txli299/book-cover-recognizer

Book Cover Recognizer

This application scans book covers to extract the title and fetches book details from a JSON database.

Demo video link: link

How to Run

Prerequisites

• Docker installed

Steps

1. Build the Docker image:

   docker build -t book-scanner .

2. Run the Docker container:

   docker run -d -p 5001:5001 book-scanner

3. Test the application:

   Upload an image of a book cover using tools like Postman or curl:

   curl -X POST -F "file=@path_to_book_cover.jpg" http://localhost:5001/upload

Additional Setup for Google Vision API

1. Enable the Google Vision API in your Google Cloud project.
2. Download the JSON key file for your Google Cloud service account and rename it to google_credentials.json.
3. Place the google_credentials.json file in the root directory of the project.

Dependencies

• Flask: API framework
• OpenCV: Image processing
• pytesseract: OCR engine
• Google Vision API: OCR engine

Endpoints

1. /ocr (POST)

Extract text from an uploaded image using Optical Character Recognition (OCR).

Request:

• Method: POST
• Form Data:
  • file: Image file to process

Response:

• 200 OK:

  {"extracted_text": ["line1", "line2", ...],
  "matches": [BooksMetaData]
  }