Computer Science Colloquium, 2007-2008

Lihi Zelnik
Technion
February 27, 2008

Title: Recognizing image segmentation

Abstract:

Looking at an image, which one comes first: segmentation or recognition? We propose a probabilistic framework for carrying out the two simultaneously. The framework combines an LDA ‘bag of visual words’ model for recognition, and a hybrid parametric-nonparametric model for image segmentation. If applied to a collection of images, our framework can simultaneously and synergistically discover the segments of each image, that correspond to object parts that appear in the image collection. Thus, the model may be used for learning new categories, detecting/classifying objects, and segmenting images.

Joint work with Marco Andreetto and Pietro Perona.
 

 


Benny Pinkas