Dataset for classification of handwritten and printed text in a Doctor's prescription

Citation Author(s):
Jadavpur University
Jadavpur University
Pawan Kumar
Jadavpur University
Jadavpur University
Submitted by:
Avishek Garain
Last updated:
Sun, 08/29/2021 - 06:26
Data Format:
2 ratings - Please login to submit your rating.


Optical Character Recognition (OCR) system is used to convert the document images, either printed or handwritten, into its electronic counterpart. But dealing with handwritten texts is much more challenging than printed ones due to erratic writing style of the individuals. Problem becomes more severe when the input image is doctor's prescription. Before feeding such image to the OCR engine, the classification of printed and handwritten texts is a necessity as doctor's prescription contains both handwritten and printed texts which are to be processed separately. Much work have been done in the domain of handwritten and printed text separation albeit work related to doctor's handwriting. This dataset consists of various localized and extracted images of handwritten and printed texts from various prescriptions of doctors.

The images are categorized into 4 categories namely:

  1. Handwritten
  2. Mixed
  3. Other
  4. Printed

There are 11340 images in total after using augmentation techniques. Our model has achieved 99.5% accuracy in classifying the images. The publication link for the same will be added soon. To try out the gui for the same visit:

If you are unable to access the dataset drop a mail at

Please cite the dataset and research paper if it comes to any use.

Link to research paper:


The images are already sorted in 4 different folders. Just download and use. 


For selecting Bibtex contents, double click on IEEE contents. Then use Ctrl+C to copy. It's a bug and we need to wait till its fixed. Till then this is how you can cite.

Submitted by Avishek Garain on Tue, 10/06/2020 - 03:42

The bug has been fixed.

Submitted by Avishek Garain on Tue, 11/24/2020 - 05:09

I have subscribed IEEE, but i couldn't access your dataset. Can you help me on that?

Thank you

Submitted by Kishan Rajendra on Fri, 08/25/2023 - 00:51