Eigen Value Based Features for Offline Handwritten Signature Verification Using Neural Network Approach

A Deep Study on the Performance of the Spatial Density Distribution Method to Recognize Handwritten Signatures

“…On the other hand, the lack of dynamic information in the static mode complicates the process of implementation of these systems [20], [21]. Another challenge arises from the fact that the signature for the same person may be varied and affected by many factors such as age, gender, illness, psychological factors like fatigue, stress, or emotional state of the signer; the physical condition of the signer, like whether he is standing or sitting on a chair; lightning conditions; signing period; writing instrument; direction and inclination of signing; signature box size; and purpose of signing [22][23][24] In general, offline systems are preferred over online, because the signer need not be present at the time of signing, which means that the features of his or her signature could be extracted at any time [12], [18]. In contrast to online systems, offline systems are considered inexpensive as they digitize the signature into a 2D image after scanning the paper or using a digital camera.…”