Query-Adaptive Logo Search using Shape-Aware Descriptors

We propose a graph-based optimization framework to leverage category independent object proposals (candidate object regions) for logo search in a large scale image database. The proposed contour-based feature descriptor EdgeBoW is robust to view-angle changes, varying illumination conditions and can implicitly capture the significant object shape information. Being equipped with a local descriptor, it can handle a fair amount of occlusion and deformation frequently present in a real-life scenario. Given a small set of initially retrieved candidate object proposals, a fast graph based short-listing scheme is designed to exploit the mutual similarities among these proposals for eliminating outliers. 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 proposed query expansion strategy assesses each of the remaining 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 number of benchmark datasets demonstrates its effectiveness and superior generalization ability in both clutter intensive real life images and poor quality binary document images.EICPCI-S(ISTP)dbhattacharjee@ntu.edu.sg; jsyuan@ntu.edu.sg; lingyu@pku.edu.cn1155-115