Object recognition from range images using superquadric representations

Erik van Dop, Paul Regtien

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    4 Downloads (Pure)


    Segmentation of range images using superquadric entities has been pointed out by a number of researchers as a powerful approach towards object recognition. Problems exist in finding an unbiased decision function for the assignment of a superquadric representation with an object prototype. This paper discusses current distance measures between recovered models and prototypes and presents a novel method for classification of uncertain superquadric representations using a maximum likelihood criterium and incorporating the range image characteristics of an active optical triangulation sensor. The main advantage of this probabilistic method is its inherent minimisation of the classification error rate. The approach is applied to recognition of electronic components for printed circuit board waste management.
    Original languageEnglish
    Title of host publicationProceedings of MVA '96
    Subtitle of host publicationIAPR Workshop on Machine Vision Applications : November 12-14 1996, Tokyo, Japan
    Place of PublicationTokyo, Japan
    PublisherKeio University
    Publication statusPublished - 12 Nov 1996
    EventIAPR Workshop on Machine Vision Applications, MVA 1996 - Tokyo, Japan
    Duration: 12 Nov 199614 Nov 1996


    WorkshopIAPR Workshop on Machine Vision Applications, MVA 1996


    • METIS-113418

    Fingerprint Dive into the research topics of 'Object recognition from range images using superquadric representations'. Together they form a unique fingerprint.

    Cite this