MNIST HWR using R

Handwriting Recognition (HWR) is a very commonly used procedure in modern technology. The image of the written text can be detected offline from a piece of paper by optical scanning (optical character recognition (OCR)) or intelligent word recognition. Alternatively, pen tip movements can be detected online (for example, from a pen-computer surface, a task that is generally easier since there are more clues available). Technically, recognition of handwriting is the ability of a computer to receive and interpret a handwritten intelligible input from sources such as paper documents, photos, touchscreens, and other devices.

HWR is performed through various techniques that generally require OCR. However, a complete script recognition system also manages formatting, carries out correct character segmentation, and finds the most plausible words.

Modified National Institute of Standards and Technology (MNIST) is a large database of handwritten digits. It has a set of 70,000 examples...