I’ve presented a paper “Content-based Retrieval of Images for Cultural Institutions using Local Descriptors” in the Conference Geometric Modelling and Imaging — New Trends — GMAI 2006.
This was the first paper published about my thesis results, in a moment were I was convinced that local descriptors were “the way to go” but wasn’t still sure of how I would address their performance issues — by choosing smaller (low-dimensional) descriptors? Trying to reduce the dimensionality of the descriptors I had already chosen? Reducing the number of descriptors in the database? In the query? All those avenues seemed reasonable at the time.
Here is the abstract: “The task of identifying an image whose metadata are missing is often demanded from cultural image collections holders, such as museums and archives. The query image may present distortions (cropping, rescaling rotations, colour changes, noise…) from the original, which poses an additional complication. The majority of proposed solutions are based on classic image signatures, such as the colour histogram. Our approach, however, follows computer vision methods, and is based on local descriptors. In this paper we describe our approach, explain the SIFT method on which it is based and compared it to the Multiscale-CCV, an established scheme employed in a large scale practical
system. We demonstrate experimentally the efficacy of our approach, which achieved a 99,2% success rate, against 61,0% for the Multiscale-CCV, in a database of photos, drawings and paintings.”
The fulltext of the paper and related material can be found in my publications page.