EigenSegments: A Spatio-Temporal Decomposition of an Ensemble of Images
Abstract
Eigensegments combine image segmentation and Principal Component Analysis (PCA) to obtain a spatio-temporal decomposition of an ensemble of images. The image plane is spatially decomposed into temporally correlated regions. Each region is independently decomposed temporally using PCA. Thus, each image is modeled by several low-dimensional segment-spaces, instead of a single high-dimensional image-space. Experiments show the proposed method gives better classification results, gives smaller reconstruction errors, can handle local changes in appearance and is faster to compute. Results for faces and vehicles are shown.
Cite
Text
Avidan. "EigenSegments: A Spatio-Temporal Decomposition of an Ensemble of Images." European Conference on Computer Vision, 2002. doi:10.1007/3-540-47977-5_49Markdown
[Avidan. "EigenSegments: A Spatio-Temporal Decomposition of an Ensemble of Images." European Conference on Computer Vision, 2002.](https://mlanthology.org/eccv/2002/avidan2002eccv-eigensegments/) doi:10.1007/3-540-47977-5_49BibTeX
@inproceedings{avidan2002eccv-eigensegments,
title = {{EigenSegments: A Spatio-Temporal Decomposition of an Ensemble of Images}},
author = {Avidan, Shai},
booktitle = {European Conference on Computer Vision},
year = {2002},
pages = {747-758},
doi = {10.1007/3-540-47977-5_49},
url = {https://mlanthology.org/eccv/2002/avidan2002eccv-eigensegments/}
}