## January 5, 2021

• Improved math handwriting recognition
• Improved printed Romanian, Polish, Serbian, Ukrainian recogntion
• Added support for the following LaTeX characters:
\varsigma
\llcorner
\lrcorner
\uplus
\biguplus
\triangleright
\triangleleft
\dddot
\circledast
\rtimes
\ltimes
\supseteqq
\oiiint
\supsetneqq
\rightsquigarrow
\Vdash
\models


## November 12, 2020

Images like this now work in v3/text:
The goal of automatic rotation is to pick correct orientation for received images before any processing is done. The result of auto rotation looks like:
We will soon add these features to v3/latex and v3/batch as well. We implemented a very conservative rotation confidence threshold, meaning you should still try to call the API with a properly oriented image if possible!
API docs on autorotation:

## November 9, 2020

• v3/text general improvements
First of all, we trained our models on a larger dataset, resulting in a general accuracy increase.
Secondly, we improved the precision of predictions, at the potential cost of slightly decreasing prediction recall in some circumstances. Here is an example of an image, where previously our v3/text tried to read the bottom, cut off parts of the image:
Now, v3/text ignores these sections, resulting in a much cleaner output than before. The endpoint will still try to read everything in an image (vs the v3/latex endpoint which tries to read the main equation), but will be slightly less aggressive in reading unusual image sections in order to avoid garbage outputs.
• chemistry diagram detection
We have added a new field in our LineData object, subtype, so that we can return more information about diagrams to API clients. Currently subtype can only be chemistry, but more diagram subtypes are coming soon.
See an example request with chemistry: https://mathpix.com/docs/ocr/examples#chemistry-diagrams.
• added ability to create and disable new API keys to accounts.mathpix.com OCR dashboard
• added ability to invite users (to have access to API keys, usage statistics, image results dashboard) to accounts.mathpix.com OCR dashboard

## October 14, 2020

• Add support for the following characters:
«
»
\gtrless
\lessgtr
\nsucceq
\npreceq
\llbracket
\rrbracket
\curvearrowright
\curvearrowleft
№

• Improved accuracy on:
• Handwriting (math and text)
• Hindi language recognition (printed)
• Tables and matrices
• We now support backgroundless PNGs with alpha channels

## July 13, 2020

• Replace \dots with either \ldot or \cdot
• Predict empty braces when appropriate, like in Chemistry images (eg {}^)
• Fix v3/text bug where very wide lines of text were getting skipped
• Improved accuracy on handwritten math
• Improved accuracy on table predictions
• Improved accuracy on photo images of printed Hindi and Chinese text
• Add support for \mid predictions inside set notation
• Add support for the following languages: Czech, Turkish, Danish

## July 1, 2020

• Skip diagrams in v3/text which caused garbage results
Yet another reason to use v3/text over v3/latex! v3/text intelligently skips diagrams!