ML Anthology

Handwritten Digit Recognition with a Novel Vision Model That Extracts Linearly Separable Features

Loo-Nin Teow, Kia-Fock Loe
CVPR 2000 pp. 2076-2082
doi:10.1109/CVPR.2000.854742 /cvpr/2000/teow2000cvpr-handwritten/

Abstract

We use well-established results in biological vision to construct a novel vision model for handwritten digit recognition. We show empirically that the features extracted by our model are linearly separable over a large training set (MNIST). Using only a linear classifier on these features, our model is relatively simple yet outperforms other models on the same data set.

CVPR Semantic Scholar

Cite

Text

Teow and Loe. "Handwritten Digit Recognition with a Novel Vision Model That Extracts Linearly Separable Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.854742

Markdown

[Teow and Loe. "Handwritten Digit Recognition with a Novel Vision Model That Extracts Linearly Separable Features." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/teow2000cvpr-handwritten/) doi:10.1109/CVPR.2000.854742

BibTeX

@inproceedings{teow2000cvpr-handwritten,
  title     = {{Handwritten Digit Recognition with a Novel Vision Model That Extracts Linearly Separable Features}},
  author    = {Teow, Loo-Nin and Loe, Kia-Fock},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2000},
  pages     = {2076-2082},
  doi       = {10.1109/CVPR.2000.854742},
  url       = {https://mlanthology.org/cvpr/2000/teow2000cvpr-handwritten/}
}