Histogram of gradients is a highly accurate method of extracting features from the MNIST dataset for handwritten digits, however, due to the number of computations required, the efficiency of the model is in consideration. By using feature extraction on the MNIST dataset, the general performance of the Na¨ıve Bayesian classifier had shown to improve tremendously with the use of the Histogram of gradients although the results for the pixel intensity feature set were surprisingly low, as much as 5 times less than HOG
-
Notifications
You must be signed in to change notification settings - Fork 0
By using feature extraction on the MNIST dataset, the general performance of the Na¨ıve Bayesian classifier had shown to improve tremendously with the use of the Histogram of gradients although the results for pixel intensity feature set were surprisingly low, as much as 5 times less than HOG.
Craigels07/Na-ve-Bayesian-classifier
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
By using feature extraction on the MNIST dataset, the general performance of the Na¨ıve Bayesian classifier had shown to improve tremendously with the use of the Histogram of gradients although the results for pixel intensity feature set were surprisingly low, as much as 5 times less than HOG.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published