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.

AccuracyImproved KNNKNN
Dual-CTContourletWaveletDual-CTContourletWavelet

Mean93.2191.9890.1282.7275.0078.40
SD93.5293.2191.6781.1775.9378.70
Smoothness93.8391.0589.5181.7979.6380.56
Skewness92.9089.8188.8981.4875.0075.62
Uniformity93.5293.2192.2877.4779.0178.09
Entropy94.1493.5293.5279.8376.8575.62
Contrast90.7493.5292.9078.0976.5475.31
Correlation93.8392.2888.2783.0277.7878.80
Homogeneity92.9093.8392.5981.1776.8576.85

SD represents standard deviation; bold font number indicates the best performance in each class.