Currently, deep learning approaches have proven successful in the areas of handwriting recognition. Despite this, research in this field is still needed, especially in the context of multilingual online handwriting recognition scripts by adopting new network architectures and combining relevant parametric models. In this paper, we propose a multi-stage deep learning-based algorithm for multilingual online handwriting recognition based on hybrid deep Bidirectional Long Short Term Memory (DBLSTM) and SVM networks. The main contributions of our work lie in partly in the composition of a new multi-stage architecture of deep learning networks associated with effective feature vectors that integrate dynamic and visual characteristics. First, the proposed system proceeds by pretreating the acquired script and delimiting its Segments of Online Handwriting Trajectories (SOHTs). Second, two types of feature vectors combining BetaElliptic Model (BEM) and Convolutional Neural Network (CNN) are extracted for each SOHT in order to fuzzy classify them into k sub-groups using DBLSTM neural networks for both online and offline branches trained using an unsupervised fuzzy k-means algorithm. Finally, we combine the trained models to strengthen the discrimination power of the global system using SVM engine. Extensive experiments on three data sets were conducted to validate the performance of the proposed method. The experimental results show the effectiveness and complementarities of the individual modules and the advantage of their fusion.

Presentation of 3D Face Alignment method with application to Face Recognition

In this paper a new technique is integrated to Multi-Objective Particle Swarm Optimization (MOPSO) algorithm, named Pareto Neighborhood (PN) topology, to produce MOPSO-PN algorithm. This technique involves iteratively selecting a set of best solutions from the Pareto-Optimal-Fronts and trying to explore them in order to find better clustering results in the next iteration. MOPSO-PN was then used as a Multi?Objective Clustering Optimization (MOCO) Algorithm, it was tested on various datasets (real-life and artificial datasets). Two scenarios have been used to test the performances of MOPSO-PN for clustering: In the first scenario MOPSO-PN utilizes, as objective functions, two clusters validity index (Silhouette?Index and overall-cluster-deviation), three datasets for test, four algorithms for comparison and the average Minkowski Score as metric for evaluating the final clustering result; In the second scenario MOPSO-PN used, as objectives functions, three clusters validity index (I-index, Con-index and Sym?index), 20 datasets for test, ten algorithms for comparison and the F-Measure as metric for evaluating the final clustering result. In both scenarios, MOPSO-PN provided a competitive clustering results and a correct number of clusters for all datasets.

Our work aims to conduct a comprehensive literature review of deep learning methods applied in the fashion industry and, especially, the image-based virtual fitting task by citing research works published in the last years. We have summarized their challenges, their main frameworks, the popular benchmark datasets, and the different evaluation metrics. Also, some promising future research directions are discussed to propose improvements in this research field.

This work is part of an innovative e-learning project allowing the development of an advanced digital educational tool that provides feedback during the process of learning handwriting for young school children (three to eight years old). In this paper, we describe a new method for children handwriting quality analysis. It automatically detects mistakes, gives real-time on-line feedback for children’s writing, and helps teachers comprehend and evaluate children’s writing skills. The proposed method adjudges five main criteria: shape, direction, stroke order, position respect to the reference lines, and kinematics of the trace. It analyzes the handwriting quality and automatically gives feedback based on the combination of three extracted models: Beta-Elliptic Model (BEM) using similarity detection (SD) and dissimilarity distance (DD) measure, Fourier Descriptor Model (FDM), and perceptive Convolutional Neural Network (CNN) with Support Vector Machine (SVM) comparison engine. The originality of our work lies partly in the system architecture which apprehends complementary dynamic, geometric, and visual representation of the examined handwritten scripts and in the efficient selected features adapted to various handwriting styles and multiple script languages such as Arabic, Latin, digits, and symbol drawing. The application offers two interactive interfaces respectively dedicated to learners, educators, experts or teachers and allows them to adapt it easily to the specificity of their disciples. The evaluation of our framework is enhanced by a database collected in Tunisia primary school with 400 children. Experimental results show the efficiency and robustness of our suggested framework that helps teachers and children by offering positive feedback throughout the handwriting learning process using tactile digital devices.

Particle swarm optimization system based on the distributed architecture over multiple sub-swarms has shown its efficiency for static optimization and has not been studied to solve dynamic multi-objective problems (DMOPs). When solving DMOP, tracking the best solutions over time and ensuring good exploitation and exploration are the main challenging tasks. This study proposes a novel Dynamic Pareto bi-level Multi-Objective Particle Swarm Optimization (DPb-MOPSO) algorithm including two parallel optimization levels. At the first level, all solutions are managed in a single search space. When a dynamic change is successfully detected in the objective values, the Pareto ranking operator is used to enable a multiple sub-swarm’ subdivisions and processing which drives the second level of enhanced exploitation. A dynamic handling strategy based on random detectors is used to track the changes of the objective function due to time-varying parameters. A response strategy consisting in re-evaluate all unimproved solutions and replacing them with newly generated ones is also implemented. Inverted generational distance, mean inverted generational distance, and hypervolume difference metrics are used to assess the DPb-MOPSO performances. All quantitative results are analyzed using Friedman’s analysis of variance while the Lyapunov theorem is used for stability analysis. Compared with several multi-objective evolutionary algorithms, the DPb-MOPSO is robust in solving 21 complex problems over a range of changes in both the Pareto optimal set and Pareto optimal front. For 13 UDF and ZJZ functions, DPb-MOPSO can solve 8/13 and 7/13 on IGD and HVD with moderate changes. For the 8 FDA and dMOP benchmarks, DPb-MOPSO was able to resolve 4/8 with severe change on MIGD, and 5/8 for moderate and slight changes. However, for the 3 kind of environmental changes, DPb-MOPSO assumes 4/8 of the solving function on IGD and HVD metrics.

Deep-BEJT: A New Human Activity Recognition System basedon Beta Elliptical Joint Trajectory (BEJT) and Long Short TermMemory (LSTM) New journal paper

Human Face receives major attention and acquires most of the efforts of the research and studies of Machine Learning in detection and recognition. In real-life applications, the problem of quick and rapid recognition of the Human Face is always challenging researchers to come out with powerful and reliable techniques. In this paper, we proposed a new human face recognition system using the Discrete Wavelet Transformation named HFRDWT. The proposed system showed that the use of Wavelet Transformation along with the Convolutional Neural Network to represent the features of an image had significantly reduced the face recognition time, which makes it useful in real-life areas, especially in public and crowded places. The Approximation coefficient of the Discrete Wavelet Transformation played the dominant role in our system by reducing the raw image resolution to a quarter while maintaining the high level of accuracy rate that the raw image had. Results on ORL, Japanese Female Facial Expression, extended Cohn-Kanade, Labeled Faces in the Wild datasets, and our new Sudanese Labeled Faces in the Wild dataset showed that our system obtained the least recognition timing (average of 24 milliseconds for training and 8 milliseconds for testing) and acceptable high recognition rate (average of 98%) compared to the other systems.

For several decades, the offline handwriting recognition problem has escaped a satisfactory solution. In the field of online recognition, researchers have had more successful performance, but the ability to extract dynamic information from static images has not been well explored yet. In this paper, we introduce a novel multi-lingual word handwriting recovery framework based on a convolutional denoising autoencoder with an attention model for pen up / down, velocity and temporal order recovery. The proposed framework consists of extracting robust features from a handwriting image using a stacked denoising autoencoder and an encoder Bidirectional Gated Recurrent Unit (BGRU) model. Then, the obtained vectors are decoded to produce an online script with dynamic characteristics using a BGRU with temporal attention. Evaluation is done on a Latin and Arabic Online and offline handwriting character / word databases and the proposed framework achieves high competitive results. To the best of our knowledge, this is the first work of its kind.

Our work presents a virtual fitting system called Dress-up aiming to treat the task of human appearance transfer across images while preserving texture details and structural coherence of the generated outfit.

A newly introduced method called Taylor-based Optimized Recursive Extended Exponential Smoothed Neural Networks Forecasting method is applied and extended in this study to forecast numerical values. Unlike traditional forecasting techniques which forecast only future values, our proposed method provides a new extension to correct the predicted values which is done by forecasting the estimated error. Experimental results demonstrated that the proposed method has a high accuracy both in training and testing data and outperform the state-of-the-art RNN models on Mackey-Glass, NARMA, Lorenz and Henon map datasets.

- A novel approach is presented to reduced annotation based on Deep Active Learning for Arabic text detection in Natural Scene Images. - A new Arabic text images dataset (7k images) using the Google Street View service named TSVD. - A new semi-automatic method for generating natural scene text images from the streets. - Training samples is reduced to 1/5 of the original training size on average. - Much less training data to achieve better dice index : 0.84