Research Article
Image Classification Using Biomimetic Pattern Recognition with Convolutional Neural Networks Features
Table 2
Classification accuracy of different methods on MNIST.
| Training samples | Accuracy (%) | CNN [26] | CNN-SVM [19] | PCA-BPR [36] | HOG-SVM [37] | Our method |
| 600 | 84.01 | 86.48 | 89.23 | 86.47 | 91.03 | 1000 | 89.31 | 90.41 | 91.04 | 91.24 | 92.93 | 6000 | 95.06 | 94.88 | 93.83 | 93.57 | 96.74 | 10000 | 98.17 | 97.09 | 96.03 | 95.13 | 98.62 | 60000 | 98.89 | 99.06 | 98.01 | 96.85 | 99.01 |
|
|