Combined Convolutional and Perceptron Neural Networks for Handwritten Digits Recognition

Abstract

The use of a combination of a convolutional neural network and multilayer perceptrons for recognizing handwritten digits is considered. Recognition is carried out by two sets of networks following each other. The first neural network selects two digits with maximum activation functions. Depending on the winners, the following network is activated (multilayer perceptron), which selects one digit from two. The proposed algorithm is tested on the data from MNIST. The recognition error is 0.75%. Obtained results demonstrate that the minimum error with this approach is 0.68%, and the accuracy of the F-metric is about 0.99 for each digit. The main feature of the proposed solution is dealt with the fact that the proposed cascaded combination of neural networks provides a sufficiently high accuracy with a simple architecture.