Multi-classification of Pizza Sauce Spread by SupportVector Machine (SVM)

摘要

The classification of pizza sauce spread is highly sensitive to human error due to itssubjective and inconsistent nature. Image processing techniques combined with machine learningprovide an objective and consistent way to accomplish this task. By using a combination of severalbinary classifiers, support vector machine is a state-of-the-art learning algorithm for multiclassificationof pizza sauce spread. The one-versus-one (constructing all possible two-classclassifiers out of N classes) and Directed Acyclic Graph (DAG) methods achieved 87.5%classification accuracy with the extracted colour features of each sample as input.