Support Vector Machine with Inverse Fringe as Feature for MNIST Dataset

In this paper we proposed SVM algorithm for MNIST dataset with fringe and its complementary version, inverse fringe as feature for SVM. MNIST data-set is consists of 60000 examples of training set and 10000 examples of test set. In our experiments we started with using fringe distance map as feature and found that the accuracy of system on trained data is 99.99% and on test data it is 97.14%, using inverse fringe distance map as feature and found that the accuracy of system on trained data is 99.92% and on test data is 97.72% and using combination of above two feature as feature and found that the accuracy of system on trained data is 100 and on test data is 97.55%.