Traffic Sign Recognition Using Discriminative Local Features

Real-time road sign recognition has been of great interest for many years. This problem is often addressed in a two-stage procedure involving detection and classification. In this paper a novel approach to sign classification is proposed. In many previous studies focus was put on deriving a possibly most discriminative set of features from a large amount of training data using global selection techniques e.g. Principal Component Analysis or AdaBoost. In our method we have chosen a simple yet robust image representation built on top of the Colour Distance Transform (CDT). Based on this representation, we introduce a feature selection algorithm which captures a variable-size set of local image regions ensuring maximum dissimilarity between each individual sign and all other signs. Experiments have shown that the discriminative local features extracted from template sign images enable simple minimumdistance classification with error rate not exceeding 7%.