Optimization of K-means Algorithm with Computer Programming for Feature Extraction

Feature extraction is a type of image algorithm. Its problems are prevalent today. Among them, feature selection is the most important problem. How to choose the best feature is a complicated problem. Different feature selection methods may select different feature sets, which may affect the accuracy of classification or regression. In this paper, k-means algorithm is used to select the best feature subset. It can cluster data points into different clusters, and then select the cluster with the highest degree of differentiation as the best feature subset. Finally, this paper solves the problem of error rate in the application of feature extraction and improves its accuracy and efficiency. In the future, this technology should be widely used so that it can contribute to human society.