Automatic Authentication of Handwritten Documents via Low Density Pixel Measurements

We introduce an effective approach for automatic offline auinjuries, illness, temperature, age and emotional state as well thentication of handwritten samples where the forgeries are skillfully done, as external factors such as alcohols and drugs [3] – an original i.e., the true and forgery sample appearances are almost alike. Subtle details piece of writing has many natural personal characteristics like of temporal information used in online verification are not available offline cursiveness, ballistic rhythm etc. But a forge sample, however and are also hard to recover robustly. Thus the spatial dynamic information skillful it may be, always lacks this rhythm and has poor line like the pen-tip pressure characteristics are considered, emphasizing on the quality. Hence the features to provide efficient basis for verifiextraction of low density pixels. The points result from the ballistic rhythm cation for the case of offline authentication are the non-natural of a genuine signature which a forgery, however skillful that may be, always characteristics like hesitation, patching, retouching etc., which lacks. Ten effective features, including these low density points and denare generally concerned with the gray levels of the signature sity ratio, are proposed to make the distinction between a true and a forgery (and lost if we deal with the signature as a binary image). In sample. An adaptive decision criteria is also derived for better verification the 1980s, Ammar et. al. [6], aiming at skilled forgery detecjudgements. tion, used such feature sets. They considered the geometric Keywords— Handwritten document verification, Skilled forgeries, Low information about the letters far less informative and the main density pixels, Adaptive decision boundary. emphasis was given on high-pressure regions which were actually the dark pixels in the signature image corresponding to