Recognition of warships by class using image analysis algorithms and neural networks
Αναγνώριση πολεμικών πλοίων κατά τύπο με χρήση αλγορίθμων ανάλυσης εικόνας και νευρωνικών δικτύων
View/
Keywords
Τεχνητή νοημοσύνη ; Neural networks ; CNN ; Convolutional neural networks ; Image analysis ; Πολεμικά πλοίαAbstract
In this section of the study, a summary of the project and its key areas are presented. The following study is focusing on exploring and proposing traditional Image Analysis algorithms as well as a Convolutional Neural Network, which can recognize and categorize warships, using images emanated by different sensors, efficiently and accurately by type. The project starts with a brief introduction to categorizing objects using Image Analysis algorithms, continues with a brief presentation of the existing problem at hand and similar studies as well as a description of the available dataset.
Concluding, having presented the approach on the thinking behind the creation of the algorithms and methodologies to resolve this Computer Vision problem, the benchmarking of the performance of the model is presented, followed by a comment of the performance achieved, followed by a brief description of the conclusions that were reached and a reference for future work on this particular subject.
Postgraduate Studies Programme
Προηγμένα Συστήματα Πληροφορικής - Ανάπτυξη Λογισμικού και Τεχνητής ΝοημοσύνηςDepartment
Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα ΠληροφορικήςNumber of pages
70Language
EnglishCollections
Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα