Image Translator is a web application that allows users to upload images containing text and translate that text into different languages. The application utilises optical character recognition (OCR) to detect text in the uploaded images, OpenCV to process the image and then uses DeepL API to translate the detected text.
To get a local copy up and running, follow these simple steps:
-
Clone the repo
git clone https://github.com/fsosn/Image-Translator.git
-
Install the dependencies
cd frontend npm installcd backend pip install -r requirements.txt -
Set up environment variables
- Create a
.envfile in the backend directory - Generate API key at DeepL
- Add your DeepL API key to the
.envfile in the following format:DEEPL_AUTH_KEY=your_deepl_api_key - Save the
.envfile
- Create a
-
Start the backend
flask run
-
Start the frontend
npm run dev
- Upload, paste or drag and drop an image containing text.
- Select the source and target languages.
- Click the "Translate" button to process the image and translate detected text.



