|
Printed text documents watermarking based on vertical word shift and word fragments brightness changing
D. O. Obydenkova, A. E. Frolova, Yu. V. Markina, S. A. Fomina, B. V. Kondrat’evb a Ivannikov Institute for System Programming of the RAS
b Ministry of Defence of the Russian Federation
Abstract:
This paper describes the results of the development of methods for marking text documents represented as a raster image. An important feature of the algorithms is the possibility wipe current document mark and embed another one. The study refers to structural marking algorithms based on vertical word shifts and brightness changes of certain areas of the words. Segmentation tools are used to obtain document layout, BCH codes for error correction, a likelihood maximization method for label extraction, and a neural network for perturbed words recovery. Testing has proved the practical applicability of the algorithms with printing and scanning.
Keywords:
data leakage prevention, documents watermarking, print-scan robust watermarking, blind watermarking method, stenography, image processing, error detection and correction, neural networks.
Citation:
D. O. Obydenkov, A. E. Frolov, Yu. V. Markin, S. A. Fomin, B. V. Kondrat'ev, “Printed text documents watermarking based on vertical word shift and word fragments brightness changing”, Proceedings of ISP RAS, 33:5 (2021), 65–82
Linking options:
https://www.mathnet.ru/eng/tisp628 https://www.mathnet.ru/eng/tisp/v33/i5/p65
|
Statistics & downloads: |
Abstract page: | 8 | Full-text PDF : | 11 |
|