Looking to classify images using a simple dataset derived from CIFAR-10 dataset and classify the images using 1 or maybe 2 machine learning models.
You are provided with an image dataset, where there are 10 different categories of objects, each of which has 1000 images for training and 100 images for testing. Each image only contains one object. The task is to apply supervised learning algorithms to classify the testing images into 10 object categories. The code to compute image features and visualise the image is provided. You can use it to visualise the images, compute features, and transform them if necessary, e.g. using PCA and LDA. You will then perform supervised classification and report quantitative results; writing this up into a 4-page report. You don't have to use all the provided code or methods discussed in this module. You may add additional steps to the process if you wish.
About the recuiterMember since Sep 15, 2017 Jun Ho
from Seoul, South Korea