Extraction of Dynamic Trajectory on Multi-Stroke Static Handwriting Images Using Loop Analysis and Skeletal Graph Model

Abstract

The recovery of handwritings dynamic stroke is an effective method to help improve the accuracy of anyhandwritings authentication or verification system. The recovered trajectory can be considered as a dynamic feature ofany static handwritten images. Capitalising on this temporal information can significantly increase the accuracy of theverification phase. Extraction of dynamic features from static handwritings remains a challenge due to the lack of temporalinformation as compared to the online methods. Previously, there are two typical approaches to recover the handwritingsstroke. The first approach is based on the scripts skeleton. The skeletonisation method has highly computational efficiencywhereas it often produces noisy artifacts and mismatches on the resulted skeleton. The second approach deals with thehandwritings contour, crossing areas and overlaps using parametric representations of lines and thickness of strokes. Thismethod can avoid the artifacts, but it requires complicated mathematical models and may lead to computational explosion.Our paper is based on the scripts extracted skeleton and provides an approach to processing static handwritings objects,including edges, vertices and loops, as the important aspects of any handwritten image. Our paper is also to provideanalysing and classifying loops types and humans natural writing behavior to improve the global construction of strokeorder. Then, a detailed tracing algorithm on global stroke reconstruction is presented. The experimental results reveal thesuperiority of our method as compared with the existing ones.