Cascaded heterogeneous convolutional neural networks for handwritten digit recognition

This paper presents a handwritten digit recognition method based on cascaded heterogeneous convolutional neural networks (CNNs). The reliability and complementation of heterogeneous CNNs are investigated in our method. Each CNN recognizes a proportion of input samples with high-confidence, and feeds the rejected samples into the next CNN. The samples rejected by the last CNN are recognized by a voting committee of all CNNs. Experiments on MNIST dataset show that our method achieves an error rate 0.23% using only 5 C-NNs, on par with human vision system. Using heterogeneous networks can reduce the number of CNNs needed to reach certain performance compared with networks built from the same type. Further improvements include fine-tuning the rejection threshold of each CNN and adding CNNs of more types.