Image classification using data augmentation

Version 1.1.0 (3.51 MB) by Oge Marques
A simple example of a four-class image classifier using a small dataset, with and without data augmentation.
1.5K Downloads
Updated 12 Aug 2019

View License

A simple example of a four-class image classifier using a small dataset (320 images of flowers: 80 sample x 4 categories) and a very simple CNN, with and without data augmentation.

The main goal of this example is to demonstrate the use of the MATLAB functionality for data augmentation in image classification solutions: the augmentedImageDatastore and the imageDataAugmenter.

This example should be easy to modify and expand to the user's needs.

Notes:
- The validation accuracy improves -- from ~79% (Part 1 in the code) to ~83% (Part 2) -- using a very simple CNN, as a result of data augmentation alone.
- Interestingly enough, using a pretrained AlexNet, the validation accuracy drops -- from 100% (Part 3) to ~98% (Part 4) -- which shows that data augmentation wouldn't be necessary in this case.

Cite As

Oge Marques (2024). Image classification using data augmentation (https://www.mathworks.com/matlabcentral/fileexchange/68728-image-classification-using-data-augmentation), MATLAB Central File Exchange. Retrieved .

MATLAB Release Compatibility
Created with R2019a
Compatible with R2017b to R2019a
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!
Version Published Release Notes
1.1.0

Added Parts 3 and 4 (using a pretrained AlexNet) and fixed a few bugs.

1.0.0