The Community for Technology Leaders
Green Image
Issue No. 07 - July (2012 vol. 34)
ISSN: 0162-8828
pp: 1312-1328
João Carreira , University of Bonn, Bonn
Cristian Sminchisescu , University of Bonn, Bonn
We present a novel framework to generate and rank plausible hypotheses for the spatial extent of objects in images using bottom-up computational processes and mid-level selection cues. The object hypotheses are represented as figure-ground segmentations, and are extracted automatically, without prior knowledge of the properties of individual object classes, by solving a sequence of Constrained Parametric Min-Cut problems (CPMC) on a regular image grid. In a subsequent step, we learn to rank the corresponding segments by training a continuous model to predict how likely they are to exhibit real-world regularities (expressed as putative overlap with ground truth) based on their mid-level region properties, then diversify the estimated overlap score using maximum marginal relevance measures. We show that this algorithm significantly outperforms the state of the art for low-level segmentation in the VOC 2009 and 2010 data sets. In our companion papers [1], [2], we show that the algorithm can be used, successfully, in a segmentation-based visual object category recognition pipeline. This architecture ranked first in the VOC2009 and VOC2010 image segmentation and labeling challenges.
Image segmentation, figure-ground segmentation, learning.

C. Sminchisescu and J. Carreira, "CPMC: Automatic Object Segmentation Using Constrained Parametric Min-Cuts," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 1312-1328, 2011.
162 ms
(Ver 3.3 (11022016))