Research Article
Classification of Region of Interest in Mammograms Using Dual Contourlet Transform and Improved KNN
Table 6
Classification accuracy (%) of different methods tested between benign and malignant.
| Accuracy | Improved KNN | KNN | Dual-CT | Contourlet | Wavelet | Dual-CT | Contourlet | Wavelet |
| Mean | 91.53 | 91.53 | 87.29 | 76.27 | 78.81 | 81.36 | SD | 93.22 | 88.14 | 85.59 | 76.27 | 71.19 | 75.42 | Smoothness | 95.76 | 88.98 | 83.05 | 70.34 | 77.12 | 77.97 | Skewness | 90.68 | 86.44 | 87.29 | 72.03 | 77.97 | 75.42 | Uniformity | 94.92 | 88.98 | 83.90 | 75.42 | 74.58 | 77.12 | Entropy | 90.68 | 88.98 | 86.44 | 67.80 | 77.97 | 76.27 | Contrast | 95.76 | 87.29 | 86.44 | 75.42 | 75.42 | 72.03 | Correlation | 91.53 | 86.44 | 86.44 | 76.27 | 78.81 | 80.51 | Homogeneity | 94.92 | 88.14 | 81.36 | 76.27 | 72.88 | 72.88 |
|
|
SD represents standard deviation; bold font number indicates the best performance in each class.
|