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.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Segmentation by minimal description


    Contributors:
    Darrell, T. (author) / Sclaroff, S. (author) / Pentland, A. (author)


    Publication date :

    1990-01-01


    Size :

    424512 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    SELF-SUPERVISED MAP-SEGMENTATION BY MINING MINIMAL-MAP-SEGMENTS

    Kanji, Tanaka | British Library Conference Proceedings | 2020



    Aeroelastic Control and Estimation with a Minimal Nonlinear Modal Description

    Artola, Marc / Goizueta, Norberto / Wynn, Andrew et al. | AIAA | 2021



    Page Segmentation Using the Description of the Background

    Antonacopoulos, A. | British Library Online Contents | 1998