An Expectation Maximization Approach to the Synergy Between Image Segmentation and Object Categorization
Abstract
In this work we deal with the problem of modelling and exploiting the interaction between the processes of image segmentation and object categorization. We propose a novel framework to address this problem that is based on the combination of the Expectation Maximization (EM) algorithm and generative models for object categories. Using a concise formulation of the interaction between these two processes, segmentation is interpreted as the E step, assigning observations to models, whereas object detection/analysis is modelled as the M-step, fitting models to observations. We present in detail the segmentation and detection processes comprising the E and M steps and demonstrate results on the joint detection and segmentation of the object categories of faces and cars. © 2005 IEEE.
Cite
Text
Kokkinos and Maragos. "An Expectation Maximization Approach to the Synergy Between Image Segmentation and Object Categorization." IEEE/CVF International Conference on Computer Vision, 2005. doi:10.1109/ICCV.2005.35Markdown
[Kokkinos and Maragos. "An Expectation Maximization Approach to the Synergy Between Image Segmentation and Object Categorization." IEEE/CVF International Conference on Computer Vision, 2005.](https://mlanthology.org/iccv/2005/kokkinos2005iccv-expectation/) doi:10.1109/ICCV.2005.35BibTeX
@inproceedings{kokkinos2005iccv-expectation,
title = {{An Expectation Maximization Approach to the Synergy Between Image Segmentation and Object Categorization}},
author = {Kokkinos, Iasonas and Maragos, Petros},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {2005},
pages = {617-624},
doi = {10.1109/ICCV.2005.35},
url = {https://mlanthology.org/iccv/2005/kokkinos2005iccv-expectation/}
}