MNIST to recognize handwritten word

Question

The model can now recognize only single letter with tf. How can I make it recognize for sequential letters words?

I think this would be a better fit for [datascience.se]? – Ken Y-N Dec 25 '19 at 08:25 — Ken Y-N, Dec 25 '19 at 08:25

score 0 · Answer 1 · answered Dec 25 '19 at 08:29

0

Handwritten Digit Recognition. ... MNIST is a widely used dataset for the hand-written digit classification task. It consists of 70,000 labeled 28x28 pixel grayscale pix of hand-written digits. The dataset is split into 60,000 education images and 10,000 test images.

answered Dec 25 '19 at 08:29

Carm

1

so how can i do it for words – sajifo7994 Dec 25 '19 at 08:54

score 0 · Answer 2 · answered Dec 25 '19 at 13:35

Depending on the quality and types of images, the difficulty of the task various. If you were to do text detection in natural scenes, it is quite difficult and requires multiple models, there are plenty of research papers in this area. And lots of Kaggle notebooks. This link (a good read), explains the various factors to take into account and why it is so difficult, also shares his implementation.

If you are trying to identify text in a simple binary image, then this might help Separate image of text into component character images

MNIST to recognize handwritten word

2 Answers2