Logo Retrieval using Rotated Complex Wavelet Filters
M. S. Shirdhonkar · International journal of imaging and robotics · 2013
This paper presents a new method for Logo retrieval using rotated complex wavelet filters (RCWF) and dual tree complex wavelet transform (DT-CWT) jointly for extracting details in twelve different directions of the logo image. We propose an efficient logo retrieval system which is able to retrieve logos by similarity from large databases of logo images. The performance of the system has been tested with a logo image database of 150 logos. From experimental results, we achieved a precision of 55% when considering the top 10 results. The experiments demonstrate the effectiveness and efficiency of the system on realistic datasets as the Flickr Logo 27 dataset.