Skip to content

Yuanhao-JIANG/ml-handwriting-recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ml-handwriting-recognition

A handwriting recognition project with CNN structure (LeNet).

By default, it uses MNIST dataset to train. The trained model is saved in the ./saved_model directory by default.

To use the model, use the use_model.py file, it by default recognize the images saved in the ./imgs directory, and generate output to the file ./output.txt with the format "img_path -> number \n"

As an example:

image of number 1 image of number 2 image of number 3

gives output:

./imgs/1.png -> 1
./imgs/2.png -> 2
./imgs/3.png -> 3

Note that the images should have black background and their number written in white color, and resized to the dimension 28x28 before using the model to recognize them.

About

A handwriting recognition project with CNN structure (LeNet)

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages