Research Article
Classification of Region of Interest in Mammograms Using Dual Contourlet Transform and Improved KNN
Table 4
Classification accuracy (%) of different methods tested between normal and abnormal.
| Accuracy | Improved KNN | KNN | Dual-CT | Contourlet | Wavelet | Dual-CT | Contourlet | Wavelet |
| Mean | 93.21 | 91.98 | 90.12 | 82.72 | 75.00 | 78.40 | SD | 93.52 | 93.21 | 91.67 | 81.17 | 75.93 | 78.70 | Smoothness | 93.83 | 91.05 | 89.51 | 81.79 | 79.63 | 80.56 | Skewness | 92.90 | 89.81 | 88.89 | 81.48 | 75.00 | 75.62 | Uniformity | 93.52 | 93.21 | 92.28 | 77.47 | 79.01 | 78.09 | Entropy | 94.14 | 93.52 | 93.52 | 79.83 | 76.85 | 75.62 | Contrast | 90.74 | 93.52 | 92.90 | 78.09 | 76.54 | 75.31 | Correlation | 93.83 | 92.28 | 88.27 | 83.02 | 77.78 | 78.80 | Homogeneity | 92.90 | 93.83 | 92.59 | 81.17 | 76.85 | 76.85 |
|
|
SD represents standard deviation; bold font number indicates the best performance in each class.
|