An Efficient Open System for Offline Handwritten Signature Identification based on Curvelet Transform and One-Class Principal Component Analysis

Handwritten signatures are widely utilized as a form of personal recognition However, they have the unfortunate shortcoming of being easily abused by those who would fake the identification or intent of an individual which might be very harmful Therefore, the need for an automatic signature recognition system is crucial In this paper, a signature recognition approach based on a probabilistic neural network (PNN) and wavelet transform average framing entropy (AFE) is proposed The system was tested with a wavelet packet (WP) entropy denoted as a WP entropy neural network system (WPENN) and with a discrete wavelet transform (DWT) entropy denoted as a DWT entropy neural network system (DWENN) Our investigation was conducted over several wavelet families and different entropy types Identification tasks, as well as verification tasks, were investigated for a comprehensive signature system study Several other methods used in the literature were considered for comparison Two databases were used for algorithm testing The best recognition rate result was achieved by WPENN whereby the threshold entropy reached 92%

/pdf/off-line-handwritten-signature-recognition-by-wavelet-4k91ms0s36.pdf

Off-Line Handwritten Signature Recognition by Wavelet Entropy and Neural Network

CapsNet regularization and its conjugation with ResNet for signature identification

Offline handwritten signatures is a convincing evidence form of biometrics for verification. However, the verification of offline handwritten signatures is challenging task because of the variations in handwritten signatures. To address this difficulty, this paper proposes a new approach to represent the shape. In this newly proposed approach, the signature pixels are represented by: (1) Gaussian Weighting Based Tangent Angle, to represent the curve angle at the reference pixel; (2) a new shape descriptor, i.e. cylindrical shape context is proposed for a detailed and accurate description of the curve at corresponding pixel. Experimental results show that desired pixel matching results are obtained by using cylindrical shape context which automatically increases the accuracy of verification of offline handwritten signatures. The shape dissimilarity measures are computed and given to the Support Vector Machine with Radial Basis Function (RBF) kernel for classification of signature. The results obtained using GPDS synthetic signature database, UTSig persian offline signature database, and MCYT-75 offline signature database shows the effectiveness of proposed cylindrical shape context.

Offline Handwritten Signature Verification Using Cylindrical Shape Context

Offline handwritten signature verification is widely used important form of biometrics. It is a challenging task due to time-variant nature of signature. To address the above difficulty, a new approach is proposed in this paper to compute the features of signatures. The proposed approach is divided into two parts: 1) writer-independent approach, 2) writer-dependent approach. Writer-independent approach is utilized for fine-tuning of VGG16 convolutional neural network (CNN). In writer-dependent approach, this fine-tuned CNN is utilized to extract the features from the signature. The signature is passed through this fine-tuned CNN and the vector obtained at first fully connected layer (after last convolutional layer) is used as feature vector. To obtain the accurate features for classification of signatures, the pixels of thinned signature image are replaced by their Gaussian Weighting Based Tangent Angle (GWBTA) in both writer-independent and writer-dependent approach. The computed features which are obtained in writer-dependent approach are fed to Support Vector Machine (SVM) classifier to classify the signature into genuine or forgery class. The performance results obtained on different databases of offline handwritten signatures confirms the validity of proposed methodology for offline signature verification.

Offline Signature Verification Using Convolutional Neural Network

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.

Muhammad Jehanzeb

Papers

Offline Handwritten Signature Identification Using Adaptive Window Positioning Techniques

Offline handwritten signature identification using adaptive window positioning techniques