Feature Extraction 特征提取.pptVIP

Feature Selectionusing Mutual Information SYDE 676 Course Project Eric Hui November 28, 2002 Outline Introduction … prostate cancer project Definition of ROI and Features Estimation of PDFs … using Parzen Density Estimation Feature Selection … using MI Based Feature Selection Evaluation of Selection … using Generalized Divergence Conclusions Ultrasound Image of Prostate Prostate Outline “Guesstimated” Cancerous Region Regions of Interest (ROI) Features as Mapping Functions Mapping from image space to feature space… Parzen Density Estimation Histogram Bins bad estimation with limited data available! Parzen Density Est. reasonable approximation with limited data. Features Gray-Level Difference Matrix (GLDM) Contrast Mean Entropy Inverse Difference Moment (IDM) Angular Second Moment (ASM) Fractal Dimension FD Linearized Power Spectrum Slope Y-Intercept P(X|C=Cancerous), P(X|C=Benign), and P(X) Entropy and Mutual Information Mutual Information I(C;X) measures the degree of interdependence between X and C. Entropy H(C) measures the degree of uncertainty of C. I(X;C) = H(C) – H(C|X). I(X;C) ≤ H(C) is the upper bound. Results:Mutual Information I(C;X) Feature Images - GLDM Feature Images – Fractal Dim. Feature Images - PSD Interdependence between Features Expensive to compute all features. Some features might be similar to each other. Thus, need to measure the interdependence between features: I(Xi; Xj) Results:Interdependence between Features Mutual Information BasedFeature Selection (MIFS) Select first feature with highest I(C;X). Select next feature with highest: Repeat until a desired number of features are selected. Mutual Information BasedFeature Selection (MIFS) This method takes into account both: the interdependence between class and features, and the interdependence between selected features. The parameter β controls the amount of interdependence between selected features. Varying β in MIFS Generalized Divergence J If the features are “b