A project in computer vision: Recognizes images of digits using a Naive Bayes classifier.
The overarching goal of computer vision is to gain a high-level understanding of any image. Here, we have a simpler goal of recognizing images of digits, which are composed of binary features representing the colors black and white. This is accomplished by training a Naive Bayes classifier on a set of approximately 5000 images of digits and then testing it on new images of digits to gauge how well it recognizes them.