Florent Perronnin, Gabriela Csurka, Luca Marchesotti, Yan Liu, Marco Bressan
IEVC (Image Electronics and Visual Computing), Nice, France, 5-7 March 2010
Within the field of pattern analysis, the Fisher kernel is a powerful framework which combines the strengths of generative and discriminative approaches. The idea is to represent a signal with a gradient vector derived from a generative probability model. We used this framework to describe the content of images. In our case, the input signal is one or multiple low-level local feature vectors extracted from the image and the underlying generative model is a Gaussian mixture model which approximates the distribution of low-level features in any image. We will explain how we successfully applied this idea to several image analysis problems including image categorization (i.e. annotation), image semantic segmentation and image thumbnailing.
Report number: