You are right! This is the place to submit your HW 4 Problem5. 

In previous part of HW 4 Problem 5, you learnt to process images in a form they could be used to train clustering algorithms (with each individual pixel being a 'training example'). For an RGB image, each training example would have at least 3 features (the Red, Green, and Blue values for the pixel). In addition, one could add the spatial positions of the pixel as another set of features. 

We are now going test what you have learnt in processing image by this Kaggle competition wherein you are asked to segment two RGB images. By submitting your result to Kaggle, you will see your multi-class classification accuracy and ranking on the leaderborad. 10 pts will depend on your ranking (top 10% get 10pts, top 11%-20% get 9pts, etc.), and another 5 pts depend on your method explanation and clear, well-labeled plots and images. 

Since this is an open-ended question, you should try to design your own features to achieve better classification results. Try different feature combinations, image processing techniques to get the best looking results. Refer to the homework notebook for details.