A novel solution for logo detection and recognition based on CDS

  M.ARUN KUMAR,  S. Murugaanandam

In this technical demonstration, we present a new solution for logo detection and recognition which is based on the definition of a ―Context-Dependent Similarity‖ (CDS) kernel that directly incorporates the spatial context of local features. The proposed method is model-free, i.e. it is not restricted to any a earlier alignment model. Context is considered with respect to each single SIFT key point Formally, 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. The fidelity term is inversely proportional to the expectation of the Euclidean distance between the most likely aligned interest points. The context criterion measures the spatial coherence of the alignments. The entropy term acts as a smoothing factor, assuming that with no a earlier knowledge, the joint probability distribution of alignment scores is flat.

Keywords- Local features, special context, spatial coherence, interest points.

Unique Identification Number - IJEDR1401186
Page Number(s) - 1041-1043
Pubished in - Volume 2 | Issue 1 | March 2014
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  M.ARUN KUMAR,  S. Murugaanandam,   "A novel solution for logo detection and recognition based on CDS", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.2, Issue 1, pp.1041-1043, March 2014, Available at :http://www.ijedr.org/papers/IJEDR1401186.pdf