A common problem encountered in signboard recognition is the perspective distortion of characters. In this paper, we propose a method which is able to directly recognize characters under severe perspective distortion without perspective rectification. In this method, a character is represented by a sequence of cross ratio spectra, in which the perspective effect can be modeled as an one-dimensional uneven stretching. Dynamic Time Warping algorithm is employed to estimate the pairwise similarity between spectra of the query and spectra of a fronto-parallel template. Then, it is again used to find out the pixel-level correspondence and the similarity between the query and the template. The experiment results showed that the proposed method worked well on synthetic character images and signboards in real scene under severe perspective projections. 1

Perspective deformation is one of the main issues needed to be addressed in real-scene character recognition. An effective recognition approach, which is able to handle severe perspective deformation, is to employ Cross Ratio Spectrum and Dynamic Time Warping techniques. However, this solution suffers from a time complexity of O(n 4). In this paper, a clustering based indexing method is proposed to index cross ratio spectra and thus expedite the recognition. Cross ratio spectra of all templates are clustered. A query is compared with the centroid of each cluster instead of spectra of all templates. Our method is 40 times faster than the previous method, and has archived about 15-time speed up while preserving almost the same recognition accuracy in the real scene character recognition experiment. 1

Abstract—A common problem encountered in recognizing symbols in real-scene images is the perspective deformation. In this paper, a recognition method resistant to perspective deformation is proposed. Particularly, a symbol is represented by a sequence of cross ratio spectra, in which perspective deformation is modeled as an uneven stretching deformation. Dynamic Time Warping algorithm is employed to compare the similarity of spectra and to find the pixel level correspondence between two symbols. The proposed method shows not only good resistance to severe perspective deformation and other common noise in real scene images, but also good discriminating ability to similar symbols. Index Terms—Symbol recognition, Perspective deformation, Dynamic time warping.