University of Illinois Urbana-Champaign

Hand detection on images based on deformable part models and additional features

Crisostomo Romero, Pedro Moises

Content Files
CrisostomoRomero-PedroMoises.pdf

CrisostomoRomero-PedroMoises.pdf

Download File Copy Link To File
Format
Portable Document Format
Media Type
application/pdf
Size
1.17 MB
API Resource
/items/25171/bitstreams/86733
Bundle
Content
Primary
NO
Downloads
954

Permalink

https://hdl.handle.net/2142/24270

Description

Title
Hand detection on images based on deformable part models and additional features
Author(s)
Crisostomo Romero, Pedro Moises
Issue Date
2011-05-25T15:08:06Z
Director of Research (if dissertation) or Advisor (if thesis)
Forsyth, David A.
Department of Study
Computer Science
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Date of Ingest
2011-05-25T15:08:06Z
Keyword(s)
  • Hand detection
  • computer vision
  • machine learning
  • deformable models
  • PASCAL Visual Object Classes (VOC)
  • frequency features
  • color features
  • Pattern Analysis Statistical Modeling and Computational Learning (PASCAL)
Abstract
Hand detection on images has important applications on person activities recognition. This thesis focuses on PASCAL Visual Object Classes (VOC) system for hand detection. VOC has become a popular system for object detection, based on twenty common objects, and has been released with a successful deformable parts model in VOC2007. A hand detection on an image is made when the system gets a bounding box which overlaps with at least 50% of any ground truth bounding box for a hand on the image. The initial average precision of this detector is around 0.215 compared with a state-of-art of 0.104; however, color and frequency features for detected bounding boxes contain important information for re-scoring, and the average precision can be improved to 0.218 with these features. Results show that these features help on getting higher precision for low recall, even though the average precision is similar.
Graduation Semester
2011-05
Permalink
http://hdl.handle.net/2142/24270
Copyright and License Information
Copyright 2011 Pedro Crisostomo

Owning Collections

Dissertations and Theses - Computer Science
Dissertations and Theses from the Siebel School of Computer Science
Graduate Dissertations and Theses at Illinois PRIMARY
Graduate Theses and Dissertations at Illinois