Noisy logo recognition using line segment Hausdorff distance

摘要

Logo recognition is of great interest in the document and shape analysis domain. In order to develop a recognition method that is robust to employ under adverse conditions such as different scale/orientation, broken curves, added noise and occlusion, a modified line segment Hausdorff distance is proposed in this paper. The new approach has the advantage to incorporate structural and spatial information to compute dissimilarity between two sets of line segments rather than two sets of points. The proposed technique has been applied on line segments generated from logos with encouraging results. Clear cut distinction between the correct and incorrect matches has been observed. This suggests a strong potential for logo and shape recognition system.