This paper presents a new method for logo detection and recognition based on “Context- Dependent Similarity” (CDS). It directly has as a feature the spatial context of local features. The CDS function is defined as the fixed-point of three terms: (i) an energy function which balances a fidelity term; (ii) a context criterion; (iii) an entropy term. Using the CDS kernel, the geometric layout of local regions can be compared across images which show adjacent and repeating local structures as often in the case of graphic logos. The solution is proved to be highly effective and responds to the requirements of logo detection and recognition in real world images. MICC-Logos dataset is used for the experiments.
You are here: Home / ieee projects 2013 / Context-Dependent Logo Matching and Recognition CDS Logo Detection and Recognition