Comparing Accuracy and Time of Support Vector Machine with Different Kernels for Handwritten Digits Classification

The aim of this publication is to compare the accuracy and time performance of the Support Vector Machine method with different kernels in image classification within the field of machine learning. In the classification of handwritten digits using the Support Vector Machine approach, we employed the following kernels: polynomial kernel, linear kernel, sigmoid radial kernel, and radial basis kernel. The results indicate that the algorithm employing the radial basis kernel achieved the highest accuracy, while the linear kernel algorithm demonstrated the fastest performance.