Efficient feature descriptor selection for improved Arabic handwritten words recognition

Arabic handwritten text recognition is a complex and challenging research domain. This study proposes an offline Arabic handwritten word recognition system based on transfer learning. The system exploits four pre-trained convolutional neural network (CNN) architectures, namely VGG16, ResNet50, AlexNet, and InceptionV3. In addition, a specialized image recognition model derived from the ImageNet dataset is incorporated. A combination strategy is designed to combine transfer learning with specific fine-tuning techniques, aiming to improve recognition accuracy. The study is conducted on the IFN/ENIT dataset, which includes images of Tunisian City and village names. The results show that the proposed system achieves a recognition accuracy of 94.73%, which is significantly higher than the accuracy rates achieved by previous approaches. These results suggest that the proposed system is a promising approach for Arabic handwritten text recognition.

In this work, we investigate the combination of PGM (Propabilistic Graphical Models) classifiers, either independent or coupled, for the recognition of Arabic handwritten words. The independent classifiers are vertical and horizontal HMMs (Hidden Markov Models) whose observable outputs are features extracted from the image columns and the image rows respectively. The coupled classifiers associate the vertical and horizontal observation streams into a single DBN (Dynamic Bayesian Network). A novel method to extract word baseline and a simple and easily extractable features to construct feature vectors for words in the vocabulary are proposed. Some of these features are statistical, based on pixel distributions and local pixel configurations. Others are structural, based on the presence of ascenders, descenders, loops and diacritic points. Experiments on handwritten Arabic words from IFN/ENIT strongly support the feasibility of the proposed approach. The recognition rates achieve 90.42% with vertical and horizontal HMM, 85.03% and 85.21% with respectively a first and a second DBN which outperform results of some works based on PGMs.

In this paper, an Arabic handwritten word recognition system for wide vocabulary using the analytical approach is presented. After the segmentation phase, the characters are recognized using assumption generation of letters. Thus, the proposed system generates assumptions of words by concatenation of letters assumption. Thereafter, a filtering of these words assumption is achieved thanks to a language dictionary. The system showed good performances when applied on a 500 word images dataset.

<span lang="EN-US">In the recent years, an increasing demand for securing visual resource-constrained devices become a challenging problem due to the characteristics of these devices. Visual resource-constrained devices are suffered from limited storage space and lower power for computation such as wireless sensors, internet protocol (IP) camera and smart cards. Consequently, to support and preserve the video privacy in video surveillance system, lightweight security methods are required instead of the existing traditional encryption methods. In this paper, a new light weight stream cipher method is presented and investigated for video encryption based on hybrid chaotic map and ChaCha20 algorithm. Two chaotic maps are employed for keys generation process in order to achieve permutation and encryption tasks, respectively. The frames sequences are encrypted-decrypted based on symmetric scheme with assist of ChaCha20 algorithm. The proposed lightweight stream cipher method has been tested on several video samples to confirm suitability and validation in term of encryption–decryption procedures. The performance evaluation metrics include visual test, histogram analysis, information entropy, correlation analysis and differential analysis. From the experimental results, the proposed lightweight encryption method exhibited a higher security with lower computation time compared with state-of-the-art encryption methods.</span>

Hidden Markov models (HMMs) are now widely used for off-line handwriting recognition in many languages and, in particular, in Arabic. As in speech recognition, they are usually built from shared, embedded HMMs at the symbol level, in which state-conditional probability density functions are modeled with Gaussian mixtures. In contrast to speech recognition, however, it is unclear which kinds of features should be used and, indeed, very different feature sets are in use today. Among them, we have recently proposed to simply use columns of raw, binary image pixels, which are directly fed into embedded Bernoulli (mixture) HMMs, that is, embedded HMMs in which the emission probabilities are modeled with Bernoulli mixtures. The idea is to bypass feature extraction and ensure that no discriminative information is filtered out during feature extraction, which in some sense is integrated into the recognition model. In this chapter, we review this idea along with some extensions that are currently providing state-of-the-art results on Arabic handwritten word recognition.

Hidden Markov Models (HMMs) are now widely used in off-line handwriting recognition and, in particular, in Arabic handwritten word recognition. In contrast to the conventional approach, based on Gaussian mixture HMMs, we have recently proposed to directly fed columns of raw, binary pixels into Bernoulli mixture HMMs. In this work, column bit vectors are extended by means of a sliding window of adequate width to better capture image context at each horizontal position of the word image. Using these windowed Bernoulli mixture HMMs, very good results are reported on the well-known IfN/ENIT database of Arabic handwritten Tunisian town names.

This paper presents an overview of feature extraction techniques for unconstrained Arabic handwritten word recognition. Choosing a technique for extraction the features considers the most important factor in achieving high recognition rates in word or character recognition. Different techniques were designed to extract the features from the Arabic words. These techniques are presented and discussed in terms of invariant invariance properties.

Machine Learning (ML) has been a critical computational paradigm that has shaped contemporary applications in such domains as finance, healthcare, and cybersecurity, such that its performance evaluation cannot be less critical. However, its selection and interpretation of metrics has remained inconsistent, often leading to misleading conclusions. This study presents a systematic analysis of the most commonly used performance evaluation metrics in ML, integrating conceptual taxonomy, mathematical definitions, and empirical assessment under controlled perturbations. There are three dimensions to ML performance evaluation metrics categorization: robustness, discrimination, and calibration. Experiment conducted on classification and regression, and using synthetic datasets and benchmarks, evaluate threshold variation, class imbalance and label noise. Results obtained showed that no single metric captures model performance comprehensively and widely used metrics may yield conflicting or misleading assessments under certain conditions. Also, context-aware selection and multi-dimensional reporting were necessary for reliable evaluation. By empirically linking metric behaviour to data characteristics, this study provides guidance for context-aware metric selection and reporting that is not only standardized but also evidence-based.

Performance evaluation metrics for ring-oscillator-based temperature sensors on FPGAs: A quality factor

Due to the nature of handwriting with high degree of variability and imprecision, obtaining features that represent words is a difficult task. In this research, a features extraction method for handwritten Arabic word recognition is investigated. Its major goal is to maximize the recognition rate with the least amount of elements. This method incorporates many characteristics of handwritten characters based on structural information (loops, stems, legs, diacritics). Experiments are performed on Arabic personal names extracted from registers of the national Tunisian archive and on some Tunisian city names of IFN-ENIT database. The obtained results presented are encouraging and open other perspectives in the domain of the features and classifiers selection of Arabic Handwritten word recognition.

Early detection of sexually transmitted infections from skin lesions with deep learning: a systematic review and meta-analysis.

With increasing popularity of wireless local area network (WLAN) and emerging real-time applications, seamless mobility has become one of the primary concerns. Hence, the choice of a proper handover algorithm is of utmost importance. Various performance evaluation metrics for handover algorithms have been proposed in this regard. We argue that in a multiple access point (AP) scenario, the load on each of the APs, the requested data rate of the mobile terminal, and the soft handover have significant impact on these metrics. In this paper, we present an analytical framework to measure various handover performance evaluation metrics under both load condition and soft handover for a specific data rate request. Our approach is based on finding the circular region centered around an AP within which the requested data rate can be satisfied. We have considered WLAN usage efficiency, handover failure probability, and unnecessary handover probability as evaluation metrics. We have analyzed the impact of load and soft handover on these metrics. The impact of velocity on these metrics has also been analyzed. We also have derived lower bounds on both handover failure probability and unnecessary handover probability by formulating the problem into three circle intersection problem. The circular coverage assumption used in the framework is also validated through simulation.

Researchers are interested in genomic level cancer classification because it offers a thorough, precise, and reliable diagnosis for various cancer types. The gene expression data set is made up of hundreds of samples, each containing thousands of genes. As a result, accurately and effectively classifying such samples is difficult. To analyze gene expression patterns efficiently, recent studies have used artificial intelligence, data mining, and statistical techniques. Furthermore, machine learning methods have been extensively used to construct robust and accurate classification frameworks. In this paper, we examined the effectiveness of machine learning-based classification techniques such as Support Vector Machine, Logistic Regression, Naïve Bayes, Decision Tree, K-Nearest Neighbors, and Random Forest methods. In a total of 72 patients, 7129 distinct gene expressions and their degrees were evaluated to determine their relevance. Features have been normalized and PCA was used to decrease the dataset's dimensionality and complexity. The dataset was divided into training and test sets, with 90% of the occurrences in the training set and 10% in the test set. And finally, SMOTE was employed to oversample the minority class. In this study, gene expression data was utilized to differentiate Acute Myeloid Leukemia (AML) from Acute Lymphoblastic Leukemia (ALL). To evaluate the performance of the six machine learning models we used, we examined their associated confusion matrices and calculated nine performance evaluation metrics for each model's prediction on the test dataset. Results demonstrate that SVM, Logistic Regression, and Naïve Bayes outperformed the other ML techniques with an accuracy of 100%.

Potholes are primary cause for road accidents; hence it is important to identify and classify the potholes using efficient Computer vision-based techniques. Potholes not only cause problems to car drivers but even pedestrians face problem while walking on a road having potholes. It is also a major problem for blind people who must be extremely careful while walking. This paper presents a machine learning and computer vision-based approach to identify potholes from an image and alert visually impaired person about the same. Dataset is compiled from various available open-source datasets along with few images clicked from smartphone. Five different classification algorithms are used for classification of the images after applying image pre-processing and feature vector extraction. The algorithm implemented in this paper uses machine learning based approach which is computationally efficient. It provides an accuracy at par with computationally expensive deep learning algorithms. The method involves feature extraction, dimensionality reduction and finally classification algorithms are applied. Binary classification algorithms are used to classify the images. Performance evaluation metrics like Precision, Recall, F1-Score and Accuracy are used to evaluate the model’s performance. Random forest model showed the best performance among all the algorithms with an accuracy of 88% on test dataset.

Word recognition has changed in the past years. Implementations have become better, which allows larger vocabularies to be recognized; many of the implementations now available are suited well to specific tasks, but several have to be combined to obtain maximum benefit; and they are still hampered by deficiencies, for example when trying to decide among similar words. The new view of the output interface from word recognition presented here aims at various goals: easier combination of comparable word classification systems, better post-processing of word recognition results at higher levels (where more context is available), and improvement of out-of-vocabulary behavior. The proposed solution is to provide two different result scores instead of one single value: an overall quality measure, indicating the credibility of recognition, and a similarity measure for each word alternative. This shifts the responsibility for decisions from low-level word recognition tasks to higher levels, while retaining all necessary, recognition information. This, however, gives rise to the need to define new performance metrics for evaluation. Implementations of the proposed output interface for two recognition engines are sketched.