Recognizing traffic signs using exible Discrete Cosine Transform (DCT) grid

Trac sign recognition can be performed in two phases of detection and recognition; detection deals with sensing a traffc sign in real-world image or video frame while recognition is about reading its contents. A traffc signs database may contain samples with varying font sizes and styles used for printing the interior of a traff sign and the contents may also be shifted away from the center of gravity. In this paper, we utilize the energy compaction property of Discrete Cosine Transform (DCT) to propose a Traffic Sign Recognition (TSR) system, which can generate invariant features for varying font styles and scaled up, scaled down, and translated contents of a sign. Experiments on synthetic and real-world images datasets show that the features generated by our proposed method have great intra-class similarity and inter-class variation. We have also shown that our proposed method outperforms Eigen based recognition method [1] and is comparable with the Histogram of Oriented Gradient (HOG) approach [2] using Support Vector Machine (SVM) classier.