Local description using multi-scale complete rank transform for improved logo recognition

In this paper we address the challenging problem of logo recognition. As logos appear in various scales, colors and with illuminations coming from source lights of various intensities, positions or colors, their recognition is a tedious task. The typical approach stands within Bag-of-Words (BoW) framework with SIFT (Scale Invariant Feature Transform) based features. To increase the accuracy, we rely on the recently introduced feature of the complete rank transform, which we extend for a multi-scale description. The system´s performance is verified on the FlickrLogos-32 database.