Vehicle-logo Recognition Method Based on Tchebichef Moment Invariants and SVM

Abstract

In order to solve the problem about the recognition accuracy, Tchebichef moment invariants and support vector machine (SVM) are adopted to recognize the vehicle-logo. It extracts six invariant moments of the object as feature vectors, and then uses the support vector machines (SVM) to recognize vehicle-logo. Tchebichef moment invariants perform significantly better than Hu moment invariants and Zernike moment invariants. The result of these experiments suggests that this system has a high recognition rate in both noise-free and noisy environment which has high practical value.