Pattern augmentation for handwritten digit classification based on combination of pre-trained CNN and SVM
Yoshihiro Shima, Yumi Nakashima, Michio Yasuda · 2017
Neural networks are powerful technology for classifying character patterns and object images. A huge number of training samples is very important for classification accuracy. A novel method for recognizing handwritten digits is proposed that combines pre-trained convolutional neural networks (CNN) and support vector machines (SVM). The training samples are augmented by pattern distortion such as by cosine translation and elastic distortion. A pre-trained CNN, Alex-Net, can be used as the pattern feature extractor. Alex-Net is pre-trained for large-scale object image datasets. An SVM is used as a trainable classifier. Sixty thousand samples and distorted patterns on the MNIST database are trained by the SVM. The feature vectors of character patterns are passed to the SVM from Alex-Net. Experimental results showed a test error rate of 1.03% without distortion and an error rate of 0.93% with distortion on the MNIST database's test set, which contains 10,000 handwritten characters, showing that the proposed method is effective in recognizing handwritten digits.