Machine learning for detection of interictal epileptiform discharges.

Despite the imitability of the signatures due to presence of numerous image processing programs, online verification systems could provide sufficient security for e-signatures. Recent developments in touchscreen technology and android programming also lead to utilization of hidden interfaces stealthily collecting the unique characteristics and storing the key features aside from geometrics. Therefore, we initially designed a signing interface for touchscreens which stealthily collects the precise coordinates while an individual is signing on the screen by fingertips. Even if the coordinate data is extracted as a matrix consisting of x and y values with corresponding time, the speed array is consequently calculated to investigate the higher frequency regions. The speed data processed by continuous wavelet transformations (CWT) to reveal the frequency information of the signing speed with respect to time information. The grayscale spectrograms created by wavelet transforms are converted into arrays for subsequent training session performed by support vector machines (SVM). The trained network successfully classified further attempts of the real and fake signatures with 1.67% false negative (FNR), 3.33% false positive rates (FPR) and 3.41% equal error rate (EER) for 120 signatures, even though the signature is totally public. For understanding the validity of the CWT and SVM running consecutively, the experiments are re-conducted for the signatures taken from SVC2004 and SUSIG public databases.

Online signature verification by continuous wavelet transformation of speed signals

Many techniques have been published on handwriting signature recognition, but none of these techniques presented are about Uyghur handwritten signature due to its complex nature. In this paper, we propose methods for off-line signature recognition for Uyghur handwriting first time. The signature images were pre-processed based on the nature of Uyghur signature. The preprocessing included noise reduction, binarization and normalization. Then multi-dimensional modified grid information features were extracted according to the character of Uyghur signature and its writing style. Finally, three kinds of classification techniques were used: Euclidean distance (ED) classifier, K nearest neighbor (K-NN) classifier and Bayes classifier. Experiments were performed using Uyghur signature samples from 50 different people with 1000 signatures. A promising result of 93.53% average correct recognition rate was achieved.

http://www.sce.carleton.ca/faculty/adler/publications/2012/ubul-ISSAP2012-offline-signature.pdf

Off-line Uyghur signature recognition based on modified grid information features

A novel approach for off-line signature recognition system is presented in this work, which is based on local radon features. The proposed system functions in three stages. Pre-processing stage, which consists of three steps: gray scale conversion, binarisation and fitting boundary box in order to make signatures ready for feature extraction, Feature extraction stage, where totally 16 radon transform based projection features are extracted which are used to distinguish the different signatures. Finally in Neural Network stage, an efficient Back Propagation Neural Network (BPNN) is designed and trained with 16 extracted features. The trained Neural Network is further used for signature recognition after the process of feature extraction. The average recognition accuracy obtained using this model ranges from 97%-87% with the training set of 10-40 persons.

Offline Signature Recognition System Using Radon Transform

A new approach for verifying off-line Persian signatures is presented, in this paper. In our method, feature extraction step is conducted based on estimated Fractal Dimension (FD) of signatures images, and making decision about acceptance/rejection of test signature is formulated as testing hypothesis which is used for the first time in order to verify offline Persian signatures. The proposed method has been tested on our new created database included 1000 genuine signatures and 200 skilled forgeries which have been collected from a population of 100 human subjects with different educational background. Obtained results confirm the effectiveness of the presented method.

Persian Signature Verification Based on Fractal Dimension Using Testing Hypothesis

In this work a new offline signature recognition system based on Radon Transform, Fractal Dimension (FD) and Support Vector Machine (SVM) is presented. In the first step, projections of original signatures along four specified directions have been performed using radon transform. Then, FDs of four obtained vectors are calculated to construct a feature vector for each signature. These vectors are then fed into SVM classifier for recognition of signatures. In order to evaluate the effectiveness of the system several experiments are carried out. Offline signature database from signature verification competition (SVC) 2004 is used during all of the tests. Experimental result indicates that the proposed method achieved high accuracy rate in signature recognition.

Designing an Offline Method for Signature Recognition

are short-time broadband events, which can last 20ms- 70ms and amplitude is among 100μV-200μV. In this research, a novel spike detection method based on stationary wavelet transform (SWT) and time-varying autoregressive model is proposed. In the proposed method, the discrete stationary wavelet transform is initially applied on the signal under analysis to show the important underlying unadulterated form of the data. The time-varying AR (TVAR) is used as an effective tool for analyzing non-stationary signals such as spikes. The performance of the proposed method is compared with other existing methods using both synthetic signals and real newborn Electroencephalogram (EEG). The simulation results indicate the absolute advantages of the proposed method.

/pdf/eeg-spike-detection-using-stationary-wavelet-transform-and-2ihtj327vt.pdf

Mehdi Radmehr

Papers

Designing an Offline Method for Signature Recognition

EEG Spike Detection using Stationary Wavelet Transform and Time-Varying Autoregressive Model