Writer identification using fractal dimension of wavelet subbands in gabor domain

摘要: Writer identification is an important and active branch of biometrics, which means the methods for uniquely recognizing humans based upon their intrinsic physical or behavioral traits. In this paper, we propose one new method off-line, text-independent writer by using fractal dimension wavelet subbands in Gabor domain handwriting images. method, images are firstly decomposed into a series at different orientations frequencies. Every subband extended data sequence. Then, every sequence subpatterns transform. Afterwards, mesh dimensions subpattern extracted as feature identification. Compared to traditional identification, our can extract more effective features distinguish handwritings, hence achieve much better results.