Approximate nearest neighbors for recognition of foreground and background in images and video

Author

Josh Allmann

Abstract

Problems in image matching, saliency detection in images, and background detection in video are studied. Algorithms based on approximate nearest-neighbor matching are proposed to solve problems in these related domains. Image patches are quantized into features using a special Walsh-Hadamard transform, and put into a propagation-assisted kd-tree for indexing and search. Image saliency and background-detection algorithms are then derived by looking at patch similarity over time and space.

Library of Congress Subject Headings

Nearest neighbor analysis (Statistics); Image processing--Digital techniques; Computer vision--Data processing; Optical pattern recognition

Publication Date

8-9-2013

Document Type

Thesis

Department, Program, or Center

Computer Science (GCCIS)

Advisor

Gaborski, Roger

Comments

Note: imported from RIT’s Digital Media Library running on DSpace to RIT Scholar Works. Physical copy available through RIT's The Wallace Library at: QA278.2 .A55 2013

Recommended Citation

Allmann, Josh, "Approximate nearest neighbors for recognition of foreground and background in images and video" (2013). Thesis. Rochester Institute of Technology. Accessed from
https://repository.rit.edu/theses/5513

Campus

RIT – Main Campus

Plan Codes

COMPSCI-MS