Learning Recognition and Segmentation of 3-D Objects from 2-D Images
Abstract
A framework called Cresceptron is introduced for automatic algorithm design through learning of concepts and rules, thus deviating from the traditional mode in which humans specify the rules constituting a vision algorithm. With the Cresceptron, humans as designers need only to provide a good structure for learning, but they are relieved of most design details. The Cresceptron has been tested on the task of visual recognition by recognizing 3-D general objects from 2-D photographic images of natural scenes and segmenting the recognized objects from the cluttered image background. The Cresceptron uses a hierarchical structure to grow networks automatically, adaptively, and incrementally through learning. The Cresceptron makes it possible to generalize training exemplars to other perceptually equivalent items. Experiments with a variety of real-world images are reported to demonstrate the feasibility of learning in the Cresceptron.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Cite
Text
Weng et al. "Learning Recognition and Segmentation of 3-D Objects from 2-D Images." IEEE/CVF International Conference on Computer Vision, 1993. doi:10.1109/ICCV.1993.378228Markdown
[Weng et al. "Learning Recognition and Segmentation of 3-D Objects from 2-D Images." IEEE/CVF International Conference on Computer Vision, 1993.](https://mlanthology.org/iccv/1993/weng1993iccv-learning/) doi:10.1109/ICCV.1993.378228BibTeX
@inproceedings{weng1993iccv-learning,
title = {{Learning Recognition and Segmentation of 3-D Objects from 2-D Images}},
author = {Weng, John (Juyang) and Ahuja, Narendra and Huang, Thomas S.},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {1993},
pages = {121-128},
doi = {10.1109/ICCV.1993.378228},
url = {https://mlanthology.org/iccv/1993/weng1993iccv-learning/}
}