Handwritten Digit Recognition

Handwritten digits recognition is a classic problem of machine learning. The objective is to recognize images of single handwritten digits(0- 9). in This example We will apply FANN and FANNTool on this problem. Semeion Handwritten Digit Data Set is used for training and testing.

1593 handwritten digits from around 80 persons were scanned, stretched in a rectangular box 16x16 in a gray scale of 256 values.Then each pixel of each image was scaled into a boolean (1/0) value using a fixed threshold. This data set contains no missing values. Each person wrote on a paper all the
digits from 0 to 9, twice. The commitment was to write the digit the first time in the normal way

and the second time in a fast way

This data set consists of 1593 records (rows) and 256 attributes (columns). Each record represents a handwritten digit, originally scanned with a resolution of 256 grays scale. Each pixel of the each original scanned image was first stretched, and after scaled between 0 and 1 (setting to 0 every pixel
whose value was under the value 127 of the grey scale (127 included) and setting to 1 each pixel whose original value in the grey scale was over 127). Finally, each binary image was scaled again into a 16x16 square box (the final 256 binary attributes).

 Firstly We train a ANN for this Data set by using FannTool. After that we write a demonstration program to show a results.

Reached ANN prediction Succes ;
For Training Data : %100 Succes
For Testing Data   :  % 90.1 Succes