作者: Qianjin Zhou , Yuchen Yan , Tianhong Fang , Xiao Luo , Qinghu Chen
DOI: 10.1007/S11042-015-2525-5
关键词: Texture synthesis 、 Fast Fourier transform 、 Texture (music) 、 Identification (information) 、 Computer science 、 Computer vision 、 Image (mathematics) 、 Artificial intelligence 、 Feature extraction 、 Matrix (mathematics)
摘要: There are many methods available for printer identification of questioned documents, however most them need identical contents the training and testing documents. is no effective method yet when documents different. To overcome this obstacle a based on synthetic texture analysis proposed in paper. The inner printed characters reconstructed order to generate an artificial textural image similar real while independent document content. Fast Fourier Transform (FFT) Gray Level Co-occurrence Matrix (GLCM) then used feature extraction. Experimental results demonstrate that can achieve high recognition rate provide new platform content