Recovery of temporal information from off-line arabic handwritten

Off-line signature verification based on grey level information using texture features

“…Simulated human handwriting movements are considered by means of a writing robot to study the relationship between writing process characteristics and ink deposit on paper. Approaches from the field of image processing and pattern recognition can be divided into: methods for estimating the temporal order of stroke production [18,19]; methods inspired by motor control theory, which recover temporal features on the basis of stroke geometries such as curvature [20]; and finally, methods analysing stroke thickness and/or stroke intensity variations [21][22][23][24][25]. An analysis of mainly grey level distribution, in accordance with methods of the last group, is reported in this paper.…”

Offline Signature Verification Based on Pseudo-Cepstral Coefficients

“…Techniques from the field of forensic document examination mainly base on the microscopic inspection of the writing trace and assumptions about the underlying writing process [9]. Approaches from the field of image processing and pattern recognition can be divided in mathematical methods estimating the temporal order of stroke production [24,5]; in method inspired by motor control theory recovering temporal features on the base of stroke geometries such as curvature [25]; and finally, in methods analyzing stroke thickness and/or stroke intensity variations [1,4,11,20,7]. From last group, we considerate mainly gray level distribution.…”

Techniques for static handwriting trajectory recovery

“…In another work, El Baati et al [46] demonstrated that ambiguous zone detection could be performed in a simpler fashion. Their technique employs a square window sweeping through the image and counting the number of background regions parted by the handwriting simultaneously.…”

“…For a recovery system to be successful, such knowledge should be referred. In Arabic handwriting, branch points and end point are always located to the left of the start point [46]. For a Latin right-handed writer, the writing usually begins from the top left and progresses downwards to the right [53].…”

“…With the recent interest in stroke-level off-line signature verification [71], it is expected that trajectory recovery will attract more attention from the handwriting recognition community as it deserves. [36] 2000 Skeleton Handwriting 200 dpi, 100 single stroke drawing 91.6% Doermann et al [42] 2002 Contour Loops 1270 words by 5 individuals 84.0% El Baati et al [46] 2005 Contour Handwriting 50 Arabic words by 2 individuals 92.0% Lau et al [74] 2005 Skeleton Signatures 350 online training / 300 off-line testing 90.0% Nel et al [26] 2005…”