Skip to Main Content
 

Global Search Box

 
 
 
 

ETD Abstract Container

Abstract Header

View Invariant Planar-Object Recognition

Srestasathiern, Panu

Abstract Details

2008, Master of Science, Ohio State University, Geodetic Science and Surveying.
In many photogrammetry and computer vision applications, there ultimate goals is to recognize objects of interest. Various framework for object recognition problem have been developed. Among many framework, geometric invariances have been proven to be an efficient way to recognize object under geometric transformation i.e. affine transformation. Motivated by geometric invariance framework, we propose a new method for rec¬ognizing the isolated planar object under the circumstance of geometric transforma¬tion. Namely, we assume that object shape is deformed by projective transformation. Firstly, we present a new object’s shape representation based on an assumption that the boundary of the object’s shape can be approximately represented by a set of piecewise conics. Secondly, a new projective invariant feature is derived based on the distribution of the projective relations between the conic pairs, which are estimated from the objects shape. We hypothecate that two objects of the same type, which are viewed from different viewpoints generate similar histograms, such that the distance between these two histogram is smaller than the histograms generated from other object types. The proposed method has shown promising performance our shape database in which object’s shapes are deformed by projective transformation.
Alper Yilmaz (Advisor)
Anton F. Schenk (Committee Member)
116 p.

Recommended Citations

Citations

  • Srestasathiern, P. (2008). View Invariant Planar-Object Recognition [Master's thesis, Ohio State University]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=osu1420564069

    APA Style (7th edition)

  • Srestasathiern, Panu. View Invariant Planar-Object Recognition. 2008. Ohio State University, Master's thesis. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=osu1420564069.

    MLA Style (8th edition)

  • Srestasathiern, Panu. "View Invariant Planar-Object Recognition." Master's thesis, Ohio State University, 2008. http://rave.ohiolink.edu/etdc/view?acc_num=osu1420564069

    Chicago Manual of Style (17th edition)