Writer's identification by using word reason feature transform
Prashant Madhukar Patil, R. B. Wagh · 2016
Automatic identification of the author of a document has a variety of applications for both online and offline handwritten data such as facilitating the use of writer-dependent recognizer's verification of claimed identity for security, enabling personalized HCI and countering repudiations for legal purposes. Most of the existing writer identification techniques require the data to be from a specific text or a recognizer be available, which is not always feasible. Text-independent approaches often require large amount of data to be confident of good results. Unique offline text independent author identification methodology supported scale invariant feature remodel (SIFT), composed of coaching, enrollment, and identification stages. Altogether stages, associate degree identical LoG filter are initial wont to phase the handwriting image into word regions (WRs). Then, the SIFT descriptors (SDs) of WRs and also the corresponding scales and orientations (SOs) square measure extracted. Within the coaching stage, associate degree Coyote State codebook is made by agglomeration the SDs of coaching samples. Within the enrollment stage, the Coyote States of the input handwriting square measure adopted to make associate degree Coyote State signature (SDS) by trying up the SD codebook and also the SOs square measure utilized to get a scale and orientation bar graph (SOH). Within the identification stage, the SDS and sol of the input handwriting square measure extracted and matched with the registered ones for identification. Support Vectors Machines (SVM) have recently shown their ability in pattern recognition and classification.