Monash University
Browse
tr-2004-160-full.pdf (476.68 kB)

Principal Component Analysis for the Approximation of a Fruit as an Ellipse

Download (476.68 kB)
report
posted on 2022-08-29, 04:56 authored by S N R Wijewickrema, A P Paplinski
Principal component analysis (PCA) has been widely used in fields such as computer vision and image processing since its inception. Conceptually it describes the shape of a cluster of data starting with the direction in which there is most data variability. We investigate the novel idea of fitting an encapsulating ellipse to an image of a hypothetically ellipsoidal fruit using principal component analysis. This is achieved by representing the fruit as a distribution of data points in 2-D space, identifying the principal components and the variance of the data along the principal components, and determining the ellipse parameters using them.

History

Technical report number

2004/160

Year of publication

2004

Usage metrics

    Monash Information Technology Technical Reports

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC