type
status
date
slug
summary
tags
category
icon
password
URL
Rating
 
[English] | [中文版]
 
 
Pix2Text (P2T) uses the latest OCR technology to recognize mathematical formulas and text in images, converting mathematical formulas into pure Latex text representations. Pix2Text (P2T) aims to be a free open-source Python alternative to Mathpix. Currently, it has replicated the core functionalities of Mathpix, supporting the recognition of mixed images containing both text and formulas, returning results similar to those of Mathpix.

P2T Online Service

 
Everyone can use the P2T Online Service for free, with no limit on the number of uses under normal circumstances. However, please refrain from making bulk calls to the API. Machine resources are limited, and bulk calls can cause the service to become unavailable to others.
 

Available Models

P2T includes two kinds of models: Math Formula Detection (MFD) and Math Formula Recognition (MFR). For details, see the project description. By default, P2T uses free open-source models and will automatically download them when in use. Besides the free models, I will continue to optimize the models. The latest models require purchase for downloading and usage. If you are not deploying locally, it's recommended to directly use the P2T Online Service, as the Online Service always utilizes the most recent models.
 
The current models used in the Online Service are:
  • MFD: version-20230613
  • MFR: version-20230702
The paid models used in the Online Service perform better than the open-source models. If you need to deploy the P2T service on your own, it's advisable to purchase the same models used in the Online Service.
 
To thank our Planet Members for their support, all models are available at a 20% discount for Planet Members. To purchase, add the assistant as a friend, and after arranging payment, the assistant will provide the model files directly.
 
Things to note before purchasing:
📌
Make sure you've successfully run Pix2Text using the open-source models. Otherwise, after downloading the paid models, you might encounter problems getting them to work. Detailed installation and usage instructions can be found in the Pix2Text project documentation. If you face any issues, feel free to comment here or join the group chat to communicate with me. However, please note that helping you to get the code running is not within the services provided by the Planet host (refer to Planet Description).
📌
For personal use, please follow the column “Individual Purchase” of the tables; For business or commercial use, please follow the column “Commercial Purchase” of the tables, or contact the author (Email: breezedeus AT gmail.com).

Purchasing the Math Formula Detection (MFD) models

Available MFR models are listed in the table below. For detailed descriptions, see Pix2Text’s New YoloV7 MFD Model.
Model Version
Commercial Purchase
Individual Purchase
For Planet Members
Free Download
YoloV7_Tiny Open-source Model
✖️
✖️
✔️
✔️
version-20230208
✖️
✔️ Bilibili
✔️ Free
✖️
version-20230613
✔️ 20% off
✖️
 
Instructions after purchase can be found here.
 

Purchasing the Math Formula Recognition (MFR) models

Available MFR models are listed in the table below. For detailed descriptions, see Pix2Text’s New Formula Recognition Model.
Model Version
Commercial Purchase
Individual Purchase
For Planet Members
Free Download
Latex-OCR Open-source Model
✖️
✖️
✔️
✔️
version-20230702
✔️ 20% off
✖️
 
Instructions after purchase can be found here.
 
If you purchase both detection and recognition models, you'll need to set the path for the detection model as well as set the path for the recognition model. Here's how you can do it:
 

Code Repo

 
The free models will be downloaded automatically when necessary. You can also manually download the weights.pth and image_resizer.pth files from Baidu Cloud Drive. Then, place them in the ~/.pix2text/formula directory (on Windows, the default path is C:\Users\<username>\AppData\Roaming\pix2text\formula). The extraction code is p2t0. For detailed instructions, see the documentation in the above code repository.
 
 
📌
P2T uses CnOCR to recognize the text part in images. For more information on CnOCR, refer to this link.
 
Breezedeus
Breezedeus
Breezedeus
公告
type
status
date
slug
summary
tags
category
icon
password
URL
Rating
🎉CnOCR V2.3 新版发布🎉
-- 新版本特性 ---
CnOCR V2.3 新版模型精度比旧版模型更高。同时加入了分场景、大小规模不同的各种模型,可商用。
 
在线 Demo,欢迎体验