Accueil › Annuaire des chercheurs › Afef Kacem Echi
Afef Kacem Echi
Affiliation : Tunis University · ENSIT
- 58Publications (affiliation tunisienne)
- 75Publications au total
- 576Citations
- 15Indice h
Profil de recherche
Afef Kacem Echi compte 58 publications référencées (2000–2026). Ses travaux paraissent principalement dans « Communications in computer and information science », « IAPR International Conference on Document Analysis and Recognition (ICDAR) » et « ELCVIA Electronic Letters on Computer Vision and Image Analysis ». Son article le plus cité, « A transformer‐based deep neural network for detection and classification of lung cancer via PET / CT images » (2023), a été cité 44 fois. 13 de ces publications datent des trois dernières années d’activité. Ses travaux sont cosignés avec au moins 12 chercheurs, notamment dans des établissements de Espagne, France.
C’est vous ? Faites connaître vos travaux
Créez gratuitement votre profil DzCademia et ajoutez vos articles : ils apparaîtront plus facilement sur Google et dans les assistants d’IA comme ChatGPT. Plus de personnes pourront vous lire et vous citer.
Créer mon profil gratuit Ajouter mes publicationsDomaines de recherche
- Handwritten Text Recognition Techniques
- Vehicle License Plate Recognition
- Advanced Neural Network Applications
- Mathematics, Computing, and Information Processing
- Image Processing and 3D Reconstruction
Publications (58)
- Head and Neck Organ-at-Risk Multi-Modal Semantic Segmentation using 3D-UNet Head and Neck Organ-at-Risk Multi-Modal Semantic Segmentation using 3D-UNet
- A Hybrid CNN–Swin Transformer Model for Emotion Recognition from Facial Expressions in Real-World Contexts
- Hybrid CNN-Transformer Model for Ovarian Cancer Lesion Classification
- Multi-views Knee MRI Classification Using Vision Transformers for Automated Meniscal Tear Detection
- Enhancing DR Classification with Swin Transformer and Shifted Window Attention
- Parkinson's Disease Severity Assessment from Gait Patterns: A CNN-Transformer Hybrid Approach
- Diabetic Retinopathy Grade Assessment Using ResNetRS
- Adaptive Facial Expression Recognition in the Wild with a CNN-Swin Transformer
- Deep Learning for Diabetic Retinopathy Early Detection and Severity Grading
- Advanced Segmentation of Diabetic Retinopathy Lesions Using DeepLabv3+
- Hybrid CNN-Swin Transformer for Glaucoma Screening in Fundus Images
- Off-line identifying Script Writers by Swin Transformers and ResNeSt-50
- Deep Learning based-framework for Math Formulas Understanding
- A transformer‐based deep neural network for detection and classification of lung cancer via PET / CT images
- Arabic Handwriting off-Line Recognition Using ConvLSTM-CTC
- Deep Learning Based Localisation and Segmentation of Prostate Cancer from mp-MRI Images
- Prostate Cancer Detection, Segmentation, and Classification using Deep Neural Networks
- Deep Layout Analysis of Multi-lingual and Composite Documents
- Off-Line Handwritten Math Formula Layout Analysis by ConvGNN
- Attention-based deep learning model for Arabic handwritten text recognition
- Attention-based CNN-ConvLSTM for Handwritten Arabic Word Extraction
- Deep Learning-Based Segmentation of Connected Components in Arabic Handwritten Documents
- Deep Learning Architecture for Off-Line Recognition of Handwritten Math Symbols
- Unconstrained Handwritten Arabic Text-lines Segmentation based on AR2U-Net
- Arabic Handwritten Documents Segmentation into Text-Lines and Words using Deep Learning
- Bayesian Versus Convolutional Networks for Arabic Handwriting Recognition
- On the Use of Attention Mechanism in a Seq2Seq Based Approach for Off-Line Handwritten Digit String Recognition
- Math Formula Script and Type Identification and Recognition
- The Incremental Artificial Immune System for Arabic Handwritten Recognition
- Arabic Recognition Based on Statistical Methods
- Impact of features and classifiers combinations on the performances of Arabic recognition systems
- Arabic/Latin and handwritten/machine-printed formula classification and recognition
- Handwritten/Machine-printed and Arabic/Latin Mathematical Formula Discrimination and Recognition
- A System for Off-Line Arabic Handwritten Word Recognition Based on Bayesian Approach
- A proposal for touching component segmentation in Arabic manuscripts
- A texture-based approach for word script and nature identification
- Localization of Touching Letters in Arabic Handwritten Documents
- Arabic/Latin and Machine-printed/Handwritten Word Discrimination using HOG-based Shape Descriptor
- Arabic handwritten words off-line recognition based on HMMs and DBNs
- Co-occurrence Matrix of Oriented Gradients for word script and nature identification
- A recognition based approach for segmenting touching components in Arabic manuscripts
- A syntax directed system for the recognition of printed Arabic mathematical formulas
- Pyramid histogram of oriented gradient for machine-printed/handwritten and Arabic/Latin word discrimination
- How to separate between Machine-Printed/Handwritten and Arabic/Latin Words?
- Towards Arabic Handwritten Word Recognition via Probabilistic Graphical Models
- Segmentation of Touching Component in Arabic Manuscripts
- Prior segmentation of old Arabic manuscripts by separator word spotting
- Recognition of machine-printed Arabic mathematical formulas
- Proposition to distinguish machine-printed from handwritten Arabic and Latin words
- Identification of Machine-Printed and Handwritten Words in Arabic and Latin Scripts
- Segmentation of Connected Components in Arabic Handwritten Documents
- COLLABORATIVE COMBINATION OF NEURON-LINGUISTIC CLASSIFIERS FOR LARGE ARABIC WORD VOCABULARY RECOGNITION
- OCR-independent and segmentation-free word-spotting in handwritten Arabic Archive documents
- Structural Features Extraction for Handwritten Arabic Personal Names Recognition
- A System for an Automatic Reading of Student Information Sheets
- Neural-linguistic classifier combination for large Arabic word vocabulary recognition
- Neural Network for the Recognition of Handwritten Tunisian City Names
- Extraction de formules à partir de documents mathématiques
Revues de publication
- Communications in computer and information science × 8
- IAPR International Conference on Document Analysis and Recognition (ICDAR) × 8
- ELCVIA Electronic Letters on Computer Vision and Image Analysis × 7
- International Conference on Frontiers in Handwriting Recognition × 6
- Lecture notes in computer science × 2
- International Conference on ICT & Accessibility (ICTA) × 2
Publications par année
- 20264
- 20254
- 20245
- 20236
- 20223
- 20211
- 20201
- 20195
- 20181
- 20173
Collaborations
Établissements partenaires : University of Monastir · Manouba University · Tunis El Manar University · National Engineering School of Tunis · Institut Salah-Azaïz
Pays des co-auteurs : Espagne · France
Co-auteurs
- Takwa Ben Aïcha Gader
- Asma Saïdani
- Nabil Aouadi
- Kawther Khazri Ayeb
- Akram Khémiri
- Imen Ben Cheikh
- Mourad Elloumi
- Yahia Bouslimi
- Meher Boulaabi
- Sameh Mbarek
- Leila Jemni Ben Ayed
- Soumaya Hamrouni
Données bibliographiques issues d’OpenAlex (base ouverte).
Pourquoi choisir Dzcademia ?
Pour donner à vos travaux plus de chances d’être découverts et recommandés par les IA. Profils, articles et communications : donnez à votre recherche une présence publique structurée. Les métadonnées intégrées aident les moteurs de recherche et les assistants IA à identifier vos travaux et à comprendre leurs références.
Commenter avec Google
Connecte-toi avec Google pour commenter directement sur cette page.