Frequency Selective Convolutional Neural Networks for Traffic Sign Recognition

Zifeng Lian, Xiaojun Jing, Songlin Sun, Hai Huang

Abstract: Image recognition, especially traffic sign recognition is an important task for autonomous driving and driver assistance systems. A new Convolutional Neural Network model with the ability of feature selection in frequency domain is presented in this paper, called Frequency Selective Filter Aided (FSFA) CNN model. The new model can integrate low-pass and high-pass filters into both forward and backward propagations in order to place special emphases on feature components in different frequency bands. The theoretical basis, as well as forward and backward propagations are also formulated. Experiments on CIFAR and GTSRB traffic sign recognition datasets show that the proposed model yields better performance for the task of image recognition compared with classic methods.