Nonlinear distortion-tolerant filters for detection of road signs in background noise

In a road sign recognition task, many distortions of targets can occur at the same time. Scale invariance, tolerance to both in-plane and out-of-plane rotations, and illumination invariance are examples of features that a road sign recognition system must possess. We propose a nonlinear correlator that performs several correlations between an input scene and different reference targets. Postprocessing of nonlinear correlation results permits attainment of a single output for the recognition system. The nonlinear filters provide invariance to distortions of the target, noise robustness, and rejection of background noise. In this work, we combine a bank of nonlinear composite correlation filters to design a more versatile road sign recognition system. The bank of filters allows tolerance to changes in scale and tolerance to a certain degree of input-plane rotation. The synthesized nonlinear composite correlation filter permits tolerance to out-of-plane rotation of the target. The system is tested by analysis of real images, which include different distorted versions of stop signs. The processor can be designed for a variety of road signs in background scenes. The recognition results obtained for the proposed system show its robustness against the aforementioned distortions, any varying illumination conditions, and partially occluded objects.