Hand Signature Research Articles

In-Air Hand Gesture Signature Recognition Using Multi-Scale Convolutional Neural Networks

The hand signature is a unique handwritten name or symbol that serves as a proof of identity. Due to its practicality and widespread use, hand signature is still used by financial institutions as a means of verifying and validating the identity of their customers. The emergence of the COVID-19 global pandemic has raised hygiene concerns regarding the conventional touch-based hand signature recognition system, which often requires sharing the acquisition devices among the public. This paper presents in-air hand gesture signature recognition using convolutional neural networks to address this concern. We designed a shallow multi-scale convolutional neural network using 3x3 and 5x5 kernel filter sizes to extract features on different scales. The feature maps from these two filters are then concatenated to provide more robust features, which improve the model’s performance. The experiment results show that the proposed architecture outperforms other architectures, which obtained the highest accuracy of 93.00%. On the other hand, our architecture consumed significantly fewer computational resources, requiring only an average of 3 minutes and 33 seconds to train. Additionally, the performance of the proposed architecture could be further enhanced by integrating it with recurrent neural networks (RNN). This integrated architecture of convolutional recurrent neural networks (C-RNN) can capture spatio-temporal features simultaneously.

Automatic Verification for Handwritten Based on GLCM Properties and Seven Moments

In recent years, the need for community verification of personality has increased dramatically, and biometrics are becoming very important in many daily applications. Biometrics work to verify individuals based on measurable data for their descriptions and characteristics. Biometric systems have thus been able to verify or identify a person.
 The fact that the use of handwritten signatures are recognized in all societies, and because they are biometric, has made signature verification an important biometric process. In this paper, a number of models are collected from hand signatures for a person to study the characteristics of the parity matrix for each of these signatures for the purpose of finding common factors between the characteristics of the matrix of these models. The practical aspect summarizes the removal of all empty spaces outside the frame of the signature image to be followed by the process of unifying the dimensions, and then drawing four characteristics of the matrix of the dialogues. The process is conducted on a sample of 100 samples to sign the person to draw the qualities of his signature and then find the common characteristics among those four attributes of the signatures group.
 The tests conducted on 10 people proved that the adoption of the plastic qualities offers a clear distinction between people's manual signatures. More than 80% of the signatures of people who were approved for the test were found. Thus supporting the possibility of being adopted as a biometric standard for personal verification, Matlab has been adopted for the implementation of the software.

Off the Record

Off the Record

Offline Signature Identification Using Deep Learning and Euclidean Distance

Hand signature is one of human characteristic that human have since birth, which can be used as identity recognition. A high accuracy signature recognition is needed to identify the right owner of signature. This study present signature identification using a combination method between Deep Learning and Euclidean Distance. 3 different signature datasets are used in this study which consist of SigComp2009, SigComp2011, and private dataset. Signature images preprocessed using binary image conversion, Region of Interest, and thinning. Several testing scenarios is applied to measure proposed method robustness, such as usage of various Pretrained Deep Learning, dataset augmentation, and dataset split ratio modifier. The best accuracy achieved is 99.44% with high precision rate.

Dual-Mode Sensor and Actuator to Learn Human-Hand Tracking and Grasping

Humans can track, grasp, and learn hand signatures while applying the subtle pressure values. An integrated sensory array and the actuator are the building blocks of a mechanical flexible system for detecting subtle pressure changes and transduction. However, due to different governing mechanisms of sensors and actuators, it is still challenging to fabricate sensors and actuators from the same structures, which limits the devices integration. Here, we report the synthesis of graphene (Gr)–graphene oxide (GO) heterostructure film and the application of Gr–GO heterostructure film in smart sense and action. Such smart flexible sensors-based Gr–GO heterostructure film could be applied to the hand tracking recognition with an advanced artificial intelligence (AI) recognition algorithm of 99.4% classification accuracy. The smart actuator-based Gr–GO heterostructure film can grasp objects like robotic arm simultaneously. This brief paves the way for a future all-in-one flexible smart sense-action system.

Peranan Kontur dan Slope dalam Pengenalan Keaslian Tanda Tangan Menggunakan Dynamic Time Warping dan Polar Fourier Transform

The writer has seen that so far signatures are just validated manually, so there is possibility to create a system for hand signature recognition. The objective of this research is to improve the method for hand signature recognition using combination method with different characteristic. Contour and slope used for special feature in this research. Contour and slope from image will be applied using Dynamic Time Warping (DTW). Another extraction feature that been used was Polar Fourier Transform (PFT). The method employed for classification are Support Vector Machine (SVM).From the research results, the writer obtains the fact that the combination between the DTW and PFT using SVM classification, provide the better results in verification of an authentic hand signature with the accuracy of 93.23%. it is expected that from this research, the results can be utilized in the process of verification of an authentic hand signature in near future dailylife.

Authentication System for Any Touch Devices Using DWT

In today's world, the identification techniques based on human biometric features gaining much more importance. For e.g. Iris recognition system, face recognition system, finger print recognition system, retina scanning system, etc. Some important area of other techniques is also to recognize the human hand signature. Also, there is the requirement of some techniques which works automatically based on some standard computer algorithms for recognition. For e.g. to identify the criminal identity automatically based on biometric features. The aim of research is to develop an on-line system for signature verification using Discrete Wavelet Transform (DWT). Discrete Wavelet Transform (DWT) algorithm is used for features extraction. In online signature dynamic features are usually available. Genuine or Forgery signature is substantiating based features comparison. Each feature of an input signature is extracted using various steps discrete wavelet transform algorithm are matched against a reference signature to identify the genuine signature. The final decision of verification is made based on the matched features of both the signatures.

Paperless and Soulless

E-signatures are one of the fastest growing global practices because of their convenience. Much less is known, however, about whether people perceive e-signatures to be symbolically equivalent to traditional hand signatures. Results of four studies demonstrate that although functionally the same, e-signatures evoked markedly different psychological reactions than hand signatures. Namely, e-signatures evoked a weaker sense of the signer’s presence and involvement. This weaker sense of social presence, in turn, induced negativity: People were more likely to discount the validity of an e-signed application than that of an identical application signed by hand. They also anticipated that e-signed contracts would lead to greater likelihood of contract breaches. This negativity toward e-signatures persisted across five different types of e-signatures, regardless of an individual’s level of comfort with technology. Taken together, the studies reveal deeply rooted psychological reactions to a practice that is now prevalent worldwide.

Efficient online signature authentication approach

Signature authentication systems often have to focus their processing on acquired dynamic and/or static signatures descriptors to authenticate persons. This approach gives satisfactory results in ordinary cases but remains vulnerable against skilled forgeries. This is mainly because there is no relation between the signatory and his signature. We will show that the inclusion of the hand shape in the authentication process will considerably reduce the false acceptance rates of skilled forgeries and improve the authentication accuracy performances. A new online hand signature authentication approach based on both signature and hand shape descriptor is proposed. The signature acquisition is completely transparent, which allows a high level of security against fraudulent imitation attempts. Authentication performances are evaluated with extensive experiments. The obtained test results [equal error rate (EER)=2%, genuine acceptance rate (GAR)=96%]confirm the efficiency of the proposed approach.

"What’s in a Name: Hand Signatures Censor, while Electronic Signatures Condone, Cheating"

E-signatures are one of the fastest growing global sectors. Indeed, e-signatures can provide greater efficiency than traditional hand signatures. Much less is known, however, about e-signatures’ effectiveness in preventing unethical behaviors—one of the fundamental functions of a signature. This research directly assesses the possibility that while hand signatures typically censor cheating, e-signatures may condone it. Results from five studies consistently demonstrated that e-signatures are largely ineffective in curbing cheating behavior. Furthermore, e-signatures fundamentally transform the way people perceive their unethical behavior by loosening what is deemed morally acceptable. Finally, these effects were caused by the e-signature’s inability to evoke the signer’s self-concept. This research also assessed an easy-to-implement solution that could preserve the efficiency of e-signatures while adding the force of compliance inherent to hand signatures. By systematically examining whether and why e-signatures condone cheating, findings from this research illuminate an unintentional—yet critical—consequence of a practice that is now prevalent worldwide.

Extreme Learning Machines [Trends & Controversies

This special issue includes eight original works that detail the further developments of ELMs in theories, applications, and hardware implementation. In "Representational Learning with ELMs for Big Data," Liyanaarachchi Lekamalage Chamara Kasun, Hongming Zhou, Guang-Bin Huang, and Chi Man Vong propose using the ELM as an auto-encoder for learning feature representations using singular values. In "A Secure and Practical Mechanism for Outsourcing ELMs in Cloud Computing," Jiarun Lin, Jianping Yin, Zhiping Cai, Qiang Liu, Kuan Li, and Victor C.M. Leung propose a method for handling large data applications by outsourcing to the cloud that would dramatically reduce ELM training time. In "ELM-Guided Memetic Computation for Vehicle Routing," Liang Feng, Yew-Soon Ong, and Meng-Hiot Lim consider the ELM as an engine for automating the encapsulation of knowledge memes from past problem-solving experiences. In "ELMVIS: A Nonlinear Visualization Technique Using Random Permutations and ELMs," Anton Akusok, Amaury Lendasse, Rui Nian, and Yoan Miche propose an ELM method for data visualization based on random permutations to map original data and their corresponding visualization points. In "Combining ELMs with Random Projections," Paolo Gastaldo, Rodolfo Zunino, Erik Cambria, and Sergio Decherchi analyze the relationships between ELM feature-mapping schemas and the paradigm of random projections. In "Reduced ELMs for Causal Relation Extraction from Unstructured Text," Xuefeng Yang and Kezhi Mao propose combining ELMs with neuron selection to optimize the neural network architecture and improve the ELM ensemble's computational efficiency. In "A System for Signature Verification Based on Horizontal and Vertical Components in Hand Gestures," Beom-Seok Oh, Jehyoung Jeon, Kar-Ann Toh, Andrew Beng Jin Teoh, and Jaihie Kim propose a novel paradigm for hand signature biometry for touchless applications without the need for handheld devices. Finally, in "An Adaptive and Iterative Online Sequential ELM-Based Multi-Degree-of-Freedom Gesture Recognition System," Hanchao Yu, Yiqiang Chen, Junfa Liu, and Guang-Bin Huang propose an online sequential ELM-based efficient gesture recognition algorithm for touchless human-machine interaction.

Robust Facial Data Recognition using Multimodal Fusion Features in Multi-Variant Face Acquisition

Biometric use physiological traits such as fingerprints, face and behavioral traits such as voice, hand signatures characteristics to verify an individual’s identity. The two process involved in biometrics are verification and identification. Verification process is performed by matching an individual’s biometric with the template of claimed identity only. The identification process performed by matching an individual’s biometric with template of every identity in the database. Existing work presented a multimodal (2D and 3D) face recognition algorithm by way of performing hybrid matching which was based on both feature and holistic metrics. The Pose of 3D face and its texture corrected using single automatically detected point and hotelling transform. 3D Spherical Face Representation (SFR) is used in conjunction with Scale-Invariant Feature Transform (SIFT) descriptor which results in formation of a rejection classifier. It quickly eliminates a large number of candidate faces at an early stage for efficient recognition for known faces as attributes. Our proposed work presented a Feature Based Multimodality Face Recognition System to recognize the human individuals in environment of known faces using features like shape of the eyes, nose and jaw. Case study and preliminary experimental results conducted in Mat lab proves to be a viable approach using multimodality method based on 2D and 3D facial representation for known faces. Facial recognition rate is measured in terms of validation index generated for false acceptance rate, false rejection rate.

Application of Biometrics in Corporations – A Case of Indian Banking Sector

Biometrics is becoming very much an essence today. There are various biometric products and one can encounter an excess of fingerprint scanners, voice and facial recognition system, retina/iris scanners, hand geometry devices and signature verification systems. This paper looks at the tools of biometrics, their implementation in the Indian Banking Sector, and critically evaluates them.

Online Hand Signature Verification: A Review

Online Hand Signature Verification: A Review

SURFACE MORPHOLOGY OF CHALKBOARD TIPS CAPTURES THE UNIQUENESS OF THE USER'S HAND STROKES

Penmanship has a high degree of uniqueness as exemplified by the standard use of hand signature as identifier in contract validations and property ownerships. In this work, we demonstrate that the distinctiveness of one's writing patterns is possibly embedded in the molding of chalk tips. Using conventional photometric stereo method, the three-dimensional surface features of blackboard chalk tips used in Math and Physics lectures are microscopically resolved. Principal component analysis (PCA) and neural networks (NN) are then combined in identifying the chalk user based on the extracted topography. We show that NN approach applied to eight lecturers allow average classification accuracy (Φ NN ) equal to 100% and 71.5 ± 2.7% for the training and test sets, respectively. Test sets are chalks not seen previously by the trained NN and represent 25% or 93 of the 368 chalk samples used. We note that the NN test set prediction is more than five-fold higher than the proportional chance criterion (PCC, Φ PCC = 12.9%), strongly hinting to a high degree of unique correlation between the user's hand strokes and the chalk tip features. The result of NN is also about three-fold better than the standard methods of linear discriminant analysis (LDA, Φ LDA = 27.0 ± 4.2%) or classification and regression trees (CART, Φ CART = 17.3 ± 3.7%). While the procedure discussed is far from becoming a practical biometric tool, our work offers a fundamental perspective to the extent on which the uniqueness of hand strokes of humans can be exhibited.

Completing the circuit in e‐government process automation

Purpose – The purpose of this paper is to provide a technique that helps in completing the automation cycle in e‐government and e‐business transactions. Some e‐government and e‐business transactions require the physical intervention of a user or an employee to place a physical stamp or a hand signature on a document. This paper suggests a digital watermarking approach for online hand signatures and physical stamps. The suggested technique may be used by individuals or organizations to place hand signatures and stamps on remote documents.Design/methodology/approach – The work started by surveying existing security protocols and authentication techniques. Digital watermarking techniques have then been deeply studied to investigate their security capabilities and effect on the performance of the system. A scenario‐based approach has then been used to derive a number of secure digital watermarking protocols that may be used to place remote physical signatures and stamps. The derived protocols were then audite...

Secure Hashing of Dynamic Hand Signatures Using Wavelet-Fourier Compression with BioPhasor Mixing and Discretization

We introduce a novel method for secure computation of biometric hash on dynamic hand signatures using BioPhasor mixing and 2N discretization. The use of BioPhasor as the mixing process provides a one-way transformation that precludes exact recovery of the biometric vector from compromised hashes and stolen tokens. In addition, our user-specific 2N discretization acts both as an error correction step as well as a real-to-binary space converter. We also propose a new method of extracting compressed representation of dynamic hand signatures using discrete wavelet transform (DWT) and discrete fourier transform (DFT). Without the conventional use of dynamic time warping, the proposed method avoids storage of user's hand signature template. This is an important consideration for protecting the privacy of the biometric owner. Our results show that the proposed method could produce stable and distinguishable bit strings with equal error rates (EERs) of 0% and 9.4% for random and skilled forgeries for stolen token (worst case) scenario, and 0% for both forgeries in the genuine token (optimal) scenario.

Development and validation of a performance-based measure of upper extremity functional limitation

While the standardized lower extremity physical performance battery (LEPPB) is widely used to measure lower body functional limitation, no corresponding measure has been developed for upper body functional limitation. We combined three standard measures (William's Hand Test, Hand Signature, Functional Reach) to develop an upper extremity physical performance battery (UEPPB) analogous to the LEPPB, and examined its validity. We used baseline data from a community-dwelling cohort of 749 Mexican American and European American elders and combined times to complete the William's Hand Board, Hand Signature, and distance on Functional Reach into a single composite measure, using scoring methods analogous to those for the LEPPB. We summarize concurrent, discriminant, and construct validity evidence for the UEPPB, based on observed associations with established measures of physical functional limitation, disability, and dependence. All correlations were in the expected direction. Shared variance with self-reported upper and lower extremity functional limitation was 10 and 5%, respectively, and with self-reported ADL disability, ADL dependency, and IADL dependency it was 32, 26, and 31%, respectively. In multivariate models of self-reported and performance-based disability and dependency, the UEPPB and LEPPB made significant, independent contributions and, net of contextual variables (age, sex, ethnic group, education, income) explained 4 to 10% of the variance in disability and dependency. The UEPPB is a valid performance-based measure of upper extremity functional limitation and makes an independent contribution beyond LEPPB in explaining disability and dependence.

GloveSignature: A Virtual-Reality-Based System for Dynamic Signature Verification

A survey of the principal schemes in the literature suggested that a new way of addressing the problem of signature recognition be formulated in order to find a satisfactory solution for eliminating random forgeries. A fundamental problem in the field of off-line signature recognition is the lack of a pertinent shape representation or shape factor. This paper introduces a novel idea for a dynamic signature recognition system. An initial attempt is presented to demonstrate the data glove as an effective high-bandwidth data entry device for signature recognition. GloveSignature is a virtual-reality-based environment to support the signing process. The proposed approach retains the power to discriminate against forgeries. This paper extends the use of instrumented data gloves—gloves equipped with sensors for detecting finger bend and hand position and orientation for recognizing hand signatures. Several researchers have already explored the use of gloves in other application areas but using the gloves for the recognition of hand signatures has never been reported. An attempt is made in this research to explore the feasibility of using the 5th Glove in on-line signature recognition. Two hundred signatures were collected from 20 subjects, and features were extracted. We demonstrate the effectiveness of a hybrid technique, which is based on both the most discriminating eigenfeatures and the self-organizing maps (SOFMs) for signature recognition.