An Enhanced Hybrid Model Based on CNN and BiLSTMfor Identifying Individuals via Handwriting Analysis

Handwriting is a unique and significant human feature that distinguishes them from one another.There are many researchers have endeavored to develop writing recognition systems utilizing specific signatures or symbols for person identification through verification.However,such systems are susceptible to forgery,posing security risks.In response to these challenges,we propose an innovative hybrid technique for individual identification based on independent handwriting,eliminating the reliance on specific signatures or symbols.In response to these challenges,we propose an innovative hybrid technique for individual identification based on independent handwriting,eliminating the reliance on specific signatures or symbols.Our innovative method is intricately designed,encompassing five distinct phases:data collection,preprocessing,feature extraction,significant feature selection,and classification.One key advancement lies in the creation of a novel dataset specifically tailored for Bengali handwriting(BHW),setting the foundation for our comprehensive approach.Post-preprocessing,we embarked on an exhaustive feature extraction process,encompassing integration with kinematic,statistical,spatial,and composite features.This meticulous amalgamation resulted in a robust set of 91 features.To enhance the efficiency of our system,we employed an analysis of variance(ANOVA)F test and mutual information scores approach,meticulously selecting the most pertinent features.In the identification phase,we harnessed the power of cutting-edge deep learning models,notably the Convolutional Neural Network(CNN)and Bidirectional Long Short-Term Memory(BiLSTM).These models underwent rigorous training and testing to accurately discern individuals based on their handwriting characteristics.Moreover,our methodology introduces a groundbreaking hybrid model that synergizes CNN and BiLSTM,capitalizing on fine motor features for enhanced individual classifications.Crucially,our experimental results underscore the superiority of our approach.The CNN,BiLSTM,and hybrid models exhibited superior performance in individual classification when compared to prevailing state-of-the-art techniques.This validates our method’s efficacy and underscores its potential to outperform existing technologies,marking a significant stride forward in the realm of individual identification through handwriting analysis.

Person-Dependent Handwriting Verification for Special Education Using DeepLearning

Individuals with special needs learn more slowly than their peers and they need repetitions to be permanent.However,in crowded classrooms,it is dif-ficult for a teacher to deal with each student individually.This problem can be overcome by using supportive education applications.However,the majority of such applications are not designed for special education and therefore they are not efficient as expected.Special education students differ from their peers in terms of their development,characteristics,and educational qualifications.The handwriting skills of individuals with special needs are lower than their peers.This makes the task of Handwriting Recognition(HWR)more difficult.To over-come this problem,we propose a new personalized handwriting verification sys-tem that validates digits from the handwriting of special education students.The system uses a Convolutional Neural Network(CNN)created and trained from scratch.The data set used is obtained by collecting the handwriting of the students with the help of a tablet.A special education center is visited and the handwrittenfigures of the students are collected under the supervision of special education tea-chers.The system is designed as a person-dependent system as every student has their writing style.Overall,the system achieves promising results,reaching a recognition accuracy of about 94%.Overall,the system can verify special educa-tion students’handwriting digits with high accuracy and is ready to integrate with a mobile application that is designed to teach digits to special education students.

Handwriting Classification Based on Support Vector Machine with Cross Validation

Support vector machine (SVM) has been successfully applied for classification in this paper. This paper discussed the basic principle of the SVM at first, and then SVM classifier with polynomial kernel and the Gaussian radial basis function kernel are choosen to determine pupils who have difficulties in writing. The 10-fold cross-validation method for training and validating is introduced. The aim of this paper is to compare the performance of support vector machine with RBF and polynomial kernel used for classifying pupils with or without handwriting difficulties. Experimental results showed that the performance of SVM with RBF kernel is better than the one with polynomial kernel.

Automated Handwriting Recognition and Speech Synthesizer for Indigenous Language Processing

In recent years,researchers in handwriting recognition analysis relating to indigenous languages have gained significant internet among research communities.The recent developments of artificial intelligence(AI),natural language processing(NLP),and computational linguistics(CL)find useful in the analysis of regional low resource languages.Automatic lexical task participation might be elaborated to various applications in the NLP.It is apparent from the availability of effective machine recognition models and open access handwritten databases.Arabic language is a commonly spoken Semitic language,and it is written with the cursive Arabic alphabet from right to left.Arabic handwritten Character Recognition(HCR)is a crucial process in optical character recognition.In this view,this paper presents effective Computational linguistics with Deep Learning based Handwriting Recognition and Speech Synthesizer(CLDL-THRSS)for Indigenous Language.The presented CLDL-THRSS model involves two stages of operations namely automated handwriting recognition and speech recognition.Firstly,the automated handwriting recognition procedure involves preprocessing,segmentation,feature extraction,and classification.Also,the Capsule Network(CapsNet)based feature extractor is employed for the recognition of handwritten Arabic characters.For optimal hyperparameter tuning,the cuckoo search(CS)optimization technique was included to tune the parameters of the CapsNet method.Besides,deep neural network with hidden Markov model(DNN-HMM)model is employed for the automatic speech synthesizer.To validate the effective performance of the proposed CLDL-THRSS model,a detailed experimental validation process takes place and investigates the outcomes interms of different measures.The experimental outcomes denoted that the CLDL-THRSS technique has demonstrated the compared methods.

Perceptual Visuo-Motor Skills and Handwriting Production of Children With Learning Disabilities

This study aimed to explore the performance of the perceptual-visuomotor skills and the production of handwriting in children with Learning Disabilities.A total of 56 children participated,being a convenience sample,of both sexes,average age of eight years old,from 3rd to 5th grade level of Elementary School.The children were divided into the following groups:GI(28 children diagnosed with Learning Disabilities);GII(28 children with good academic performance,paired with GI in relation to chronological age and sex).They were evaluated individually in dysgraphic scale,visual perception development test,and fine motor evaluation.Data analysis was performed.There was a significant difference between GI and GII for the subtests of eye-hand coordination,copying,visual closure,fine motor precision,and fine manual control tests.They had difference between the groups for handwriting performance in descending and/or ascending subtests,irregularity of dimension,poor forms,and total score of Dysgraphia Scale.The results presented in this study indicate that children with Learning Disabilities can manifest significant visomotor impairment and deficit in legibility and handwriting quality,causing failures in the elaboration of sensorimotor plans that,added to the intrinsic deficit of long-term memory,result in persistent academic difficulties.

Neural and Kinematic Metrics of Handwriting in Neurotypical Adults

Detailed Assessment of Speed of Handwriting (DASH 17+) assessment provides information about the speed and legibility of handwriting. Handwriting difficulties in general and DASH17+ performance, in particular, are signs of neuromotor difficulties. Individualized interventions can be developed with a better understanding of both the biomechanical and neurological underpinnings of the task. We used a multimodal assessment strategy to deconstruct the product and process of handwriting measures in adults. A total of 23 neurotypical college age adults took part in the study. We combined the standardized norm-referenced test DASH17+ and explored the online process of handwriting using the MovAlyzeR software, and simultaneously explored prefrontal cortex activity, using functional near infrared spectroscopy (fNIRS), during the task execution. Our research indicated that underlying neural and kinematic mechanisms changed between tasks, within tasks, and even from one trial block to another that are not reflected in the DASH17+ performance assessment alone. Therefore, this multi-modal approach provides a promising method in clinical populations to further investigate any subtle change in handwriting.

The Effect of a Visual Memory Training Program on Chinese Handwriting Performance of Primary School Students with Dyslexia in Hong Kong

This study investigated the effect of a visual memory training program on Chinese handwriting performance among primary school students with dyslexia in Hong Kong. Eight students of Grade 2 to 3 who were diagnosed with dyslexia were recruited. All participants received six sessions of training, which composed of 30-minute computerized game-based visual memory training and 30-minute Chinese character segmentation training. Visual perceptual skills and Chinese handwriting performance were assessed before and after the training, as well as three weeks after training using the Test of Visual Perceptual Skills (3rd edition) (TVPS-3) and the Chinese Handwriting Analysis System (CHAS). In comparing the pre- and post-training results, paired t-tests revealed significant improvements in visual memory skills, as well as handwriting speed, pause time and pen pressure after the training. There was no significant improvement in handwriting accuracy or legibility. The improved visual memory and handwriting performance did not show a significant drop at the follow-up assessments. This study showed promising results on a structured program to improve the Chinese handwriting performance, mainly in speed, of primary school children. The improvements appeared to be well-sustained after the training program. There is a need to further study the long-term effect of the program through a randomized controlled trial study.

Research of handwriting detecting system for space pen

A handwriting detecting system based on Micro- accelerometer and Micro-gyros is proposed. And the algorithm of the detecting system is also described in detail. And the error analysis of the detecting system is also described in de-tail. The motion contrail of the handwriting de-tecting in the 3-D space can be recognized through compute the matrix of attitude angles and the dynamic information of the handwriting detecting which is mapped on the 2-D plane. Then the information of contrail can be recurred on the writing plane by integral. There were good results in the actual experiment.

Extraction of Arabic Handwriting Fields by Forms Matching

Filling forms is one of the most useful and powerful ways to collect information from people in business, education and many other domains. Nowadays, almost everything is computerized. That creates a curtail need for extracting these handwritings from the forms in order to get them into the computer systems and databases. In this paper, we propose an original method that will extract handwritings from two types of forms;bank and administrative form. Our system will take as input any of the two forms already filled. And according to some statistical measures our system will identify the form. The second step is to subtract the filled form from a previously inserted empty form. In order to make the acting easier and faster a Fourier-Melin transform was used to re-orient the forms correctly. This method has been evaluated with 50 handwriting forms (from both types Bank and University) and the results were approximatively 90%.

Comparison of ANN and SVM to Identify Children Handwriting Difficulties

This paper compares two classification methods to determine pupils who have difficulties in writing. Classification experiments are made with neural network and support vector machine method separately. The samples are divided into two groups of writers, below average printers (test group) and above average printers (control group) are applied. The aim of this paper is to demonstrate that neural network and support vector machine can be successfully used in classifying pupils with or without handwriting difficulties. Our results showed that support vector machine classifier yield slightly better percentage than neural network classifier and it has a much stable result.

A Comparison of the Identifying Features of Imitated Handwriting and Elderly Handwriting

Imitated handwriting and elderly handwriting are two manifestation patterns of altered handwriting.Several similarities in features can be found in both,such as gentle movement and curved jitter.In practice,it is very easy to confuse the two patterns,leading to wrong decisions and difficulties in document examination.The key to solving these problems is to recognize the similarities and differences between imitated handwriting and elderly handwriting.This paper comprises four parts.The first part introduces the general features of elderly handwriting;the second part takes up the general characteristics of imitated handwriting;the third part analyzes the common features of imitated handwriting and elderly handwriting;the fourth part draws a conclusion about their key points of identification.Since the number of cases requiring identification of elderly handwriting and imitated handwriting is increasing every year,this paper has practical significance for document examiners and provides theoretical support to questioned document examination.

The classification of handwriting features of the Kazakh language written in Latin script

In 2017,the Republic of Kazakhstan began the phased transition of its alphabet from Cyrillic to Latin script.This transition has presented significant challenges to Kazakhstani document examiners,who have yet to develop appropriate methodologies for the analysis of handwriting samples written in the Kazakh language using Latin letters.This study aims to identify distinguishing macro and micro features of letters within Kazakh writing samples produced using the Latin alphabet and determine their frequencies of occurrence and discriminating power indices.Micro features were examined using the four most frequently appearing letters:“a”,“y”,“e”and“n”.A comparative analysis of tested Latin letters with those of a similar configuration in Cyrillic demonstrated differences in the number of distinguishing features,as well as in the frequency of occurrence and discriminating power indices of similar features.These results show that separate statistical bases should be used for Latin and Cyrillic letters when analysing handwriting samples based on the frequencies of occurrence of micro and macro writing features.

Handwriting Input System Based on Ultrasonic Transducers

A handwriting input system was developed using three collinear ultrasonic transducers. These collinear polyvinylidene fluoride （PVDF） transducers were specially designed for the handwriting input system to give a large writeable area with writing in any direction. Driver and detection circuits were developed for the handwriting system. This handwriting input system based on 2-dimensional position tracing has large writeable area （A4 paper）, low drive voltage （5 V）, and is independent of the handwriting pad or the pen.

Exploratory Analysis on Dictated Handwriting Samples

Dictated handwriting samples are widely used in practice due to their simplicity,convenience,and practicality.However,dictation is typically listed as one of the many collection methods in textbooks and monographs,and there is usually no separate section focusing on dictated handwriting samples.Therefore,further study of dictated handwriting samples will have important practical significance.Consideration of the definition,existing problems,collection techniques,and critical aspects of dictated handwriting samples willsupport investigators and document examiners in their professional abilities and contribute to the theoretical system of document examination.In this article,an exploratory analysis will be conducted and ideas about dictated handwriting samples will be shared,including the definition of dictated samples,their relationship to experimental samples,practical problems,feasible collection methods,and some critical points that require special attention.Dictation is widely used but problematic because of a lack of quantity and low levels of comparability.Those difficulties are mainly caused by a lack of theoreticalstudy and understanding of the requirements and collection techniques of dictated handwriting samples among first‑line investigators.Dictated samples should be collected based on subjective and objective conditions of formation with aims to improve comparability and five similarities.Further studies are needed to improve the theoretical system and practical use of dictated samples so that they can contribute to successfully reaching conclusions in investigations.

Handwriting Identification:Challenges and Solutions

As a historic technology,handwriting identification,especially that of Chinese characters,plays an important role in judicial trials both in domestic and abroad.However,in recent decades,handwriting identification has feced a challenging situation;the scientificity of handwriting identification has been questioned.This article analyzes the reasons for questioning handwriting identification,focusing on the aspects of standards,methods,quantitative analysis of handwriting identification,and qualification,training,and assessment of document examiners.Besides,corresponding solutions for the above aspects and some other characteristics,such as systematic identification,cross-examination of expert opinions,and rule of corroboration,are proposed.

Handwriting Expertise Reliability:A Review

Handwriting expertise,as a form of forensic evidence,was once considered by most courts under the Anglo-American law system to be infallible,but this position was significantly challenged by the Daubert case(1993)and further by the President’s Council of Advisors on Science and Technology report published in 2016.In China,handwriting expertise has often been accepted as forensic evidence.However,this does not mean that there is no need to review the reliability of handwriting expertise.In this study,we analyze the current situation in China regarding the reliability of handwriting identification using cases from China’s judicial judgment database.We intend to identify the reasons for rejection of handwriting expertise,analyze the outcomes of applications for re-examination,and examine the court’s evaluation of different forensic opinions in relation to a given case.We also propose ways to strengthen the reliability of handwriting identification in China.

Research on Subjective Bias Cognition Effect in Handwriting Identification

This article starts from the point of view that handwriting examination is dependent on empiricism and by analyzing the core steps ofhandwriting identification explains that it might be influenced by subjective bias.In practice,examiners cannot avoid biases in decision-making;instead,we must accept the existence of subjective bias in handwriting identification and then discuss its impact;for instance,feature selection in the process of comprehensive evaluation,which involves a comparison of the number and quality of similarities and differences between a questioned sample and the references.While we conclude that comprehensive evaluation is the most important step in the identification process,industries in China do not stipulate explicit and transparent criteria for it,making it hard to numerically quantify the characteristics ofhandwriting identification.In this article,forensic examiners5 opinions on handwriting identification were obtained through a survey.One finding was that most handwriting examiners believe that handwriting identification is subject to subjective bias.In addition,they believe that the subjective cognition of handwriting identification can somehow help actively produce the correct opinion;before the examination,most handwriting examiners think that they should understand the context and so on.Finally,through the questionnaire,which contained variations such as the same case with different background information,different cases with the same background information,and the same case with or without context,it was concluded that handwriting identification does have certain subjectivity.However,which kind of factors influence this subjectivity is not presently clear.Furthermore,it is difficult to control uncertainties when fbnnmg an opinion on identification.An alternative way is to perform scrutiny after the formulation ofhandwritmg opinions;for example,internal and external reviews such as appearing in court.

Hyperspectral Imaging Technology for Revealing the Original Handwritings Covered by the Same Inks

This manuscript presents a preliminary investigation on the applicability of hyperspectral imaging technology for nondestructive and rapid analysis to reveal covered original handwritings.The hyperspectral imager Nuance‑Macro was used to collect the reflected light signature of inks from the overlapping parts.The software Nuance1p46 was used to analyze the reflected light signature of inks which shows the covered original handwritings.Different types of black/blue ballpoint pen inks and black/blue gel pen inks were chosen for sample preparation.From the hyperspectral images examined,the covered original handwritings of application were revealed in 90.5%,69.1%,49.5%,and 78.6%of the cases.Further,the correlation between the revealing effect and spectral characteristics of the reflected light of inks at the overlapping parts was interpreted through theoretical analysis and experimental verification.The results indicated that when the spectral characteristics of the reflected light of inks at the overlapping parts were the same or very similar to that of the ink that was used to cover the original handwriting,the original handwriting could not be shown.On the contrary,when the spectral characteristics of the reflected light of inks at the overlapping parts were different to that of the ink that was used to cover the original handwriting,the original handwriting was revealed.

MNIST Handwritten Digit Classification Based on Convolutional Neural Network with Hyperparameter Optimization

Accurate handwriting recognition has been a challenging computer vision problem,because static feature analysis of the text pictures is often inade-quate to account for high variance in handwriting styles across people and poor image quality of the handwritten text.Recently,by introducing machine learning,especially convolutional neural networks(CNNs),the recognition accuracy of various handwriting patterns is steadily improved.In this paper,a deep CNN model is developed to further improve the recognition rate of the MNIST hand-written digit dataset with a fast-converging rate in training.The proposed model comes with a multi-layer deep arrange structure,including 3 convolution and acti-vation layers for feature extraction and 2 fully connected layers(i.e.,dense layers)for classification.The model’s hyperparameters,such as the batch sizes,kernel sizes,batch normalization,activation function,and learning rate are optimized to enhance the recognition performance.The average classification accuracy of the proposed methodology is found to reach 99.82%on the training dataset and 99.40%on the testing dataset,making it a nearly error-free system for MNIST recognition.

Chinese Guqin Music and Calligraphy for Treating Symptoms of Primary Insomnia

Purpose:To investigate the intervention effiects of using traditional Chinese Guqin music and Chinese Calligraphy handwriting(CCH)for patients with Primary Insomnia.Methods:A total of ninety patients were assigned to control group,Guqin group,and calligraphy group for 8 weeks.For 5 days a week,patients’heart rate variability(HRV)and frontal midline(FZ)electroencephalographic signals were recorded in a clinic during interventional period while either listening to Guqin music or writing calligraphy.Patients in the control group remained in rest condition.Results:For the Guqin group,the higher low-frequency-range HRV of coherence was found with marginal significance(P=0.055),and heart rate was significantly reduced(P<0.05)during Hie 4^th week in listening to Guqin music compared to the prerest period.For listening to Guqin music or calligraphy intervention,FZδ,FZθ,and FZα waves in the 8^th week compared to the 0^th week(Pre Intervention)showed a significantly enhanced effect(.P<0.05).Between the three groups,for heart rate and FZδ and FZθ waves,calligraphy group showed significantly increased heart rate than the Guqin group(P<0.001)and the control group(P=0.004);increased FZδ wave than die Guqin group(P<0.001)and the control group(P<0.001);and increased FZθ wave than the Guqin group(P=0.024)and the control group(P=0.008)respectively.Conclusion:Positive intervention effects on 11RV coherence of Guqin music;FZδ,FZθ,and FZα waves of Guqin music and calligraphy proved that Guqin music together with calligraphy training helping to promote physical and mental health,thereby it contributes to the clinical application of TCM Psychology for patients with insomnia syndrome.