Object Recognition by a Hopfield Neural Network
Abstract
A model-based recognition method is introduced which is formulated as an optimization problem. An energy function is derived which represents the constraints on the best solution in order to find the best match. A two-dimensional binary Hopfield neural network is implemented to minimize the energy function. The state of each neuron in the Hopfield network represents the possibility of a match between a node in the model graph and a node in the scene graph. >
Cite
Text
Nasrabadi et al. "Object Recognition by a Hopfield Neural Network." IEEE/CVF International Conference on Computer Vision, 1990. doi:10.1109/ICCV.1990.139542Markdown
[Nasrabadi et al. "Object Recognition by a Hopfield Neural Network." IEEE/CVF International Conference on Computer Vision, 1990.](https://mlanthology.org/iccv/1990/nasrabadi1990iccv-object/) doi:10.1109/ICCV.1990.139542BibTeX
@inproceedings{nasrabadi1990iccv-object,
title = {{Object Recognition by a Hopfield Neural Network}},
author = {Nasrabadi, Nasser M. and Li, Wei and Choo, Chang Y.},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {1990},
pages = {325-328},
doi = {10.1109/ICCV.1990.139542},
url = {https://mlanthology.org/iccv/1990/nasrabadi1990iccv-object/}
}