Minimum-Distance-Classifier

Minimum Distance Classifier (MDC) on Persian Handwritten Digits (Hoda dataset) A Minimum Distance Classifier attempts to classify an unlabelled sample to a class which minimise the distance between the sample and the class in multi-feature space. As minimising distance is a measure for maximising similarity, MDC actually assigns data to its most similar category. While MDC might look too basic, it works pretty well in some problems. One of them could be Optical Character Recognition (OCR), where the goal is to distinguish handwritten or printed text characters inside digital images of documents. Here, we aim to apply this technique to the problem of Farsi digits classification. We use a dataset named Hoda, which contains 102353 samples of digits written