Abstract
Image segmentation is the most important process in road sign detection and classification systems. In road sign systems, the spatial information of road signs are very important for safety issues. Road sign segmentation is a complex segmentation task because of the different road sign colors and shapes that make it difficult to use specific threshold. Most road sign segmentation studies do good in ideal situations, but many problems need to be solved when the road signs are in poor lighting and noisy conditions. This paper proposes a hybrid dynamic threshold color segmentation technique for road sign images. In a pre-processing step, the authors use the histogram analysis, noise reduction with a Gaussian filter, adaptive histogram equalization, and conversion from RGB space to YCbCr or HSV color spaces. Next, a segmentation threshold is selected dynamically and used to segment the pre-processed image. The method was tested on outdoor images under noisy conditions and was able to accurately segment road signs with different colors (red, blue, and yellow) and shapes.Article Preview
TopThe first step in all previous works is image segmentation process. It aims at locating the regions of interest and features of road signs and determining the type of a detected sign (de la Escalera et al., 1997; Paclík et al., 2000; Piccioli et al., 1996, Gao et al., 2006). In segmentation and detection, traditionally color information was primarily used (de la Escalera et al., 2003; de la Escalera et al., 1997; Gao et al., 2006; Janssen et al., 1993; Piccioli et al., 1996). Other approaches use shape based detection with the geometrical edge analysis (Gao et al., 2006; Garcia-Garrido et al., 2006; Piccioli et al., 1996) or corner analysis (de la Escalera et al., 1997).