This repo contains the code to perform a simple image classification task using Python and Machine Learning. We will apply global feature descriptors such as Color Histograms, Haralick Textures and Hu Moments to extract features from FLOWER17 dataset and use machine learning models to learn and predict.
- Global Feature Descriptors such as Color Histograms, Haralick Textures and Hu Moments are used on University of Oxford's FLOWER17 dataset.
- Classifiers used are Logistic Regression, Linear Discriminant Analysis, K-Nearest Neighbors, Decision Trees, Random Forests, Gaussian Naive Bayes and Support Vector Machine.
- Tutorial for this project is available at - Image Classification using Python and Machine Learning
We will use the FLOWER17 dataset provided by the University of Oxford, Visual Geometry group. This dataset is a highly challenging dataset with 17 classes of flower species, each having 80 images. So, totally we have 1360 images to train our model. For more information about the dataset and to download it, kindly visit this link, http://www.robots.ox.ac.uk/~vgg/data/flowers/17/