Offline handwritten signature identification using adaptive window positioning techniques
This addresses signature identification for security applications, though it appears incremental as it builds on window-based feature extraction methods.
The paper tackles offline handwritten signature identification by proposing an Adaptive Window Positioning technique that divides signatures into 13 small windows to capture writer individuality, achieving efficient and reliable feature extraction as tested on a dataset of 4870 signatures from 90 writers.
The paper presents to address this challenge, we have proposed the use of Adaptive Window Positioning technique which focuses on not just the meaning of the handwritten signature but also on the individuality of the writer. This innovative technique divides the handwritten signature into 13 small windows of size nxn(13x13).This size should be large enough to contain ample information about the style of the author and small enough to ensure a good identification performance.The process was tested with a GPDS data set containing 4870 signature samples from 90 different writers by comparing the robust features of the test signature with that of the user signature using an appropriate classifier. Experimental results reveal that adaptive window positioning technique proved to be the efficient and reliable method for accurate signature feature extraction for the identification of offline handwritten signatures.The contribution of this technique can be used to detect signatures signed under emotional duress.