Welcome to the project on apple classification, where you will classify between bruised on sound apples! From the tutorials you will learn the following:
- Tutorial 1 - Data cleaning & visualization
- Tutorial 2 - Baseline Calculation
- Tutorial 3 - Feature Engineering and Selection
- Tutorial 4 - Machine learning classification.
Infrared spectra data for three apple cultivars, namely ’Golden Delicious’ (GD) (yellowish green), ’Granny Smith’ (GS) (green) and ’Royal Gala’ (RG) (predominantly red), were acquired in two installments (in two consecutive months) from two different local retail shops from Stellenbosch, Western Cape, South Africa, in 2019.
From the three apple cultivars, two main sample categories were created, namely bruised (B) and non-bruised (S) fruit. From the B category, three subcategories were created by representing the different levels of bruise severity, thus contributing to more variability in the data set.
From the proposed pipeline, investigate new ways to classify between bruised and sound apples using machine learning.
All the libraries/dependencies necessary to run the tutorials are listed in the requirements.txt file.
All the required libraries can be installed using pip and the requirements.txt file in the repo:
> pip install -r requirements.txt> git clone https://github.com/Hack4Dev/apple_classification.gitThen make sure you have the right Python libraries for the tutorials.
The easiest way to get all of the lecture and tutorial material is to clone this repository. To do this you need git installed on your laptop. If you're working on Linux you can install git using apt-get (you might need to use sudo):
apt install git
You can then clone the repository by typing:
git clone https://github.com/Hack4Dev/apple_classification.git
To update your clone if changes are made, use:
cd apple_classification/
git pull
Nturambirwe, J.F.I.; Hussein, E.A.; Vaccari, M.; Thron, C.; Perold, W.J.; Opara, U.L. Feature Reduction for the Classification of Bruise Damage to Apple Fruit Using a Contactless FT-NIR Spectroscopy with Machine Learning. Foods 2023, 12, 210. https://doi.org/10.3390/foods12010210