Handwriting is one of the most common types of questioned writing encountered and frequently attracts the attention in litigation. Contrary to the physiological characteristics, handwriting is a behavioral characteristic thus no two individuals with mature handwriting are exactly alike or an individual cannot produce the others writing exactly. Writing behavior and individualities are examined for similarities for both specimen and questioned document, thus, it is very efficient and effective strategy for biometrics. In this paper, we present a comprehensive review of writer identification methods and intend to provide taxonomy of dataset, feature extraction methods, as well as classification (conventional and deep learning based) for writer identification. For ease of reader, we grouped the discussion into English, Arabic, Western and Other languages from script prospective, whereas, from algorithm and methods perspective, we grouped the discussion with respect to implementation steps sequence. In the end, we highlighted the challenges and open research issues in the field of writer identification. Finally, we also suggest future direction.

Writer identification using machine learning approaches: a comprehensive review

Despite myriad attempts over the years to design curricula with logical ordering and connections, concerns persist that students view science as a body of prescribed information to memorize. In this essay, we argue that attempts to build coherence into the curriculum reflect fundamental and enduring misconceptions about the nature of coherence itself. Using examples of prominent curriculum projects over the past decade, we argue that premeditated coherence, the kind of coherence that is planned and designed for students, may inhibit students’ learning to seek coherence for themselves. We conclude with an approach to curriculum and assessment that emphasizes students’ epistemic agency in seeking coherence.

/pdf/looking-for-coherence-in-science-curriculum-41gagaefwg.pdf

Looking for coherence in science curriculum

Identification of a person from his writing is one of the challenging problems; however, it is not new. No one can repudiate its applications in a number of domains, such as forensic analysis, historical documents, and ancient manuscripts. Deep learning-based approaches have proved as the best feature extractors from massive amounts of heterogeneous data and provide promising and surprising predictions of patterns as compared with traditional approaches. We apply a deep transfer convolutional neural network (CNN) to identify a writer using handwriting text line images in English and Arabic languages. We evaluate different freeze layers of CNN (Conv3, Conv4, Conv5, Fc6, Fc7, and fusion of Fc6 and Fc7) affecting the identification rate of the writer. In this paper, transfer learning is applied as a pioneer study using ImageNet (base data-set) and QUWI data-set (target data-set). To decrease the chance of over-fitting, data augmentation techniques are applied like contours, negatives, and sharpness using text-line images of target data-set. The sliding window approach is used to make patches as an input unit to the CNN model. The AlexNet architecture is employed to extract discriminating visual features from multiple representations of image patches generated by enhanced pre-processing techniques. The extracted features from patches are then fed to a support vector machine classifier. We realized the highest accuracy using freeze Conv5 layer up to 92.78% on English, 92.20% on Arabic, and 88.11% on the combination of Arabic and English, respectively.

/pdf/automatic-visual-features-for-writer-identification-a-deep-3qe1e1e1re.pdf

Automatic Visual Features for Writer Identification: A Deep Learning Approach

Thyroid nodule is one of the endocrine problem caused due to abnormal growth of cells. This survival rate can be enhanced by earlier detection of nodules. Thus, the accurate detection of nodule is of utmost importance in providing effective diagnosis to increase the survival rate. However, accuracy of nodule detection from ultrasound images is suffered due to speckle noise. It considerably deteriorates the image quality and makes the differentiation of fine details quite difficult. Most of the detection systems for the thyroid nodules are semi-automated entailing manual intervention to draw rough outline of the nodule at some level or require manual segmentation in training or testing phases that increase the inaccuracies and evaluation time. To handle this, a fully Computer-Aided Detection system is presented for speckle reduction and segmentation of nodules from thyroid ultrasound images. The proposed system has three components: speckle reduction to reduce speckle noise and preserve the diagnostic features of ultrasound image, automatic generation of Region of interest (ROI) that identifies suspicious regions and fully automatic segmentation of nodule in processed ROI image. The proposed segmentation method outperformed other methods by gaining high True Positive (TP) value (95.92 ± 3.70%), False Positive (FP) value (7.04 ± 4.21%), Dice Coefficient (DC) value (93.88 ± 2.59%), Overlap Metric (OM) (91.18 ± 7.04 pixels) and Hausdroff Distance (HD) (0.52 ± 0.20 pixels). This system can facilitate the endocrinologists by providing second opinion to improve diagnosis of nodules as benign or malignant.

Computer Aided Thyroid Nodule Detection System Using Medical Ultrasound Images

Sustainable site selection for electric vehicle charging station (EVCS) is a significant process in the promotion of electric vehicle system development. The assessment and selection of suitable EVCS site is a very critical decision, involving complexity due to the presence of several associated criteria. Furthermore, uncertainty is an inevitable component of the information in the decision‐making procedure and its significance in the selection process is relatively high and needs to be cautiously measured. Single‐valued neutrosophic set (SVNS) is one of the valuable and flexible tools for handling such type of uncertain information arising in multi‐criteria decision‐making (MCDM) applications. Thus, the objective of this study is to introduce novel single‐valued neutrosophic information‐based additive ratio assessment (ARAS) approach for evaluating and prioritizing the sustainable EVCS sites. In this method, novel single‐valued subjective and objective weighted integrated approach (SVN‐SOWIA) is developed to compute the criteria by aggregating the objective weights resulted from a similarity measure‐based procedure and the subjective weights given by the experts. For this purpose, an innovative similarity measure is proposed for SVNSs. To display the performance of the present methodology, a computational study of EVCS sites evaluation is conferred under single‐valued neutrosophic environment. Comparative and sensitivity analyses are further performed to verify the strength of the developed approach. The outcome illustrates EVCS site EvUrjaa—Electric Vehicle Charging Station is the most optimal EVCS site in Indore region, India. Also, the environmental (0.324) and social (0.273) criteria are more important than technological (0.236) and economical (0.167) criteria in assessing the EVCS sites. The sensitivity analysis outcomes signify the EVCS option EvUrjaa—Electric Vehicle Charging Station always acquires its highest ranking in spite of how sub‐criteria weights fluctuate. The outcome of this study indicates that the developed approach can suggest more realistic performance under uncertain environment and therefore, provides a wide range of applications.

Single-valued neutrosophic similarity measure-based additive ratio assessment framework for optimal site selection of electric vehicle charging station

Discrete wavelet transform (DWT) is often implemented by an iterative filter bank; hence, a lake of optimization of a discrete time basis is observed with respect to time localization for a constant number of zero moments. This paper discusses and presents an improved form of DWT for feature extraction, called Slantlet transform (SLT) along with neutrosophy, a generalization of fuzzy logic, which is a relatively new logic. Thus, a novel composite NS-SLT model has been suggested as a source to derive statistical texture features that used to identify the malignancy of brain tumor. The MR images in the neutrosophic domain are defined using three membership sets, true ( ), false ( ), and indeterminate ( ); then, SLT was applied to each membership set. Three statistical measurement-based methods are used to extract texture features from images of brain MRI. One-way ANOVA has been applied as a method of reducing the number of extracted features for the classifiers; then, the extracted features are subsequently provided to the four neural network classification techniques, Support Vector Machine Neural Network (SVM-NN), Decision Tree Neural Network (DT-NN), - Nearest Neighbor Neural Network (KNN-NN), and Naive Bayes Neural Networks (NB-NN), to predict the type of the brain tumor. Meanwhile, the performance of the proposed model is assessed by calculating average accuracy, precision, sensitivity, specificity, and Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC) curve. The experimental results demonstrate that the proposed approach is quite accurate and efficient for diagnosing brain tumors when the Gray Level Run Length Matrix (GLRLM) features derived from the composite NS-SLT technique is used.

/pdf/a-novel-intelligent-system-for-brain-tumor-diagnosis-based-3tlait3hpc.pdf

A Novel Intelligent System for Brain Tumor Diagnosis Based on a Composite Neutrosophic-Slantlet Transform Domain for Statistical Texture Feature Extraction.

Recognizing the writer of a text that has been handwritten is a very intriguing research problem in the field of document analysis and recognition. This study tables an automatic way of recognizing the writer from handwritten samples. Even though much has been done in previous researches that have presented other various methods, it is still clear that the field has a room for improvement. This particular method uses Optimum Features based writer characterization. Here, each of the samples written is grouped according to their set of features that are acquired from a computed codebook. This proposed codebook is different from the others which segment the samples into graphemes by fragmenting a certain part of the writing known as ending strokes. The proposed technique is employed to a locate and extract the handwriting fragments from ending zone and then grouped the similar fragments to generate a new cluster known as ending cluster. The cluster that comes in handy in the process of coming up with the ending codebook through picking out the center of the same fragment group. The process is finalized by evaluating the proposed method on four datasets of the various languages. This method being proposed had an impressive 97.12% identification rate which is rates the best result on the ICFHR dataset.

/pdf/writer-identification-on-multi-script-handwritten-using-mgobeg89pg.pdf

Writer Identification on Multi-Script Handwritten Using Optimum Features

This study is focused on as Cuckoo Search (CS), one of the current meta-heuristic optimization algorithm. The CS algorithm is useful in generating and searching for the most optimum particles of important meta-heuristic optimization algorithm, known as the Particle Swarm Optimization (PSO), to enhance its performance. This optimization is confirmed through a benchmark online optimization and actual problems. The PSO algorithm performance is also compared with differing algorithms representative of the area. The CS optimal solutions outperform alternative current solutions as CS has distinct search features. The study findings have implications for future studies and practice.

Using the Cuckoo Search for Generating New Particles in Particle Swarm Optimization Algorithm

This paper proposes a copyright protection system for digital certificate image using blind watermarking technique by applying discrete wavelet transform algorithm (DWT) The proposed technique utilizes three interrelated watermarks namely, Red watermark (RW), Green-watermark (GW) and Blue-watermark (BW) Firstly, RGB cover and RGB watermark image are divided for three color space R,G,B Then the R component is chosen for embedding (RW), the B component is selected for embedding the (BW) and the G component is selected for embedding the (GW), R,G and B of the cover image are converted into the transform domain using DWT, and is subsequently decomposed into three levels viz  LH1, LL2 and LL3 sub-bands RW, GW and BW are then embedded onto LL3 Experimental results show that the performance of the proposed technique is very encouraging with average PSNR of 44 db, and NCC value of more than 099 for extracted watermarks after performing several types of attacks

/pdf/copyright-protection-for-digital-certificate-using-blind-50wic2e0d0.pdf

Harith Raad Hasan

Papers

A Novel Intelligent System for Brain Tumor Diagnosis Based on a Composite Neutrosophic-Slantlet Transform Domain for Statistical Texture Feature Extraction.

Writer Identification on Multi-Script Handwritten Using Optimum Features

Using the Cuckoo Search for Generating New Particles in Particle Swarm Optimization Algorithm

Copyright Protection for Digital Certificate using Blind Watermarking Technique