Try the Model

Use the widget below to experiment with Surya. You can detect COCO classes such as people, vehicles, animals, household items.

Overview

Surya is a Python package designed for OCR on document layout analysis. It features multilingual support and layout identification of elements such as tables, images, and headers. It is open-sourced on GitHub with over 5,000 stars.

In benchmarks conducted by and published to the repository, it outperforms Tesseract on inference time and accuracy, as well as showing proficiency in layout recognition and analysis.

Surya License

Surya

is licensed under a

license.

Performance

Deploy a Surya API

You can use Roboflow Inference to deploy a

Surya

API on your hardware. You can deploy the model on CPU (i.e. Raspberry Pi, AI PCs) and GPU devices (i.e. NVIDIA Jetson, NVIDIA T4).

Below are instructions on how to deploy your own model API.

Label Data Automatically with Surya

You can automatically label a dataset using Surya with help from Autodistill, an open source package for training computer vision models. You can label a folder of images automatically with only a few lines of code. Below, see our tutorials that demonstrate how to use Surya to train a computer vision model.

No items found.