A novel approach for recognising various traffic sign shapes in outdoor environments is presented. To reduce the influence of digital noise and extract the shape of each individual traffic sign, the external boundaries of traffic signs segmented based on colour information are simplified and decomposed through discrete curve evolution whose stop stage is determined by an arc similarity measure in tangent space. The recognition of a closed candidate shape is achieved through the direct matching with templates. An optimal enclosure is generated to minimise the geometric differences between the retrieved unclosed candidate shape and templates. The experimental results justify that the proposed algorithm is translation, rotation and scaling invariant, and gives reliable shape recognition in complex traffic scenes where clustering and partial occlusion normally occur.