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

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: https://garain.github.io/Authentication/prescription

If you are unable to access the dataset drop a mail at avishekgarain@gmail.com.

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

Link to research paper:

https://doi.org/10.1007/s11042-020-10151-w