Skip main navigation

Image classification

Mike Mayo shows that with appropriate features, machine learning can be used to classify images. Weka has a package for extracting image features.

Mike Mayo shows that with appropriate features, Weka can be used to classify images. The imageFilters package processes image files to extract features, and implements 10 different feature sets. You need to put all your images into a single folder and create an ARFF file with two attributes: the image filename (a string) and its class (nominal). The image filters appear as unsupervised instance filters, under imageFilter. One is the ColorLayoutFilter, another is the EdgeHistogramFilter. Each adds several attributes to the ARFF file. Furthermore, they can be used in sequence, each filter adding its own attributes.

This article is from the free online

Advanced Data Mining with Weka

Created by
FutureLearn - Learning For Life

Reach your personal and professional goals

Unlock access to hundreds of expert online courses and degrees from top universities and educators to gain accredited qualifications and professional CV-building certificates.

Join over 18 million learners to launch, switch or build upon your career, all at your own pace, across a wide range of topic areas.

Start Learning now