptor EdgeBoW is ro-bust to view-Angle changes, varying illumination conditions and can implicitly capture the signifficant object shape infor-mation. Being equipped with a local descriptor, it can han-dle a fair amount of occlusion and deformation frequently present in a real-life scenario. Given a small set of ini-tially retrieved candidate object proposals, a fast graph-based short-listing scheme is designed to exploit the mu-tual similarities among these proposals for eliminating out-liers. In contrast to a coarse image-level pairwise similarity measure, this search focused on a few specific image regions provides a more accurate method for matching. The pro-posed query expansion strategy assesses each of the remain-ing better matched proposals against all its neighbors within the same image for a precise localization. Combined with an efficient feature descriptor EdgeBoW, a set of insightful edge-weights and node-utility measures can yield promising results, especially for object categories primarily defined by its shape. Extensive set of experiments performed on a num-ber of benchmark datasets demonstrates its effectiveness and superior generalization ability in both clutter intensive real-life images and poor quality binary document images.