Vehicle Image Matching Using Siamese Neural Networks with Multi-Directional Image Projections
Gábor Kertész, Sándor Szénási, Zoltán Vámossy · 2018
A novel method to measure similarity on images is based on the Siamese architecture of Convolutional Neural Networks. Two identical CNNs extract the significant parts of the inputs, and a single neuron outputs the distance of the two. The aim of this paper is to introduce that the Siamese structure can be applied to match image projection based signatures of vehicles.