The CIFAR-10 and CIFAR-100 are labeled subsets of the 80 million tiny images dataset by MIT. They were collected by AlexKrizhevsky, Vinod Nair, and Geoﬀrey Hinton.
Write an OpenCV program that trains on CIFAR-10 training set and classiﬁes the objects in its test set with the highest accuracy you can obtain.
You are free to choose any feature and classiﬁer you prefer. (SIFT, HoG, etc) / (kNN, SVM, CNN, etc). C++ should be the programming language and it should be created as Microsoft Visual Studio 2015 Project.
Detailed document has been given before starting to work.