- Extract text from images or documents using Azure Cognitive Services OCR.
- Translate extracted text to multiple languages with the Azure Translator.
- Supports various image formats, including JPEG, PNG, and PDF.
- User-friendly interface for easy image upload and webcam capture.
- Seamless integration with Streamlit for interactive usage.
This project utilizes the following Azure Cognitive Services:
- Computer Vision OCR API: To perform optical character recognition and extract text from images or documents.
- Translator API: To provide translation services for the extracted text to multiple languages.
- App Services: To host the streamlit on azure portal.
The project uses the following Python libraries:
azure-cognitiveservices-vision-computervision: Python SDK for Azure Computer Vision.requests: For making HTTP requests to the Azure Translator API.streamlit: For creating the user interface and interactive web app.opencv-python: For capturing and processing images from the webcam.#created/requirements.txt
- Clone the repository:
git clone https://github.com/yourusername/your-repo.git
cd your-repo- Install the required dependencies:
pip install -r requirements.txt- Run the Streamlit app:
streamlit run main_script.py- Select the capture method (webcam or upload image) and follow the on-screen instructions to extract and translate text.
This project is licensed under the MIT License - see the LICENSE file for details.