Vehicle logo recognition based on interior structure using SIFT descriptor and neural network

This paper presents an approach for automatic recognition of vehicle make from its logo in a front-view image using SIFT descriptor of interior structure and back-propagation neural network. The proposed method focuses on recognition of automobile make by integrating Top-Hat transformation with shape descriptor to locate the logo of an automobile from an image then uses back-propagation neural network to recognize an automobile make from the SIFT (Scale-Invariant Feature Transform) descriptor of inner structure of the logo. The training set contains eighteen images of six different logos, whereas the test set contains 220 images of automobile. The recognition results from the proposed method were compared with the results from other existing methods and the results reveal that it can recognize automobile makes regardless of illumination condition or position and the accuracy rate is over 50%.