<title>Artificial neural networks architecture for handwritten signature authentication</title>

For the problem that the early fault information of diesel engine system is weak and difficult to identify and diagnose, an early fault diagnosis method based on cross-point frequency response and static and dynamic information fusion was proposed for the assembly quality of diesel engine system. The dynamic vibration response signal and static cross-point frequency response signal of the diesel engine system were collected by reasonable layout of measuring points. After CEEMD reconstruction and de-noising, the sample entropy and approximate entropy were extracted as characteristic parameters of the dynamic signal, and the frequency response features were extracted from the static signal. The static and dynamic information of the two kinds of information was integrated by PCA. The optimized support vector machine is used to identify the dynamic information and the static and dynamic fusion information respectively. The results show that this method can effectively detect the assembly quality of key components of diesel engine system, and the accuracy of diagnosis is up to 95%, and the recognition rate after static and dynamic information fusion is better than that of dynamic information. The method presented in this paper has a good application prospect in the assembly quality inspection and early fault diagnosis of diesel engine system.

A declarative approach to detecting design patterns from Java execution traces and source code

In this paper, we proposed Discrete Radon Transform (DRT) technique for feature extraction of static signature recognition to identify forgeries. Median filter has been introduced for noise cancellation of handwritten signature. This paper describes static signature verification techniques where signature samples of each person was collected and cropped by automatic cropping system. Projection based global features are extracted like Horizontal, Vertical and combination of both the projections, these all are one dimensional feature vectors to recognize the handwritten static signature. The distance between two corresponding vectors can be measured with Dynamic Time Warping algorithm (DTW) and using only six genuine signatures samples of each person has been employed here in order to train our system. In the proposed system process time required for training our system for each person is between 1.5 to 4.2 seconds and requires less memory for storage. The optimal performance of the system was found using proposed technique for Combined projection features and it gives FAR of 5.60%, FRR of 8.49% and EER 7.60%, which illustrates such new approach to be quite effective and reliable.

Dynamic analysis extracts information that describes the structure of the runtime behavior of a software system. This information, typically represented in the form of execution traces, is useful in many software modernization activities, such as reverse engineering and program analysis. The Architecture-Driven Modernization initiative has defined standards to support the modernization process in the context of Model-Driven Engineering (MDE). However, to date, there is no standard for representing runtime information that allows the specification of dynamic information independent of any programming language. In light of this, we present TRACEM, a metamodel for representing trace information under a standard representation that would allow traces to become a new domain in software engineering. The purpose of defining TRACEM is to complement an MDE framework for software modernization that aims to integrate static and dynamic analysis techniques during the reverse engineering process. This article contains a description of TRACEM and a case study that illustrates how dynamic information combined with static information allows for improving the whole reverse engineering process.

This work explores human intervention to improve Automatic Signature Verification (ASV). Significant efforts have been made in order to improve the performance of ASV algorithms over the last decades. This work analyzes how human actions can be used to complement automatic systems. Which actions to take and to what extent those actions can help state‐of‐the‐art ASV systems is the final aim of this research line. The analysis at classification level comprises experiments with responses from 500 people based on crowdsourcing signature authentication tasks. The results allow to establish a human baseline performance and comparison with automatic systems. Intervention at feature extraction level is evaluated using a self‐developed tool for the manual annotation of signature attributes inspired in Forensic Document Experts analysis. We analyze the performance of attribute‐based human signature authentication and its complementarity with automatic systems. The experiments are carried out over a public database including the two most popular signature authentication scenarios based on both online (dynamic time sequences including position and pressure) and offline (static images) information. The results demonstrate the potential of human interventions at feature extraction level (by manually annotating signature attributes) and encourage to further research in its capabilities to improve the performance of ASV.

This paper proposes novel framework for facial expressions analysis using dynamic and static information in video sequences. First, based on incremental formulation, discriminative deformable face alignment method is adapted to locate facial points to correct in‐plane head rotation and break up facial region from background. Then, spatial‐temporal motion local binary pattern (LBP) feature is extracted and integrated with Gabor multiorientation fusion histogram to give descriptors, which reflect static and dynamic texture information of facial expressions. Finally, a one‐versus‐one strategy based multiclass support vector machine (SVM) classifier is applied to classify facial expressions. Experiments on Cohn‐Kanade (CK) + facial expression dataset illustrate that integrated framework outperforms methods using single descriptors. Compared with other state‐of‐the‐art methods on CK+, MMI, and Oulu‐CASIA VIS datasets, our proposed framework performs better.

How to fuse static and dynamic information is a key issue in event analysis. In this paper, a top-down motion guided fusing method is proposed for recognizing events in an unconstrained news video. In the method, the static information is represented as a Bag-of-SIFT-features and motion information is employed to generate event specific attention map to direct the sampling of the interest points. We build class-specific motion histograms for each event so as to give more weight on the interest points that are discriminative to the corresponding event. Experimental results on TRECVID 2005 video corpus demonstrate that the proposed method can improve the mean average accuracy of recognition.

This paper presents an effective procedure to select the reference specimens for a signature verification system. Specifically, from the analysis of local stability in handwritten signatures, a suitable measure is proposed to determine the capability of different sets of signatures in supporting effective verification. The measure uses a correlation-based criterium which detects and recovers non-linear time distortions in different specimens. In the experimental test, the selected set of signatures has been used for reference in a system for dynamic signature verification based on a multi-expert verification strategy. The experimental results points out the capability of the new technique in selecting effective reference signatures.

INFORMATION-BASED EVACUATION EXPERIMENT AND ITS CELLULAR AUTOMATON SIMULATION

This paper proposes a method (SDP method) of off-line signature verification incorporating a sequential application of the dynamic programming matching method in its preprocessing stage. Based on the frequencies of black pixels in each signature projected on the x-axis, the SDP method determines an optimum segmentation of any signature into the same number of components as the representative reference signature. The SDP method measures the dissimilarity between the suspect signature and the representative signature, and accept the suspect signature as genuine without any further scrutiny, if the dissimilarity is below a threshold. When the suspect signature is not accepted, the SDP method subsequently applies a verification procedure proposed by Yoshimura and Yoshimura(1997) to it. This paper evaluates also the effectiveness of the SDP method through an experiment using a database of 800 Japanese signatures, half of which were obtained on the area of countersignature on sheets similar to a traveler's check, whereas the remaining were on the area of authentic signature. The experiment used the countersignatures as suspect signatures to obtain estimates of mis-verification rate, taking five signatures alternatively from the twenty authentic signatures as the reference signatures. It achieved values as low as 12.9% in an average mis-verification rate.KeywordsReference SignatureDynamic Programming AlgorithmDynamic Time WarpingInput SignatureBlack PixelThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

This paper reports the design, implementation, and evaluation of a research work for developing an automatic person identification system using hand signatures biometric. The developed automatic person identification system mainly used toolboxes provided by MATLAB environment‥ In order to train and test the developed automatic person identification system, an in-house hand signatures database is created, which contains hand signatures of 100 persons (50 males and 50 females) each of which is repeated 30 times. Therefore, a total of 3000 hand signatures are collected. The collected hand signatures have gone through pre-processing steps such as producing a digitized version of the signatures using a scanner, converting input images type to a standard binary images type, cropping, normalizing images size, and reshaping in order to produce a ready-to-use hand signatures database for training and testing the automatic person identification system. Global features such as signature height, image area, pure width, and pure height are then selected to be used in the system, which reflect information about the structure of the hand signature image. For features training and classification, the Multi-Layer Perceptron (MLP) architecture of Artificial Neural Network (ANN) is used. This paper also investigates the effect of the persons' gender on the overall performance of the system. For performance optimization, the effect of modifying values of basic parameters in ANN such as the number of hidden neurons and the number of epochs are investigated in this work. The handwritten signature data collected from male persons outperformed those collected from the female persons, whereby the system obtained average recognition rates of 76.20% and74.20% for male and female persons, respectively. Overall, the handwritten signatures based system obtained an average recognition rate of 75.20% for all persons.

Both radar and AIS (automatic identification system) are the most important navigational equipment for a ship. But, there are some differences between them in the performance and the target information. The paper studied the difference and characteristic of the dynamic target information from the radar and the AIS. Based on the survey platform of the target information system developed by the own, measurements were vastly done for the target's dynamic information, including position, speed and course. It evaluated the differences between them, and got the very important statistic results. It offers not only the valuable references for the voyager to understand and identify the target information characteristic, but also the research foundation of the information processing such as target information fusion, and the intelligent ship collision avoidance and so on.

Handwritten signatures are one of the most commonly used biometrics. Because signatures are widely accepted, their verification is a fundamental problem. The aim of signature verification is to decide about the origin of the signature so the ability to detect forgeries. Until offline signature verification is based on the scanned image of the signatures, online signature verification applies different electronic devices to capture the signatures. Online signatures also contain dynamic information such as the pressure or inclination angle of the pen, so it is much more challenging to forge online signatures than offline ones. In addition, it is possible to define and calculate further derived features based on the captured ones. The captured features are usually function features, which means they assign a value to each signature point or specified sets of signature points. This work aims to compare the usability of common derived function features using a dynamic time warping (DTW) based solution.

Handwritten signature identification is a process that determines an individual’s true identity by analyzing their signature. This is an important task in various applications such as financial transactions, legal document verification, and biometric systems. Various techniques have been developed for signature identification, including feature-based methods and machine learning-based methods. However, verifying handwritten signatures in digital transactions and remote document authentication is still challenging. The inherent variety in people’s signatures, which may occur due to factors such as mood, exhaustion, or even the writing tool used, contributes to the problem. Furthermore, the proliferation of sophisticated forgery methods, such as freehand mimicking and sophisticated picture manipulation, necessitates the development of reliable and precise tools for identifying authentic signatures from fake ones.The present paper suggests a method for identifying signatures based on integrating static (off-line) handwritten signature data. This is done by fusing three types of signature features: Linear Discriminant Analysis (LDA) as appearance-based features, Fast Fourier Transform (FFT) as frequency-features, and Gray-Level Co-occurrence Matrix (GLCM) as texture-features. Then, these fused features are inputted into four types of machine learning algorithms: Naive Bayes, K-Nearest Neighbor, Decision Tree, and AdaBoost classifiers, to identify each person and to find the most robust algorithm in terms of accuracy and precision and recall. For experiments, we have used two famous datasets: SigComp2011 and CEDAR. After training datasets, the highest accuracy achieved was 100% on the CEDAR dataset and 94.43% on the SigComp2011 dataset using a Naive Bayes classifier. Index Terms— Fast Fourier Transform, Gray-Level Co-occurrence Matrix, Handwritten Signature, Linear Discriminant Analysis, Machine Learning.

The problems of authentication and identification have received wide interest in cryptographic research. However, there has been no satisfactory solution for the problem of authentication by a human recipient who does not use any trusted computational device, which arises for example in the context of smartcard-human interaction, in particular in the context of electronic wallets. The problem of identification is ubiquitous in communication over insecure networks.