A Hybrid Trademark Retrieval System Using Four-Gray-Level Zernike Moments and Image Compactness Indices

There are just too many trademarks out there so that a good automated retrievalsystem is required to help to protect them from possible infringements. However,it is from people, i.e., the general consumers' viewpoint how similar or confusingtwo trademarks can be. Thus, in this paper we propose a hybrid system wherewe patently incorporate human inputs into a computerized trademark retrievalscheme. Various surveys involving general consumers' cognition and responsesare conducted, and the results are used as benchmarks in developing theautomated part. The core mathematical features used in the scheme are fourgray-level Zernike moments and two new image compactness indices.Experimental results show that this hybrid system, when compared with humangeneratedresults, is able to achieve an average accuracy rate of 95% while thatof the closest competing existing method is 65%.