| This paper investigates statistical methodology for the automated recognition of handwritten digits. A handwritten digit, 0 through 9, was obtained from 42,000 participants' writing samples. These handwriting samples were digitally scanned and stored in an image database. The objective of the analysis is to create a statistical testing procedure that can be easily automated by the computer to recognize which digit was written. The testing procedure is designed to be sensitive to Type I errors and will control an overall measure of these errors through a Bonferroni correction. The procedure was constructed based off of a training portion of the data set, then applied and validated on the remaining testing portion of the data. |
Updated 03/19/2014