Camera-Based Graphical Symbol Detection

In this paper we present a method to locate and recog-nize graphical symbols appearing in real images. A vector-ial signature is defined to describe graphical symbols. It is formulated in terms of accumulated length and angular in-formation computed from polygonal approximation of con-tours. The proposed method aims to locate and recognize graphical symbols in cluttered environments at the same time, without needing a segmentation step. The symbol sig-nature is tolerant to rotation, scale, translation and to dis-tortions such as weak perspective, blurring effect and illu-mination changes usually present when working with scenes acquired with low resolution cameras in open environments. 1