Learning to Find Pictures of People
Abstract
Finding articulated objects, like people, in pictures present.s a par(cid:173) ticularly difficult object. recognition problem. We show how t.o find people by finding putative body segments, and then construct.(cid:173) ing assemblies of those segments that are consist.ent with the con(cid:173) straints on the appearance of a person that result from kinematic properties. Since a reasonable model of a person requires at. least nine segments, it is not possible to present every group to a classi(cid:173) fier. Instead, the search can be pruned by using projected versions of a classifier that accepts groups corresponding to people. We describe an efficient projection algorithm for one popular classi(cid:173) fier , and demonstrate that our approach can be used to determine whether images of real scenes contain people.
Cite
Text
Ioffe and Forsyth. "Learning to Find Pictures of People." Neural Information Processing Systems, 1998.Markdown
[Ioffe and Forsyth. "Learning to Find Pictures of People." Neural Information Processing Systems, 1998.](https://mlanthology.org/neurips/1998/ioffe1998neurips-learning/)BibTeX
@inproceedings{ioffe1998neurips-learning,
title = {{Learning to Find Pictures of People}},
author = {Ioffe, Sergey and Forsyth, David A.},
booktitle = {Neural Information Processing Systems},
year = {1998},
pages = {782-788},
url = {https://mlanthology.org/neurips/1998/ioffe1998neurips-learning/}
}