MATLAB: Classifying images using Machine Learning or Deep Learning

Question

I am pretty new to image processing and machine learning. Currently, I am doing a school project where I have to classify images in: bottle of water or can of soda. The idea is to train a model with different brands of bottles of water and cans of soda. Then, if one of those brands appear, classify the image in one of the two categories. Is this possible using the Matlab machine learning toolbox or the deep learning one? Any suggestion?

Answer 1

First try the general machine learning algorithms to classify such as Support Vector Machines. The following example would be similar to what you want to do:

• Digit Classification Using HOG Features https://www.mathworks.com/help/vision/examples/digit-classification-using-hog-features.html

If you are not satisfied with your classification results, and you have a lot of image data, consider to use Deep Learning. The easiest way to get started is to use the pre-trained model such as alexnet:

• Pretrained Convolutional Neural Network https://www.mathworks.com/help/nnet/ug/install-trained-convolutional-deep-network.html

If you want to use more complex ones, see the examples in the documentation first.