Full text of article: Russian language.
The research focuses on selection of human signature features that allow ascertaining identity and are invariant to shift transformations, scaling and rotations. We consider a hypothesis of Edmond Locard, a forensic science pioneer in France, about the angles formed by the main human-signature line elements. We propose a feature selection algorithm from human-signature images, statistical analysis of results of the algorithm operation on signature series, comparison of the algorithm with present detection algorithms of image straight-line segments and possible options for applying the developed approach.
human signature features, affine transformations, signature series, Locard’s principle.
Mikhailov PI, Faizullin RT. Stability testing of angular coefficients formed by line elements of a human signature (Locard’s principle) [In Russian]. Computer Optics 2007; 31(3): 70-72.
© 2009, ИСОИ РАН
Россия, 443001, Самара, ул. Молодогвардейская, 151; электронная почта: email@example.com ; тел: +7 (846) 332-56-22, факс: +7 (846 2) 332-56-20