The authors formulate the segmentation task as a search for a set of descriptions which minimally encodes a scene. A novel framework for cooperative robust estimation is used to estimate descriptions that locally provide the most savings in encoding an image. A modified Hopfield-Tank networks finds the subset of these descriptions which best describes an entire scene, accounting for occlusion and transparent overlap among individual descriptions. Using a part-based 3-D shape model the authors have implemented a system that is able to successfully segment images into their constituent structure.<>
Segmentation by minimal description
1990-01-01
424512 byte
Conference paper
Electronic Resource
English
SELF-SUPERVISED MAP-SEGMENTATION BY MINING MINIMAL-MAP-SEGMENTS
British Library Conference Proceedings | 2020
|Page Segmentation Using the Description of the Background
British Library Online Contents | 1998
|