Improvements on Gabor Descriptor Retrieval for Patch Detection

Authors

  • Szidónia Lefkovits Department of Mathematics-Computer Science, "Petru Maior" University, 540088 Tîrgu-Mureş

Keywords:

Local descriptor, 2D Gabor wavelets, fine-tuning parameters, response map, GentleBoost, part-based object model, acceleration algorithm, LoG interest points, mutual information

Abstract

The localization of object parts in the component-based object detection is among the main tasks to solve. This paper presents several improvements of the proposed local image descriptor based on Gabor wavelets. Including these descriptors in the desired application is an ambitious challenge if we take into account the high number of parameters. Determining of parameters can be very hard because of their infinite definition range. Defining the filters is done in two stages: a theoretical consideration narrows the domain and the cardinality of parameters; this is followed by adequate experiments to select the most characteristic descriptor for a target image patch. The descriptor is created from a given number of 2D Gabor filters chosen by the GentleBoost learning algorithm. Comparing the proposed descriptor to those found in the state of the art, we can conclude that the selected filters are adaptable to any target object. In contrast to this, the majority of filter-based descriptors have fixed values for the parameters that do not allow to be ductile to the given object. Parameters fine-tuning allows the descriptor to be general, and discriminative at the same time. The effect of the following experiments has been analyzed during the investigation: elimination of redundancy between the weak classifiers, using the LoG interest points in the detection process. Finally, we propose an acceleration algorithm in order to deter- mine the response map faster. By means of the descriptor, the response map is created, which accurately localizes the target object part and can easily be integrated in almost all detection systems.

Downloads

Download data is not yet available.

Author Biography

Szidónia Lefkovits, Department of Mathematics-Computer Science, "Petru Maior" University, 540088 Tîrgu-Mureş

Szidonia Lefkovits is a Ph.D. in Computer Science at the Babes-Bolyai University Cluj-Napoca (Romania) since 2008. Currently she works as senior lecturer at the Department of Mathematics-Computer Science of the Petru Maior University Tirgu-Mures (Romania) since 2008. She received her electrical engineering degree in computer science in 2009 at the Sapientia University Tirgu-Mures (Romania) and at the same time graduated in mathematics and computer science in 2008 at Petru Maior University Tirgu-Mures. She is the author of over 20 scientific papers and is reviewer for several international conferences. Her topics of interest include, but are not limited to, computer vision, object detection, image processing and pattern recognition, databases, programming techniques, data structures.

Downloads

Published

2016-03-02

How to Cite

Lefkovits, S. (2016). Improvements on Gabor Descriptor Retrieval for Patch Detection. Computing and Informatics, 34(6), 1374–1396. Retrieved from https://www.cai.sk/ojs/index.php/cai/article/view/1001