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.

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.

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.

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.

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.

Treatment Effects of Acupuncture and Calligraphy Training on Cognitive Abilities in Senile Demented Patients

Purpose:This study compared the relative effectiveness of Chinese calligraphy handwriting(CCH)and acupuncture in the treatment of patients with senile dementia.Materials and Methods:A randomized controlled trial(RCT)with 17 mild-to-moderate dementia patients with an average age of 77.29 years were randomly assigned with 9 to the calligraphy handwriting group and 8 to the acupuncture treatment group for a month of consecutive treatment.The participants'cognitive abilities,as well as symptoms of senile dementia,were measured by the Chinese version of the Mini-mental State Examination(CMMSE)and the Chinese Medicine Quantitative Diagnostic Survey for Senile Dementia Symptoms,respectively,before and after the treatment.Results:The calligraphy group showed a significant increase in calculation and memory as well as a decline in the symptoms of senile dementia.Patients in the acupuncture group experienced a significant growth in total CMMSE scores and the subscales in orientation to time and place,behavioral operations,as well as reduced clinical symptoms.However,no significant changes were found in their memory and calculation abilities.Conclusion:Both CCH and acupuncture treatments were found significantly effective for,respectively,enhancing the patients'cognitive abilities and reducing their clinical symptoms.Further,calligraphy handwriting also improved the level of their attention and concentration,physical relaxation,and emotional stability.

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.

The Temporal Making of a Great Literary Corpus by a XX-Century Mystic: Statistics of Daily Words and Writing Time

Maria Valtorta (1897-1961, Italian mystic)—bedridden since 1934 because paralyzed—wrote in Italian 13,193 pages of 122 school notebooks concerning alleged mystical visions on Jesus’ life, during World War II and few following years. The contents—about 2.64 million words—are now scattered in different books. She could write from 2 to 6 hours without pausing, with steady speed, and twice in the same day. She never made corrections and was very proficient in Italian. We have studied her writing activity concerning her alleged mystical experience with the main scope of establishing the time sequence of daily writing. This is possible because she diligently annotated the date of almost every text. We have reconstructed the time series of daily words and have converted them into time series of writing time, by assuming a realistic speed of 20 words per minute, a reliable average value of fast handwriting speed, applicable to Maria Valtorta. She wrote for 1340 days, about 3.67 years of equivalent contiguous writing time, mostly concentrated in the years 1943 to 1948. This study is a first approach in evaluating the effort done, in terms of writing time, by a mystic turned out to be a very effective literary author, whose texts are interesting to read per se, beyond any judgement—not of concern here—on her alleged visions.

Human Machine Interface with Wearable Electronics Using Biodegradable Triboelectric Films for Calligraphy Practice and Correction

Letter handwriting,especially stroke correction,is of great importance for recording languages and expressing and exchanging ideas for individual behavior and the public.In this study,a biodegradable and conductive carboxymethyl chitosan-silk fibroin(CSF)film is prepared to design wearable triboelectric nanogenerator(denoted as CSF-TENG),which outputs of V_(oc)≈165 V,I_(sc)≈1.4μA,and Q_(sc)≈72 mW cm^(−2).Further,in vitro biodegradation of CSF film is performed through trypsin and lysozyme.The results show that trypsin and lysozyme have stable and favorable biodegradation properties,removing 63.1%of CSF film after degrading for 11 days.Further,the CSF-TENG-based human-machine interface(HMI)is designed to promptly track writing steps and access the accuracy of letters,resulting in a straightforward communication media of human and machine.The CSF-TENG-based HMI can automatically recognize and correct three representative letters(F,H,and K),which is benefited by HMI system for data processing and analysis.The CSF-TENG-based HMI can make decisions for the next stroke,highlighting the stroke in advance by replacing it with red,which can be a candidate for calligraphy practice and correction.Finally,various demonstrations are done in real-time to achieve virtual and real-world controls including writing,vehicle movements,and healthcare.

Recognition of Offline Handwritten Arabic Words Using a Few Structural Features

Handwriting recognition is one of the most significant problems in pattern recognition,many studies have been proposed to improve this recognition of handwritten text for different languages.Yet,Fewer studies have been done for the Arabic language and the processing of its texts remains a particularly distinctive problem due to the variability of writing styles and the nature of Arabic scripts compared to other scripts.The present paper suggests a feature extraction technique for offlineArabic handwriting recognition.A handwriting recognition system for Arabic words using a few important structural features and based on a Radial Basis Function(RBF)neural networks is proposed.The methods of feature extraction are central to achieve high recognition performance.The proposed methodology relies on a feature extraction technique based on many structural characteristics extracted from the word skeleton(subwords,diacritics,loops,ascenders,and descenders).In order to reach our purpose,we built our own word database and the proposed system has been successfully tested on a handwriting database of Algerian city names(wilayas).Finally,a simple classifier based on the radial basis function neural network is presented to recognize certain words to verify the reliability of the proposed feature extraction.The experiments on some images of the benchmark IFN/ENIT database show that the proposed system improves recognition and the results obtained are indicative of the efficiency of our technique.

Quantum Particle Swarm Optimization Based Convolutional Neural Network for Handwritten Script Recognition

Even though several advances have been made in recent years,handwritten script recognition is still a challenging task in the pattern recognition domain.This field has gained much interest lately due to its diverse application potentials.Nowadays,different methods are available for automatic script recognition.Among most of the reported script recognition techniques,deep neural networks have achieved impressive results and outperformed the classical machine learning algorithms.However,the process of designing such networks right from scratch intuitively appears to incur a significant amount of trial and error,which renders them unfeasible.This approach often requires manual intervention with domain expertise which consumes substantial time and computational resources.To alleviate this shortcoming,this paper proposes a new neural architecture search approach based on meta-heuristic quantum particle swarm optimization(QPSO),which is capable of automatically evolving the meaningful convolutional neural network(CNN)topologies.The computational experiments have been conducted on eight different datasets belonging to three popular Indic scripts,namely Bangla,Devanagari,and Dogri,consisting of handwritten characters and digits.Empirically,the results imply that the proposed QPSO-CNN algorithm outperforms the classical and state-of-the-art methods with faster prediction and higher accuracy.

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.

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.

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.

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.

Effects of Excision of a Mass Lesion of the Precentral Region of the Left Hemisphere on Disturbances of Graphomotor Output

In the present study, the effect of neurosurgery on graphomotor output of a right-handed female patient with a mass lesion of the precentral region of the left frontal lobe was reported. For examination of handwriting movements a digitizing tablet was used. Preoperatively, the patient showed longer movement times than healthy subjects and patients with lesions of the left frontal lobe without involvement of the precentral region. Furthermore, the analysis of kinematic data revealed a severe dysfluency of her handwriting. Postoperatively, a significant improvement of writing time and fluency of handwriting was observed. Since the integrity of handwriting plays an important role in everyday functioning, disturbances of handwriting movements should be objectified and reassessed in follow-up assessment using new techniques such as digitizing tablets.

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 Multi-Agent Approach to Arabic Handwritten Text Segmentation

The segmentation of individual words into characters is a vital process in handwritten character recognition systems. In this paper, a novel approach is proposed to segment handwritten Arabic text (words). We consider the “Naskh” font style. The segmentation algorithm employs seven agents in order to detect regions where segmentation is illegal. Feature points (end points) are extracted from the remaining regions of the word-image. Initially, the middle of every two successive end points is considered as a candidate segmentation point based on a set of rules. The experimental results are very promising as we achieved a success rate of 86%.