This project focuses on real-time word detection and recognition using the EasyOCR library. The system takes input as an image or live feed, processes it to detect and extract words, and outputs the detected text along with its location in the image. It is designed for applications like document digitization, text extraction from images, and real-time text recognition.
Detects and recognizes text from images and live video feeds.
Outputs detected words with bounding boxes.
Supports multiple languages for word detection.
Provides high accuracy and efficiency using the EasyOCR framework.
=> Python 3.x
=> EasyOCR
=> OpenCV
=> Torch
=> NumPy
1. Input:
Upload an image or capture a live feed using a webcam.
2. Processing:
The image or video frame is passed to EasyOCR, which detects words and their positions.
3. Output:
The system returns the detected words along with bounding boxes drawn around them in the original image or video.
Use it by-
git clone https://github.com/Neerajdec2005/Word-Detection-Using-EasyOCR.git
Contributions are welcome! Feel free to submit a pull request or open an issue to discuss new features or improvements.
This project is licensed under the MIT License. See the LICENSE file for details.