KurdSet: A Kurdish Handwritten Characters Recognition Dataset Using Convolutional Neural Network

Handwritten character recognition(HCR)involves identifying characters in images,documents,and various sources such as forms surveys,questionnaires,and signatures,and transforming them into a machine-readable format for subsequent processing.Successfully recognizing complex and intricately shaped handwritten characters remains a significant obstacle.The use of convolutional neural network(CNN)in recent developments has notably advanced HCR,leveraging the ability to extract discriminative features from extensive sets of raw data.Because of the absence of pre-existing datasets in the Kurdish language,we created a Kurdish handwritten dataset called(KurdSet).The dataset consists of Kurdish characters,digits,texts,and symbols.The dataset consists of 1560 participants and contains 45,240 characters.In this study,we chose characters only from our dataset.We utilized a Kurdish dataset for handwritten character recognition.The study also utilizes various models,including InceptionV3,Xception,DenseNet121,and a customCNNmodel.To show the performance of the KurdSet dataset,we compared it to Arabic handwritten character recognition dataset(AHCD).We applied the models to both datasets to show the performance of our dataset.Additionally,the performance of the models is evaluated using test accuracy,which measures the percentage of correctly classified characters in the evaluation phase.All models performed well in the training phase,DenseNet121 exhibited the highest accuracy among the models,achieving a high accuracy of 99.80%on the Kurdish dataset.And Xception model achieved 98.66%using the Arabic dataset.

Development of a Lightweight Model for Handwritten Dataset Recognition: Bangladeshi City Names in Bangla Script

The context of recognizing handwritten city names,this research addresses the challenges posed by the manual inscription of Bangladeshi city names in the Bangla script.In today’s technology-driven era,where precise tools for reading handwritten text are essential,this study focuses on leveraging deep learning to understand the intricacies of Bangla handwriting.The existing dearth of dedicated datasets has impeded the progress of Bangla handwritten city name recognition systems,particularly in critical areas such as postal automation and document processing.Notably,no prior research has specifically targeted the unique needs of Bangla handwritten city name recognition.To bridge this gap,the study collects real-world images from diverse sources to construct a comprehensive dataset for Bangla Hand Written City name recognition.The emphasis on practical data for system training enhances accuracy.The research further conducts a comparative analysis,pitting state-of-the-art(SOTA)deep learning models,including EfficientNetB0,VGG16,ResNet50,DenseNet201,InceptionV3,and Xception,against a custom Convolutional Neural Networks(CNN)model named“Our CNN.”The results showcase the superior performance of“Our CNN,”with a test accuracy of 99.97% and an outstanding F1 score of 99.95%.These metrics underscore its potential for automating city name recognition,particularly in postal services.The study concludes by highlighting the significance of meticulous dataset curation and the promising outlook for custom CNN architectures.It encourages future research avenues,including dataset expansion,algorithm refinement,exploration of recurrent neural networks and attention mechanisms,real-world deployment of models,and extension to other regional languages and scripts.These recommendations offer exciting possibilities for advancing the field of handwritten recognition technology and hold practical implications for enhancing global postal services.

Hybrid Optimization Algorithm for Handwritten Document Enhancement

The Gannet Optimization Algorithm (GOA) and the Whale Optimization Algorithm (WOA) demonstrate strong performance;however, there remains room for improvement in convergence and practical applications. This study introduces a hybrid optimization algorithm, named the adaptive inertia weight whale optimization algorithm and gannet optimization algorithm (AIWGOA), which addresses challenges in enhancing handwritten documents. The hybrid strategy integrates the strengths of both algorithms, significantly enhancing their capabilities, whereas the adaptive parameter strategy mitigates the need for manual parameter setting. By amalgamating the hybrid strategy and parameter-adaptive approach, the Gannet Optimization Algorithm was refined to yield the AIWGOA. Through a performance analysis of the CEC2013 benchmark, the AIWGOA demonstrates notable advantages across various metrics. Subsequently, an evaluation index was employed to assess the enhanced handwritten documents and images, affirming the superior practical application of the AIWGOA compared with other algorithms.

Optimised CNN Architectures for Handwritten Arabic Character Recognition

Handwritten character recognition is considered challenging compared with machine-printed characters due to the different human writing styles.Arabic is morphologically rich,and its characters have a high similarity.The Arabic language includes 28 characters.Each character has up to four shapes according to its location in the word(at the beginning,middle,end,and isolated).This paper proposed 12 CNN architectures for recognizing handwritten Arabic characters.The proposed architectures were derived from the popular CNN architectures,such as VGG,ResNet,and Inception,to make them applicable to recognizing character-size images.The experimental results on three well-known datasets showed that the proposed architectures significantly enhanced the recognition rate compared to the baseline models.The experiments showed that data augmentation improved the models’accuracies on all tested datasets.The proposed model outperformed most of the existing approaches.The best achieved results were 93.05%,98.30%,and 96.88%on the HIJJA,AHCD,and AIA9K datasets.

Method to Remove Handwritten Texts Using Smart Phone

To remove handwritten texts from an image of a document taken by smart phone,an intelligent removal method was proposed that combines dewarping and Fully Convolutional Network with Atrous Convolutional and Atrous Spatial Pyramid Pooling(FCN-AC-ASPP).For a picture taken by a smart phone,firstly,the image is transformed into a regular image by the dewarping algorithm.Secondly,the FCN-AC-ASPP is used to classify printed texts and handwritten texts.Lastly,handwritten texts can be removed by a simple algorithm.Experiments show that the classification accuracy of the FCN-AC-ASPP is better than FCN,DeeplabV3+,FCN-AC.For handwritten texts removal effect,the method of combining dewarping and FCN-AC-ASPP is superior to FCN-AC-ASP alone.

An Auto-Grading Oriented Approach for Off-Line Handwritten Organic Cyclic Compound Structure Formulas Recognition

Auto-grading,as an instruction tool,could reduce teachers’workload,provide students with instant feedback and support highly personalized learning.Therefore,this topic attracts considerable attentions from researchers recently.To realize the automatic grading of handwritten chemistry assignments,the problem of chemical notations recognition should be solved first.The recent handwritten chemical notations recognition solutions belonging to the end-to-end trainable category suffered fromthe problem of lacking the accurate alignment information between the input and output.They serve the aim of reading notations into electrical devices to better prepare relevant edocuments instead of auto-grading handwritten assignments.To tackle this limitation to enable the auto-grading of handwritten chemistry assignments at a fine-grained level.In this work,we propose a component-detectionbased approach for recognizing off-line handwritten Organic Cyclic Compound Structure Formulas(OCCSFs).Specifically,we define different components of OCCSFs as objects(including graphical objects and text objects),and adopt the deep learning detector to detect them.Then,regarding the detected text objects,we introduce an improved attention-based encoder-decoder model for text recognition.Finally,with these detection results and the geometric relationships of detected objects,this article designs a holistic algorithm for interpreting the spatial structure of handwritten OCCSFs.The proposedmethod is evaluated on a self-collected data set consisting of 3000 samples and achieves promising results.

Semantic Document Layout Analysis of Handwritten Manuscripts

A document layout can be more informative than merely a document’s visual and structural appearance.Thus,document layout analysis(DLA)is considered a necessary prerequisite for advanced processing and detailed document image analysis to be further used in several applications and different objectives.This research extends the traditional approaches of DLA and introduces the concept of semantic document layout analysis(SDLA)by proposing a novel framework for semantic layout analysis and characterization of handwritten manuscripts.The proposed SDLA approach enables the derivation of implicit information and semantic characteristics,which can be effectively utilized in dozens of practical applications for various purposes,in a way bridging the semantic gap and providingmore understandable high-level document image analysis and more invariant characterization via absolute and relative labeling.This approach is validated and evaluated on a large dataset ofArabic handwrittenmanuscripts comprising complex layouts.The experimental work shows promising results in terms of accurate and effective semantic characteristic-based clustering and retrieval of handwritten manuscripts.It also indicates the expected efficacy of using the capabilities of the proposed approach in automating and facilitating many functional,reallife tasks such as effort estimation and pricing of transcription or typing of such complex manuscripts.

A Novel Siamese Network for Few/Zero-Shot Handwritten Character Recognition Tasks

Deep metric learning is one of the recommended methods for the challenge of supporting few/zero-shot learning by deep networks.It depends on building a Siamese architecture of two homogeneous Convolutional Neural Networks(CNNs)for learning a distance function that can map input data from the input space to the feature space.Instead of determining the class of each sample,the Siamese architecture deals with the existence of a few training samples by deciding if the samples share the same class identity or not.The traditional structure for the Siamese architecture was built by forming two CNNs from scratch with randomly initialized weights and trained by binary cross-entropy loss.Building two CNNs from scratch is a trial and error and time-consuming phase.In addition,training with binary crossentropy loss sometimes leads to poor margins.In this paper,a novel Siamese network is proposed and applied to few/zero-shot Handwritten Character Recognition(HCR)tasks.The novelties of the proposed network are in.1)Utilizing transfer learning and using the pre-trained AlexNet as a feature extractor in the Siamese architecture.Fine-tuning a pre-trained network is typically faster and easier than building from scratch.2)Training the Siamese architecture with contrastive loss instead of the binary cross-entropy.Contrastive loss helps the network to learn a nonlinear mapping function that enables it to map the extracted features in the vector space with an optimal way.The proposed network is evaluated on the challenging Chars74K datasets by conducting two experiments.One is for testing the proposed network in few-shot learning while the other is for testing it in zero-shot learning.The recognition accuracy of the proposed network reaches to 85.6%and 82%in few-and zero-shot learning respectively.In addition,a comparison between the performance of the proposed Siamese network and the traditional Siamese CNNs is conducted.The comparison results show that the proposed network achieves higher recognition results in less time.The proposed network reduces the training time from days to hours in both experiments.

Recognition of Handwritten Words from Digital Writing Pad Using MMU-SNet

In this paper,Modified Multi-scale Segmentation Network(MMU-SNet)method is proposed for Tamil text recognition.Handwritten texts from digi-tal writing pad notes are used for text recognition.Handwritten words recognition for texts written from digital writing pad through text file conversion are challen-ging due to stylus pressure,writing on glass frictionless surfaces,and being less skilled in short writing,alphabet size,style,carved symbols,and orientation angle variations.Stylus pressure on the pad changes the words in the Tamil language alphabet because the Tamil alphabets have a smaller number of lines,angles,curves,and bends.The small change in dots,curves,and bends in the Tamil alphabet leads to error in recognition and changes the meaning of the words because of wrong alphabet conversion.However,handwritten English word recognition and conversion of text files from a digital writing pad are performed through various algorithms such as Support Vector Machine(SVM),Kohonen Neural Network(KNN),and Convolutional Neural Network(CNN)for offline and online alphabet recognition.The proposed algorithms are compared with above algorithms for Tamil word recognition.The proposed MMU-SNet method has achieved good accuracy in predicting text,about 96.8%compared to other traditional CNN algorithms.

Handwritten digit recognition based on ghost imaging with deep learning

We present a ghost handwritten digit recognition method for the unknown handwritten digits based on ghost imaging(GI)with deep neural network,where a few detection signals from the bucket detector,generated by the cosine transform speckle,are used as the characteristic information and the input of the designed deep neural network(DNN),and the output of the DNN is the classification.The results show that the proposed scheme has a higher recognition accuracy(as high as 98%for the simulations,and 91%for the experiments)with a smaller sampling ratio(say 12.76%).With the increase of the sampling ratio,the recognition accuracy is enhanced.Compared with the traditional recognition scheme using the same DNN structure,the proposed scheme has slightly better performance with a lower complexity and non-locality property.The proposed scheme provides a promising way for remote sensing.

Improving CNN-BGRU Hybrid Network for Arabic Handwritten Text Recognition

Handwriting recognition is a challenge that interests many researchers around the world.As an exception,handwritten Arabic script has many objectives that remain to be overcome,given its complex form,their number of forms which exceeds 100 and its cursive nature.Over the past few years,good results have been obtained,but with a high cost of memory and execution time.In this paper we propose to improve the capacity of bidirectional gated recurrent unit(BGRU)to recognize Arabic text.The advantages of using BGRUs is the execution time compared to other methods that can have a high success rate but expensive in terms of time andmemory.To test the recognition capacity of BGRU,the proposed architecture is composed by 6 convolutional neural network(CNN)blocks for feature extraction and 1 BGRU+2 dense layers for learning and test.The experiment is carried out on the entire database of institut für nachrichtentechnik/ecole nationale d’ingénieurs de Tunis(IFN/ENIT)without any preprocessing or data selection.The obtained results show the ability of BGRUs to recognize handwritten Arabic script.

Recognition of Urdu Handwritten Alphabet Using Convolutional Neural Network (CNN)

Handwritten character recognition systems are used in every field of life nowadays,including shopping malls,banks,educational institutes,etc.Urdu is the national language of Pakistan,and it is the fourth spoken language in the world.However,it is still challenging to recognize Urdu handwritten characters owing to their cursive nature.Our paper presents a Convolutional Neural Networks(CNN)model to recognize Urdu handwritten alphabet recognition(UHAR)offline and online characters.Our research contributes an Urdu handwritten dataset(aka UHDS)to empower future works in this field.For offline systems,optical readers are used for extracting the alphabets,while diagonal-based extraction methods are implemented in online systems.Moreover,our research tackled the issue concerning the lack of comprehensive and standard Urdu alphabet datasets to empower research activities in the area of Urdu text recognition.To this end,we collected 1000 handwritten samples for each alphabet and a total of 38000 samples from 12 to 25 age groups to train our CNN model using online and offline mediums.Subsequently,we carried out detailed experiments for character recognition,as detailed in the results.The proposed CNN model outperformed as compared to previously published approaches.

An Optimized Deep Residual Network with a Depth Concatenated Block for Handwritten Characters Classification

Even though much advancements have been achieved with regards to the recognition of handwritten characters,researchers still face difficulties with the handwritten character recognition problem,especially with the advent of new datasets like the Extended Modified National Institute of Standards and Technology dataset(EMNIST).The EMNIST dataset represents a challenge for both machine-learning and deep-learning techniques due to inter-class similarity and intra-class variability.Inter-class similarity exists because of the similarity between the shapes of certain characters in the dataset.The presence of intra-class variability is mainly due to different shapes written by different writers for the same character.In this research,we have optimized a deep residual network to achieve higher accuracy vs.the published state-of-the-art results.This approach is mainly based on the prebuilt deep residual network model ResNet18,whose architecture has been enhanced by using the optimal number of residual blocks and the optimal size of the receptive field of the first convolutional filter,the replacement of the first max-pooling filter by an average pooling filter,and the addition of a drop-out layer before the fully connected layer.A distinctive modification has been introduced by replacing the final addition layer with a depth concatenation layer,which resulted in a novel deep architecture having higher accuracy vs.the pure residual architecture.Moreover,the dataset images’sizes have been adjusted to optimize their visibility in the network.Finally,by tuning the training hyperparameters and using rotation and shear augmentations,the proposed model outperformed the state-of-the-art models by achieving average accuracies of 95.91%and 90.90%for the Letters and Balanced dataset sections,respectively.Furthermore,the average accuracies were improved to 95.9%and 91.06%for the Letters and Balanced sections,respectively,by using a group of 5 instances of the trained models and averaging the output class probabilities.

SVM Model Selection Using PSO for Learning Handwritten Arabic Characters

Using Support Vector Machine(SVM)requires the selection of several parameters such as multi-class strategy type(one-against-all or one-against-one),the regularization parameter C,kernel function and their parameters.The choice of these parameters has a great influence on the performance of the final classifier.This paper considers the grid search method and the particle swarm optimization(PSO)technique that have allowed to quickly select and scan a large space of SVM parameters.A comparative study of the SVM models is also presented to examine the convergence speed and the results of each model.SVM is applied to handwritten Arabic characters learning,with a database containing 4840 Arabic characters in their different positions(isolated,beginning,middle and end).Some very promising results have been achieved.

A 4-Corner Codes Classifier Based on Decision Tree Inductive Learning for Handwritten Chinese Characters

The classification for handwritten Chinese character recognition can be viewed as a transformation in discrete vector space. In this paper, from the point of discrete vector space transformation, a new 4-corner codes classifier based on decision tree inductive learning algorithm ID3 for handwritten Chinese characters is presented. With a feature extraction controller, the classifier can reduce the number of extracted features and accelerate classification speed. Experimental results show that the 4-corner codes classifier performs well on both recognition accuracy and speed.

Research on Handwritten Chinese Character Recognition Based on BP Neural Network

The application of pattern recognition technology enables us to solve various human-computer interaction problems that were difficult to solve before.Handwritten Chinese character recognition,as a hot research object in image pattern recognition,has many applications in people’s daily life,and more and more scholars are beginning to study off-line handwritten Chinese character recognition.This paper mainly studies the recognition of handwritten Chinese characters by BP(Back Propagation)neural network.Establish a handwritten Chinese character recognition model based on BP neural network,and then verify the accuracy and feasibility of the neural network through GUI(Graphical User Interface)model established by Matlab.This paper mainly includes the following aspects:Firstly,the preprocessing process of handwritten Chinese character recognition in this paper is analyzed.Among them,image preprocessing mainly includes six processes:graying,binarization,smoothing and denoising,character segmentation,histogram equalization and normalization.Secondly,through the comparative selection of feature extraction methods for handwritten Chinese characters,and through the comparative analysis of the results of three different feature extraction methods,the most suitable feature extraction method for this paper is found.Finally,it is the application of BP neural network in handwritten Chinese character recognition.The establishment,training process and parameter selection of BP neural network are described in detail.The simulation software platform chosen in this paper is Matlab,and the sample images are used to train BP neural network to verify the feasibility of Chinese character recognition.Design the GUI interface of human-computer interaction based on Matlab,show the process and results of handwritten Chinese character recognition,and analyze the experimental results.

A New Segmentation Framework for Arabic Handwritten Text Using Machine Learning Techniques

The writer identification(WI)of handwritten Arabic text is now of great concern to intelligence agencies following the recent attacks perpetrated by known Middle East terrorist organizations.It is also a useful instrument for the digitalization and attribution of old text to other authors of historic studies,including old national and religious archives.In this study,we proposed a new affective segmentation model by modifying an artificial neural network model and making it suitable for the binarization stage based on blocks.This modified method is combined with a new effective rotation model to achieve an accurate segmentation through the analysis of the histogram of binary images.Also,propose a new framework for correct text rotation that will help us to establish a segmentation method that can facilitate the extraction of text from its background.Image projections and the radon transform are used and improved using machine learning based on a co-occurrence matrix to produce binary images.The training stage involves taking a number of images for model training.These images are selected randomly with different angles to generate four classes(0–90,90–180,180–270,and 270–360).The proposed segmentation approach achieves a high accuracy of 98.18%.The study ultimately provides two major contributions that are ranked from top to bottom according to the degree of importance.The proposed method can be further developed as a new application and used in the recognition of handwritten Arabic text from small documents regardless of logical combinations and sentence construction.

MCS HOG Features and SVM Based Handwritten Digit Recognition System

Digit Recognition is an essential element of the process of scanning and converting documents into electronic format. In this work, a new Multiple-Cell Size (MCS) approach is being proposed for utilizing Histogram of Oriented Gradient (HOG) features and a Support Vector Machine (SVM) based classifier for efficient classification of Handwritten Digits. The HOG based technique is sensitive to the cell size selection used in the relevant feature extraction computations. Hence a new MCS approach has been used to perform HOG analysis and compute the HOG features. The system has been tested on the Benchmark MNIST Digit Database of handwritten digits and a classification accuracy of 99.36% has been achieved using an Independent Test set strategy. A Cross-Validation analysis of the classification system has also been performed using the 10-Fold Cross-Validation strategy and a 10-Fold classification accuracy of 99.26% has been obtained. The classification performance of the proposed system is superior to existing techniques using complex procedures since it has achieved at par or better results using simple operations in both the Feature Space and in the Classifier Space. The plots of the system’s Confusion Matrix and the Receiver Operating Characteristics (ROC) show evidence of the superior performance of the proposed new MCS HOG and SVM based digit classification system.

Handwritten Numeric and Alphabetic Character Recognition and Signature Verification Using Neural Network

Handwritten signature and character recognition has become challenging research topic due to its numerous applications. In this paper, we proposed a system that has three sub-systems. The three subsystems focus on offline recognition of handwritten English alphabetic characters (uppercase and lowercase), numeric characters (0 - 9) and individual signatures respectively. The system includes several stages like image preprocessing, the post-processing, the segmentation, the detection of the required amount of the character and signature, feature extraction and finally Neural Network recognition. At first, the scanned image is filtered after conversion of the scanned image into a gray image. Then image cropping method is applied to detect the signature. Then an accurate recognition is ensured by post-processing the cropped images. MATLAB has been used to design the system. The subsystems are then tested for several samples and the results are found satisfactory at about 97% success rate. The quality of the image plays a vital role as the images of poor or mediocre quality may lead to unsuccessful recognition and verification.

A Recognition-Based Approach to Segmenting Arabic Handwritten Text

Segmenting Arabic handwritings had been one of the subjects of research in the field of Arabic character recognition for more than 25 years. The majority of reported segmentation techniques share a critical shortcoming, which is over-segmentation. The aim of segmentation is to produce the letters (segments) of a handwritten word. When a resulting letter (segment) is made of more than one piece (stroke) instead of one, this is called over-segmentation. Our objective is to overcome this problem by using an Artificial Neural Networks (ANN) to verify the resulting segment. We propose a set of heuristic-based rules to assemble strokes in order to report the precise segmented letters. Preprocessing phases that include normalization and feature extraction are required as a prerequisite step for the ANN system for recognition and verification. In our previous work [1], we did achieve a segmentation success rate of 86% but without recognition. In this work, our experimental results confirmed a segmentation success rate of no less than 95%.