Modify Google Vision OCR Script
Budget: $10 – $30 USD
Current Script:
Input: Folder full of png images, with each image being the page of a book.
Output: Text file with OCR'd content
Required Modification:
1. Chapter identification - Whenever a new chapter starts, the chapter title is always of a larger font, centered and bolded. Required output: Instead of a single .txt output, the script should detect the chapter title and create a new .txt file [Chapterwise seperation of files -> Chapter 1.txt, Chapter 2.txt and so on.]
2. Every paragraph should start on a new line. Detect a new paragraph from indentation.
Can provide: Sample images, as many as required.
Input: Folder full of png images, with each image being the page of a book.
Output: Text file with OCR'd content
Required Modification:
1. Chapter identification - Whenever a new chapter starts, the chapter title is always of a larger font, centered and bolded. Required output: Instead of a single .txt output, the script should detect the chapter title and create a new .txt file [Chapterwise seperation of files -> Chapter 1.txt, Chapter 2.txt and so on.]
2. Every paragraph should start on a new line. Detect a new paragraph from indentation.
Can provide: Sample images, as many as required.