Using Support Vector Machines to Classify Whether a Car is in Front of You or Not

摘要

Support Vector Machine (SVM) theory is a learning machine theory developed by V. Vapnik. Its most common uses are for classification problems and regression. Like other learning machines, the distribution of the population does not need to be known. It is sufficient only to know that a distribution exists. What sets SVMs apart from other learning machines is its ability to classify items correctly with a relatively small sample size. In this paper I will briefly describe learning machines and SVMs. It will not be a complete tutorial on either subject. If the reader desires to learn more about them, then please refer to the references at the end of this paper. I will also give the theory and results of using SVMs to classify whether there is a car in front of you or not, using an image from a digital camera.