Name
Title | ||
|---|---|---|
Handwritten digit recognition with a novel vision model that extracts linearly separable features |
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 |
Year | DOI | Venue |
|---|---|---|
2000 | 10.1109/CVPR.2000.854742 | CVPR |
Keywords | Field | DocType |
vision model,handwritten digit recognition,biological vision,large training set,feature extraction,linearly separable features,handwritten character recognition,linear classifier,digit recognition,handwriting recognition,algorithm design and analysis,computer vision,neural networks,biological systems | Neocognitron,Linear separability,MNIST database,Computer science,Feature (machine learning),Artificial intelligence,Intelligent word recognition,Computer vision,Pattern recognition,Intelligent character recognition,Feature extraction,Speech recognition,Linear classifier | Conference |
Volume | Issue | ISSN |
2 | 1 | 1063-6919 |
ISBN | Citations | PageRank |
0-7695-0662-3 | 5 | 3.54 |
References | Authors | |
11 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Loo-Nin Teow | 1 | 103 | 17.29 |
| Kia-Fock Loe | 2 | 180 | 20.88 |