Skip to content

Using OCR to extract the total payable amount from a receipt image (support .HEIC or jpg file)

Notifications You must be signed in to change notification settings

RainfieldMak/OCR-receipt

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation

OCR-receipt

Author:

Rainfield Mak 

Description

1.A scanned version (croped, grey scale, .jpg file) version of the original image will be store in ./scanned

2.Using OCR technique to obtain the total payable amount on a receipt image (taken from Iphone, .HEIC file).

How to run

Required File Structure .

    .
    |-- data
    |   |-- canny_image
    |   |-- failed
    |   |-- jpg
    |   |-- raw_image
    |   `-- scanned
    |-- env
    `-- script

To run

    python3 main.py 

Usage

1. Default use is for batch conversion for image stored in ./raw folder.(Singular file conversion is also support for debug purpose)

2. Script support download image from google photo using REST API (!! downloaded will be downsampled, not recommend to use since will greatly affect OCR accuracy)

Example

image

About

Using OCR to extract the total payable amount from a receipt image (support .HEIC or jpg file)

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages