Title :
Learning scale ranges for the extraction of regions of interest
Author :
Qi Li ; Bessinger, Z.
Author_Institution :
Dept. of Math. & Comput. Sci., Western Kentucky Univ., Bowling Green, KY, USA
fDate :
Sept. 30 2012-Oct. 3 2012
Abstract :
Scale space has been widely used in various applications. Given an application, it is essential to decide optimal scales under a certain criterion. Subsampling a scale space is a popular scheme to reduce the search space and thus computational costs. In the context of the extraction of Regions of Interest, we will introduce an alternative scheme that aims to learn scale ranges from training images in order to reduce the search space. We test the proposed scheme in a case study of face localization, and obtain promising results.
Keywords :
feature extraction; image classification; image sampling; computational costs; learning scale ranges; optimal scales; region of interest extraction; scale space subsampling; training images; Context; Face; Face detection; Feature extraction; Lighting; Training; Vectors; Region of interest; classification; scale;
Conference_Titel :
Image Processing (ICIP), 2012 19th IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
978-1-4673-2534-9
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2012.6467426
