Search Results for "cross correlation"

We propose the use of Differential Evolution algorithm for the weight adjustment of base classifiers used in weighted voting heterogeneous ensemble of classifier. Average Matthews Correlation Coefficient (MCC) score, calculated over 10-fold cross-validation, has been used as the measure of quality of an ensemble. DE/rand/1/bin algorithm has been utilised to maximize the average MCC score calculated using 10-fold cross-validation on training dataset. The voting weights of base classifiers are optimized for the heterogeneous ensemble of classifiers aiming to attain better generalization performances on testing datasets.

This Java native library wraps OpenCV (Computer Vision Lib.) function cvMatchTemplate and implements methods for utilities result visualization. It allows efficient images template matching using Normalized Cross-Correlation (NCC) and others algorithms.