10301998/ocr-text repository overview

OCR Text Docker Image

This Docker image provides an OCR (Optical Character Recognition) application using three different OCR libraries: PaddleOCR, EasyOCR, and KerasOCR. The application is built using Python and Gradio for the web interface. Features

PaddleOCR: An easy-to-use OCR library developed by PaddlePaddle.

KerasOCR: A high-level OCR tool built with Keras and TensorFlow.

EasyOCR: A powerful OCR library that supports multiple languages.

The user can upload an image and select one of the OCR methods to extract text from the image. Installation

To build and run this Docker image, you need to have Docker installed on your machine. Build the Docker Image

Clone the repository or download the Dockerfile and other required files.

Open a terminal and navigate to the directory containing the Dockerfile. Build the Docker image using the following command:

sh

docker build -t ocr-text .

Run the Docker Container

Once the image is built, you can run the Docker container using the following command:

sh

docker run -p 7860:7860 ocr-text

This command will start the OCR application and make it accessible via http://localhost:7860⁠. Usage

Open a web browser and go to http://localhost:7860.

You will see a user interface with an option to upload an image and select an OCR method (PaddleOCR, EasyOCR, KerasOCR). Upload an image and select the desired OCR method.

Click the "Submit" button to extract text from the uploaded image.
The extracted text will be displayed in the output textbox.

Code Explanation

The code consists of several parts: Importing Required Libraries

The necessary libraries such as Gradio, TensorFlow, Keras-OCR, EasyOCR, PaddleOCR, and others are imported. OCR Methods

Three OCR methods are defined:

ocr_with_paddle: Uses PaddleOCR to extract text from an image.
ocr_with_keras: Uses KerasOCR to extract text from an image.
ocr_with_easy: Uses EasyOCR to extract text from an image.

Utility Functions

Utility functions for image preprocessing such as converting an image to grayscale and thresholding are defined. Generate OCR

The generate_ocr function is the main function that takes the selected OCR method and image as input and returns the extracted text. User Interface

The Gradio interface is created with an image upload option, a radio button to select the OCR method, and a textbox to display the extracted text. Launching the Interface

The Gradio interface is launched, making the OCR application accessible via a web browser. Dockerfile

The Dockerfile sets up the environment to run the OCR application.

Dockerfile

# Use an official Python runtime as a parent image
FROM python:3.8-slim

# Set the working directory in the container
WORKDIR /app

# Copy the current directory contents into the container at /app
COPY . /app

# Install any needed packages specified in requirements.txt
RUN pip install --no-cache-dir -r requirements.txt

# Make port 7860 available to the world outside this container
EXPOSE 7860

# Define environment variable
ENV NAME ocr-text

# Run the application
CMD ["python", "app.py"]

Conclusion

This Docker image provides a convenient way to run an OCR application using multiple OCR methods. By using this Docker image, you can easily extract text from images using PaddleOCR, EasyOCR, or KerasOCR.