Car recognition for multiple data sets based on histogram of oriented gradients and support vector machines
Ilias Kamal · 2012
In this paper we implement a soft margin support vector machine (SVM) using linear and nonlinear kernels for image classification. The sequential minimal optimization (SMO) method will be used to find the optimal separating hyperplane between the training data that consist of a multidimensional histogram of oriented gradient (HOG) features vectors extracted from multiple data sets.