| Titre : | Algerian license plate detection and recognition system (ALCPDRS) | | Titre original : | Système de détection et de reconnaissance automatique des plaques d’immatriculation algériennes (SDRAPMA) | | Type de document : | document multimédia | | Auteurs : | Mohamed Ismail Sahli, Auteur ; Fatima Zahra Bousbaa, Directeur de thèse | | Editeur : | Laghouat : Université Amar Telidji - Département d'informatique | | Année de publication : | 2023 | | Importance : | 52 p. | | Accompagnement : | 1 disque optique numérique (CD-ROM) | | Note générale : | Option : Computer Science Systems : Systèmes Informatiques | | Langues : | Anglais | | Mots-clés : | LPDRS Deep Learning Detection Recognition Artificial Intelligence Algorithm SVM-CNN model ALPDRS | | Résumé : | With the continuing advancements in computation and communication technologies in the recent past, License Plate Detection and Recognition System (LPDRS) using artificial intelligence algorithms is an important area of research that has a wide range of applications in various domains. LPDRS is a vital technology used for vehicle identification and traffic management with the help of artificial intelligence algorithms. In fact, this system represents a type of automated inspection for transportation, traffic, and security systems, and it garners significant interest due to its potential applications in various domains, including automatic toll collection, enforcement of traffic laws, and security monitoring in restricted areas. The objective of this work is to implement an Algerian License Plate Detection and Recognition System (ALPDRS) that uses two main phases: (1) License Plate Detection (LPD) and (2) License Plate Recognition (LPR). The detection phase presents a real-time and robust method of LPR using edge detection and mathematical morphology to isolate the license plate image. The recognition phase presents a hybrid SVM-CNN model based on deep learning techniques. This model has been trained using a dataset comprising digits extracted from Algerian car plate images, which were collected specifically for this work. Our system was validated using real car images under different environmental conditions and reached a detection rate of 90.51% and an overall recognition rate of 98.66%. To improve recognition accuracy, it is crucial to use various image preprocessing techniques. For instance, blurring,gray-scale transformation, distortion correction, and edge detection. | | note de thèses : | Mémoire de master en informatique |
Algerian license plate detection and recognition system (ALCPDRS) = Système de détection et de reconnaissance automatique des plaques d’immatriculation algériennes (SDRAPMA) [document multimédia] / Mohamed Ismail Sahli, Auteur ; Fatima Zahra Bousbaa, Directeur de thèse . - Laghouat : Université Amar Telidji - Département d'informatique, 2023 . - 52 p. + 1 disque optique numérique (CD-ROM). Option : Computer Science Systems : Systèmes Informatiques Langues : Anglais | Mots-clés : | LPDRS Deep Learning Detection Recognition Artificial Intelligence Algorithm SVM-CNN model ALPDRS | | Résumé : | With the continuing advancements in computation and communication technologies in the recent past, License Plate Detection and Recognition System (LPDRS) using artificial intelligence algorithms is an important area of research that has a wide range of applications in various domains. LPDRS is a vital technology used for vehicle identification and traffic management with the help of artificial intelligence algorithms. In fact, this system represents a type of automated inspection for transportation, traffic, and security systems, and it garners significant interest due to its potential applications in various domains, including automatic toll collection, enforcement of traffic laws, and security monitoring in restricted areas. The objective of this work is to implement an Algerian License Plate Detection and Recognition System (ALPDRS) that uses two main phases: (1) License Plate Detection (LPD) and (2) License Plate Recognition (LPR). The detection phase presents a real-time and robust method of LPR using edge detection and mathematical morphology to isolate the license plate image. The recognition phase presents a hybrid SVM-CNN model based on deep learning techniques. This model has been trained using a dataset comprising digits extracted from Algerian car plate images, which were collected specifically for this work. Our system was validated using real car images under different environmental conditions and reached a detection rate of 90.51% and an overall recognition rate of 98.66%. To improve recognition accuracy, it is crucial to use various image preprocessing techniques. For instance, blurring,gray-scale transformation, distortion correction, and edge detection. | | note de thèses : | Mémoire de master en informatique |
|
Ajouter le résultat dans votre panier Faire une suggestion Affiner la rechercheAlgerian license plate detection and recognition system (ALCPDRS) / Mohamed Ismail Sahli
