Shape Modeling and GPU Based Image Warping Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_projects/mk61rj50v

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • This project addresses the problems of manually placing facial landmarks on a portrait and finding a fast way to warp the annotated image of a face. While there are many approaches to automatically find facial landmarks, most of them provide insufficient results in uncontrolled environments. Thus I introduce a method to manually adjust a non-rigid shape on a portrait. This method utilizes a statistical shape model based on point distribution models. With these manually placed landmarks the image of a face can be warped into another shape. To warp the image I use a piecewise affine transformation. This way of transforming, however, tends to be computationally intense and therefore slow. Thus in the second part of the project I introduce a way to perform a piecewise affine transformation with enhanced performance using shaders in OpenGL. This project is made in collaboration with the Pedagogical University of Berne, Switzerland and will be part of a system for diversity research named chic-o-mat. Eventually the system will run on an iPhone as an application available to the public. Therefore, the provided solutions are based on iPhone programming using the multi-touch screen for the shape adjustment and the GPU of the latest iPhone 4S. A test application demonstrates up to 20X speedup performing piecewise warping using the GPU.
Resource Type
Date Available
Date Issued
Rights Statement
Peer Reviewed
Language
Replaces
Additional Information
  • description.provenance : Submitted by David Burri (burrid@onid.orst.edu) on 2012-08-22T08:15:18Z No. of bitstreams: 3 license_rdf: 19965 bytes, checksum: 225316337756db2af069c3edfe03a49f (MD5) license_text: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) MS_Project_Report_Revised_David_Burri.pdf: 4037397 bytes, checksum: e085de58cb0b09beede624acb15ab7ca (MD5)
  • description.provenance : Approved for entry into archive by Sue Kunda(sue.kunda@oregonstate.edu) on 2012-08-23T15:34:13Z (GMT) No. of bitstreams: 3 license_rdf: 19965 bytes, checksum: 225316337756db2af069c3edfe03a49f (MD5) license_text: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) MS_Project_Report_Revised_David_Burri.pdf: 4037397 bytes, checksum: e085de58cb0b09beede624acb15ab7ca (MD5)
  • description.provenance : Made available in DSpace on 2012-08-23T15:34:13Z (GMT). No. of bitstreams: 3 license_rdf: 19965 bytes, checksum: 225316337756db2af069c3edfe03a49f (MD5) license_text: 0 bytes, checksum: d41d8cd98f00b204e9800998ecf8427e (MD5) MS_Project_Report_Revised_David_Burri.pdf: 4037397 bytes, checksum: e085de58cb0b09beede624acb15ab7ca (MD5) Previous issue date: 2012-08-14

Relationships

In Administrative Set:
Last modified: 07/25/2017

Downloadable Content

Download PDF
Citations:

EndNote | Zotero | Mendeley

Items