From: A genetic optimized neural network for image retrieval in telemedicine
Number of features | Parameters | Classifiers | Uncompressed | Compressed | ||
---|---|---|---|---|---|---|
 |  |  | Feature extraction using FFT | Feature extraction using the proposed IRS-FFT | Feature extraction using FFT | Feature extraction using proposed IRS-FFT |
20 | Classification accuracy | MLP NN | 88.46 | 92.31 | 90.38 | 92.31 |
GOP NN | 92.31 | 94.23 | 94.23 | 98.08 | ||
Precision | MLP NN | 0.92 | 0.96 | 0.86 | 1 | |
GOP NN | 0.96 | 1 | 1 | 1 | ||
Recall | MLP NN | 0.85 | 0.89 | 1 | 0.86 | |
GOP NN | 0.89 | 0.89 | 0.89 | 0.96 | ||
40 | Classification accuracy | MLP NN | 90.38 | 94.23 | 92.31 | 94.23 |
GOP NN | 94.23 | 96.15 | 94.23 | 98.08 | ||
Precision | MLP NN | 0.96 | 0.96 | 1 | 1 | |
GOP NN | 1 | 1 | 1 | 1 | ||
Recall | MLP NN | 0.86 | 0.92 | 0.86 | 0.89 | |
GOP NN | 0.89 | 0.93 | 0.89 | 0.96 | ||
60 | Classification accuracy | MLP NN | 88.46 | 90.38 | 92.31 | 94.23 |
GOP NN | 92.31 | 94.23 | 92.31 | 98.08 | ||
Precision | MLP NN | 0.92 | 0.96 | 1 | 1 | |
GOP NN | 1 | 1 | 1 | 1 | ||
Recall | MLP NN | 0.85 | 0.86 | 0.86 | 0.89 | |
GOP NN | 0.86 | 0.89 | 0.86 | 0.96 | ||
80 | Classification accuracy | MLP NN | 90.38 | 94.23 | 92.31 | 94.23 |
GOP NN | 94.23 | 96.15 | 98.08 | 98.08 | ||
Precision | MLP NN | 0.96 | 0.96 | 1 | 1 | |
GOP NN | 1 | 1 | 1 | 1 | ||
Recall | MLP NN | 0.86 | 0.92 | 0.86 | 0.89 | |
GOP NN | 0.89 | 0.93 | 0.96 | 0.96 | ||
100 | Classification accuracy | MLP NN | 90.38 | 94.23 | 92.31 | 94.23 |
GOP NN | 94.23 | 96.15 | 98.08 | 98.08 | ||
Precision | MLP NN | 0.96 | 0.96 | 1 | 1 | |
GOP NN | 1 | 1 | 1 | 1 | ||
Recall | MLP NN | 0.86 | 0.92 | 0.86 | 0.89 | |
 |  | GOP NN | 0.89 | 0.93 | 0.96 | 0.96 |