Skip to content

Handwritten Digit Classifiation using support vector machines.

Notifications You must be signed in to change notification settings

golu360/DigitRecognition-SVC

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

DigitRecognition-SVC

Handwritten Digit Classifiation using support vector machines.

Dependencies used:

OpenCV2

Scipy

ScikitLearn/SKlearn

Numpy

and some Standard libraries.

"generateClassifier.py" generates a recognition model after training.

"performRecognition.py" is used to classify the digits.(Takes two agrguments "-classifier" and "-i"(image)).

"mnist-original.mat" contains all the training data.

"deploy.bat" can be used to deploy the model.(already contains the path to the classifier,just need to add the argument for image path) Rest are example images.

Usage:

Use "python performRecognition.py -classifier(PATH TO CLASSIFIER) -i(PATH TO TEST IMAGE)

Might throw out some weird errors at first,properly edited images with a singular color background is advised to be used.

About

Handwritten Digit Classifiation using support vector machines.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published