0

I am trying to do handwriting character recognition using Tensorflow in Google-colab.

I have trained and tested model with an accuracy of 91%

I tried it on image given in the tutorial, and it worked correctly. it was 28*28 resized.

screenshot When I wanted to try it on my input-image, it is predicting wrong results as 2,3, but my input-image is of 'digit-6'.

the problem may be in image-operations and before passing to model.

screenshot

also, further I wanted to pass that image for realtime-recognition. I am doing resizing, inverting of the image, to make it compatible with my trained labels. OpenCV input image is represented opposite-notation of tensorflow labels, as the current matrix represents black as 0 and white as 255.

my GitHub Jupyter-notebook file is followed from tutorial of digitalocean's blog

How can I upload an image taken from a phone/webcam and recognize characters from that image? where I am making mistakes in processing image?

further, I wanted to pass that image in a project - real-time recognition of characters

testing images are

two.png

six.png

feedMe
  • 3,431
  • 2
  • 36
  • 61
GD- Ganesh Deshmukh
  • 1,456
  • 3
  • 24
  • 36

1 Answers1

0

do you know Mnist data set is restricted with padding of images?

appropriate realtime image processing is needed.

This is useful article about that

https://link.medium.com/0ySCmyMpzU

and following is my project about simple mnist game

https://github.com/mym0404/Math-Writer

MJ Studio
  • 3,947
  • 1
  • 26
  • 37
  • thanks MJ_Studio, Yes I know MNIST is deprecated. but It actually predicted correctly using `pillow-library`, but I think the problem is with input-image-dimensions. also I have added this details to question. BTW your project is nice. – GD- Ganesh Deshmukh Feb 24 '19 at 14:27