Pattern Recognit. Image Anal. 27, 53–65 (2017). https://doi.org/10.1134/S1054661817010023
Various periodic security elements, such as holograms, watermarks, and guilloches, are applied to documents in order to protect against counterfeiting. These elements can be detected and used to automatically check the authenticity of a document and to identify its type. They also make it possible to use special OCR system parameters in areas of security elements. This paper is devoted to developing methods for the detection and localization of periodic background patterns based on two-dimensional discrete Fourier transform. The model of a document image with a periodic background structure is considered. Algorithms for the detection and localization of background structures that follow from the model are discussed. The behavior and accuracy characteristics of the algorithms are tested on samples of Russian passport images. Their tolerance to errors in document boundary detection are experimentally analyzed. Modified detection and localization algorithms that improve the separating detection capability and reduce localization error twofold are proposed such as masking and replacement of noisy parts of document images, background spectrum suppression, and estimation of phase components of a single periodic element.