Contact

Email me at: itsawesome17@gmail.com
My blog: http://blog.mathocr.com/

Content

Dataset consists of jpg files(45×45)
DISCLAIMER: dataset does not contain Hebrew alphabet at all. It includes basic Greek alphabet symbols like: alpha, beta, gamma, mu, sigma, phi and theta.
English alphanumeric symbols are included.
All math operators, set operators.
Basic pre-defined math functions like: log, lim, cos, sin, tan.
Math symbols like: \int, \sum, \sqrt, \delta and more.

Acknowledgements

Original source, that was parsed, extracted and modified is CROHME dataset.
Visit CROHME at http://www.isical.ac.in/~crohme/index.html.

Inspiration

Due to the technological advances in recent years, paper scientific documents are used less and less. Thus, the trend in the scientific community to use digital documents has increased considerably. Among these documents, there are scientific documents and more specifically mathematics documents. So I give a tool, to research recognizing handwritten math language in variety of applications.

Source code

You can find source code responsible for parsing original CROHME dataset here:

https://github.com/XaiNano/CROHME_extractor

This parser allows you not only to extract math symbols into square images of desired size, but also lets you specify categories of classes to be extracted like: digits, greekletters, lowercaseletters, operators, and more. It also contains visualization tools and histograms showing appearances of each class in the dataset.

Commercial use

Rights for commercial usage cannot be granted.

Size: 351042 KB Price: Free Author: Xai Nano Data source: kaggle.com

Handwritten math symbols dataset