Amina Serir

Automatic License Plate Recognition (ALPR) in unconstrained traffic environments requires simultaneously addressing two fundamental challenges: reliable localization of small and degraded license plates and accurate decoding of visually ambiguous character sequences. This paper presents a hierarchical multi-stage framework that combines deep-learning-based detection, geometric normalization, dual-channel recognition, and structured post-correction to improve recognition robustness under diverse real-world conditions. A systematic ablation study involving five configurations (A0–A4) demonstrates the effectiveness of the proposed architecture across three benchmark datasets. On the UC3M-LP dataset, exact-match accuracy increases from 45.2% to 88.3%, while achieving 91.6% partial accuracy and a zero detection-miss rate. The framework further attains 95% exact-match accuracy on controlled European license plate crops and 93% on a large-scale custom dataset. In addition, we identify systematic evaluation artifacts in partially annotated benchmarks, showing that truncated ground-truth labels can underestimate genuine character-level improvements. The proposed framework supports multiple license plate formats through a configurable structural template library, and preliminary experiments on a small Arabic-script subset suggest potential extensibility without full model retraining. To ensure full reproducibility, all source code and evaluation resources are publicly released.

This study proposes an automated approach based on convolutional neural networks (CNNs) and transformers to assess the severity of knee osteoarthritis using X-ray images from the OAI database. Following preprocessing (CLAHE and segmentation), four CNN models were developed, including a direct 5-class model and a hierarchical classification strategy. The sequential method first separates healthy from diseased cases, before refining classification within each group. This approach achieved the highest accuracy, exceeding 95% with the SwinV2 architecture. Grad-CAM analyses further confirmed the relevance of the regions of interest identified by the four models. Overall, these findings highlight the potential of deep learning for osteoarthritis assessment, while also emphasizing the challenges posed by intermediate cases and class imbalance.

Acute Lymphoblastic Leukemia (ALL) is an aggressive form of blood cancer characterized by the rapid proliferation of immature lymphoblasts in the bone marrow and peripheral blood. It is the most common type of leukemia in children and requires early, accurate, and rapid diagnosis to ensure effective treatment. However, conventional methods such as flow cytometry, while effective, are expensive, time-consuming, and heavily reliant on human expertise, limiting their accessibility. In this context, Artificial Intelligence (AI), particularly deep learning-based approaches, emerges as a promising solution for automating the screening of ALL from Peripheral Blood Smear (PBS) images. This study presents a comparative evaluation of several Convolutional Neural Network (CNN) architectures, including a lightweight, custom-designed model named SLIM-CNN, and vision transformer models. To simulate realworld clinical conditions, visual perturbations, such as blur and zoom were applied to the test set, enabling an assessment of the models' robustness. The results show that although CNNs including the custom SLIM-CNN model, perform well under ideal conditions, they remain sensitive to visual perturbations and lack robustness when faced with data variability. The lightweight SLIM-CNN specifically designed for automated ALL detection and classification, benefited from explainable AI (XAI) techniques, enabling visual identification of the model's attention regions. However, despite this interpretability, its stability remains limited under realistic image degradations. In contrast, vision transformer models demonstrate superior generalization capabilities and enhanced robustness in environments that simulate real-world clinical conditions, positioning them as strong candidates for effective integration into medical practice.

With the emergence of medical imaging, the compression of volumetric medical images is essential. For this purpose, we propose a novel Multiplicative Multiresolution Decomposition (MMD) wavelet coding scheme for lossless compression of volumetric medical images. The MMD is used in speckle reduction technique but offers some proprieties which can be exploited in compression. Thus, as the wavelet transform the MMD provides a hierarchical representation and offers a possibility to realize lossless compression. We integrate in proposed scheme an inter slice filter based on wavelet transform and motion compensation to reduce data energy efficiently. We compare lossless results of classical wavelet coders such as 3D SPIHT and JP3D to the proposed scheme. This scheme incorporates MMD in lossless compression technique by applying MMD/wavelet or MMD transform to each slice, after inter slice filter is employed and the resulting sub-bands are coded by the 3D zero-tree algorithm SPIHT. Lossless experimental results show that the proposed scheme with the MMD can achieve lowest bit rates compared to 3D SPIHT and JP3D.

This paper presents a quantitative visualization study and a theoretical analysis of two-phase flow relevant to polymer electrolyte membrane fuel cells (PEMFCs) in which liquid water management is critical to performance. Experiments were conducted in an air-flow microchannel with a hydrophobic surface and a side pore through which water was injected to mimic the cathode of a PEMFC. Four distinct flow patterns were identified: liquid bridge (plug), slug/plug, film flow, and water droplet flow under small Weber number conditions. Liquid bridges first evolve with quasi-static properties while remaining pinned; after reaching a critical volume, bridges depart from axisymmetry, block the flow channel, and exhibit lateral oscillations. A model that accounts for capillarity at low Bond number is proposed and shown to successfully predict the morphology, critical liquid volume and evolution of the liquid bridge, including deformation and complete blockage under specific conditions. The generality of the model is also illustrated for flow conditions encountered in the manipulation of polymeric materials and formation of liquid bridges between patterned surfaces. The experiments provide a database for validation of theoretical and computational methods.

In the contemporary period, significant attention has been focused on the prospects of innovative personal recognition methods based on palm-print biometrics. However, diminished local consistency and interference from noise are only some of the obstacles that hinder the most common methods of palm-print imaging such as the grey texture and other low-level of the palm. Nevertheless, the development of the process and tackling of the obstacles faced have a potential solution in the form of high-level characteristic imaging for palm-print identification. In this study, Zernike moments are used for acquiring superpixel features that are spiral scanned images, which is an innovative recognition method. By using the extreme learning machine, the inter- and intra-similarities of the palm-print feature maps are determined. Our experiments yield good results with an accuracy rate of 97.52 and an equal error rate of 1.47% on the palm-print PolyU database.

Ultrasonographic examination, either as visual inspection or quantitative analysis, is the most widely diagnostic resource. However, speckle noise is one of the drawbacks that makes it less effective than other medical imaging systems. Several speckle reduction methods often offer effective speckle reduction but generally suffer from oversmoothing, a blurring effect and a man-made appearance. In this paper, we propose a multi-output filter based on the multiplicative multiresolution decomposition (MOF-MMD). This multi-scale based method enables the enhancement of the original image and provides three enhanced outputs: global, edge and texture images. The multi-output filter aims at offering an enhanced image according to the features desired by radiologists. The different structures, textures and edges are filtered according to the contour image obtained by morphological operators. Three radiologists with different years of experience, have subjectively evaluated the speckle reduction methods according to enhanced features. The results of objective metrics and subjective evaluation showed that the proposed method reduces speckle and could help radiologists, according to their years of experience, in the diagnostic task. Finally, the correlation between three objective metrics and the perceived quality of contrast, diagnostic, texture and edges show that an objective metric is suitable for assessing quality of ultrasound images.