Constrained parametric min-cuts for automatic object segmentation

• Published in: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition pp. 3241 - 3248
• Main Authors: Carreira, Joao, Sminchisescu, Cristian
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2010
• Subjects: Computer vision; Humans; Image segmentation; Machine learning; Machine learning algorithms; Mathematics; Numerical simulation; Object segmentation; Predictive models

We present a novel framework for generating and ranking plausible objects hypotheses in an image using bottom-up processes and mid-level cues. The object hypotheses are represented as figure-ground segmentations, and are extracted automatically, without prior knowledge about properties of individual...