This task uses the dataset of Bangla graphemes published by kaggle. Grapheme images are first resized and then converted into gray scale images. The images are then binarized by applying otsu image thresholding. The binarized images are employed into a CNN consisting softmax function in the last layer. Convolution, global average and dropout layers are inserted in the middle of the network.
-
Notifications
You must be signed in to change notification settings - Fork 0
This task uses the dataset of Bangla graphemes published by kaggle. Grapheme images are first resized and then converted into gray scale images. The images are then binarized by applying otsu image thresholding. The binarized images are employed into a CNN consisting softmax function in the last layer. Convolution, global average and dropout lay…
yeasmin62/Bangla-Grepheme-Classification-using-CNN
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
About
This task uses the dataset of Bangla graphemes published by kaggle. Grapheme images are first resized and then converted into gray scale images. The images are then binarized by applying otsu image thresholding. The binarized images are employed into a CNN consisting softmax function in the last layer. Convolution, global average and dropout lay…
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published