Bill Classification in Tunisia Challenge
Use computer vision to classify receipts in Tunisa
Prize
Knowledge
Time
Active
Participants
33 active · 311 enrolled
Helping
Tunisia
Intermediate
Classification
Financial Services
About

The data is composed of a set of receipt images that belong to 4 categories: restaurants, parking, fuel and transport.

Each category contains images of receipts in different languages (English, French, German, Italian and Spanish)

The objective of this challenge is to create a deep learning model to classify images of receipts by the category of the expense.

Train and Test images can be downloaded here:

How to use Colab on Zindi

How to mount a drive on Colab

Files
Description
Files
This file contains image IDs and labels (the 4 categories described above); to be used in training models
This file contains the test set image IDs
This shows the submission format for this competition, with the ‘ID’ column mirroring that of Test.csv and the ‘target’ column containing your predictions. The order of the rows does not matter, but the names of the ID must be correct.