--- title: "IndicPhotoOCR" colorFrom: "purple" colorTo: "pink" sdk: "gradio" python_version: "3.9" sdk_version: "4.44.0" app_file: app.py pinned: True CPU: "cpu-basic" suggested_storage : "small" app_port: 7865 ---

BharatOCR Logo

IndicPhotoOCR - Comprehensive Scene Text Recognition Toolkit
across 13 Indian Languages

![Open Source](https://img.shields.io/badge/Open%20Source-Bhashini-FF6C00) [![Hits](https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fgithub.com%2FBhashini-IITJ%2FBharatOCR&count_bg=%233D48C8&title_bg=%23555555&icon=&icon_color=%0C0983&title=hits&edge_flat=false)](https://hits.seeyoufarm.com) [![GitHub stars](https://img.shields.io/github/stars/Bhashini-IITJ/BharatOCR.svg?style=social&label=Star&color=orange)](https://github.com/Bhashini-IITJ/BharatOCR/stargazers) ![GitHub forks](https://img.shields.io/github/forks/Bhashini-IITJ/BharatOCR?style=social) [![Hugging Face](https://img.shields.io/badge/Hugging_Face-Demo-FF6C00?logo=Huggingface&logoColor=white)](https://huggingface.co/spaces/anikde/BharatOCR)
IndicPhotoOCR is an advanced OCR toolkit designed for detecting, identifying, and recognizing text across 13 Indian languages, including Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Meitei Odia, Punjabi, Tamil, Telugu, Urdu, and English. Built to handle the unique scripts and complex structures of Indian languages, IndicPhotoOCR provides robust detection and recognition capabilities, making it a valuable tool for processing multilingual documents and enhancing document analysis in these diverse scripts. ![](static/pics/visualizeIndicPhotoOCR.png)
## Table of Content [Updates](https://github.com/Bhashini-IITJ/BharatOCR/blob/main/README.md#updates)
[Installation](https://github.com/Bhashini-IITJ/BharatOCR/blob/main/README.md#installation)
[How to use](https://github.com/Bhashini-IITJ/BharatOCR/blob/main/README.md#how-to-use)
[Acknowledgement](https://github.com/Bhashini-IITJ/BharatOCR/blob/main/README.md#acknowledgement)
[Contact us](https://github.com/Bhashini-IITJ/BharatOCR/blob/main/README.md#contact-us)
## Updates [November 2024]: Try demo in [huggingface space](https://huggingface.co/spaces/anikde/BharatOCR).\ [November 2024]: Use this package in [Google Colab](https://colab.research.google.com/drive/1BILXjUF2kKKrzUJ_evubgLHl2busPiH2?usp=sharing).\ [November 2024]: Added support for [10 languages](#config) in the recognition module.
[September 2024]: Private repository created.
## Installation Currently we need to manually create virtual environemnt. ```python conda create -n indicphotoocr python=3.9 -y conda activate indicphotoocr git clone https://github.com/Bhashini-IITJ/IndicPhotoOCR.git cd IndicPhotoOCR ```
CPU Installation ```bash python setup.py sdist bdist_wheel pip install dist/IndicPhotoOCR-1.1.0-py3-none-any.whl[cpu] ```
CUDA 11.8 Installation ```bash python setup.py sdist bdist_wheel pip install ./dist/IndicPhotoOCR-1.1.0-py3-none-any.whl[cu118] --extra-index-url https://download.pytorch.org/whl/cu118 ```
CUDA 12.1 Installation ```bash python setup.py sdist bdist_wheel pip install ./dist/IndicPhotoOCR-1.1.0-py3-none-any.whl[cu121] --extra-index-url https://download.pytorch.org/whl/cu121 ```

If you find any trouble with the above installation use the ```setup.sh``` script. ```bash chmod +x setup.sh ./setup.sh ``` ## Config Currently this model works for hindi v/s english script identification and thereby hindi and english recognition. Detection Model: EAST\ ScripIndetification Model: Hindi v/s English\ Recognition Model: Hindi, English, Assamese, Bengali, Gujarati, Marathi, Odia, Punjabi, Tamil, Telugu. ## How to use ### Detection ```python >>> from IndicPhotoOCR.ocr import OCR # Create an object of OCR >>> ocr_system = OCR(verbose=True) # for CPU --> OCR(device="cpu") # Get detections >>> detections = ocr_system.detect("test_images/image_141.jpg") # Running text detection... # 4334 text boxes before nms # 1.027989387512207 # Save and visualize the detection results >>> ocr_system.visualize_detection("test_images/image_141.jpg", detections) # Image saved at: test.png ``` ## Cropped Word Recognition ```python >>> from IndicPhotoOCR.ocr import OCR # Create an object of OCR >>> ocr_system = OCR(verbose=True) # for CPU --> OCR(device="cpu") # Get recognitions >>> ocr_system.recognise("test_images/cropped_image/image_141_0.jpg", "hindi") # Recognizing text in detected area... # 'मण्डी' ``` ## End-to-end Scene Text Recognition ```python >>> from IndicPhotoOCR.ocr import OCR # Create an object of OCR >>> ocr_system = OCR(verbose=True) # for CPU --> OCR(device="cpu") # Complete pipeline >>> ocr_system.ocr("test_images/image_141.jpg") # Running text detection... # 4334 text boxes before nms # 0.9715704917907715 # Identifying script for the cropped area... # Recognizing text in detected area... # Recognized word: रोड # Identifying script for the cropped area... # Recognizing text in detected area... # Recognized word: बाराखम्ब # Identifying script for the cropped area... # Recognizing text in detected area... # Using cache found in /DATA1/ocrteam/.cache/torch/hub/baudm_parseq_main # Recognized word: barakhaml # Identifying script for the cropped area... # Recognizing text in detected area... # Recognized word: हाऊस # Identifying script for the cropped area... # Recognizing text in detected area... # Using cache found in /DATA1/ocrteam/.cache/torch/hub/baudm_parseq_main # Recognized word: mandi # Identifying script for the cropped area... # Recognizing text in detected area... # Using cache found in /DATA1/ocrteam/.cache/torch/hub/baudm_parseq_main # Recognized word: chowk # Identifying script for the cropped area... # Recognizing text in detected area... # Recognized word: मण्डी # Identifying script for the cropped area... # Recognizing text in detected area... # Using cache found in /DATA1/ocrteam/.cache/torch/hub/baudm_parseq_main # Recognized word: road # Identifying script for the cropped area... # Recognizing text in detected area... # Using cache found in /DATA1/ocrteam/.cache/torch/hub/baudm_parseq_main # Recognized word: house # Identifying script for the cropped area... # Recognizing text in detected area... # Using cache found in /DATA1/ocrteam/.cache/torch/hub/baudm_parseq_main # Recognized word: rajiv # Identifying script for the cropped area... # Recognizing text in detected area... # Recognized word: राजीव # Identifying script for the cropped area... # Recognizing text in detected area... # Recognized word: चौक ``` ## Acknowledgement Text Recognition - [PARseq](https://github.com/baudm/parseq)\ EAST re-implemenation [repository](https://github.com/foamliu/EAST).
National Language Translation Mission [Bhashini](https://bhashini.gov.in/). ## Contact us For any queries, please contact us at: - [Anik De](mailto:anekde@gmail.com)