Sort by AttachmentsUse SHIFT+ENTER to open the menu (new window).
The course provides mathematical foundations and practical techniques for digital manipulation of images, image acquisition, representation, preprocessing, segmentation, and compression. Other topics include multi-resolution image processing, wavelets, morphological image processing, noise reduction and restoration, simple feature extraction and recognition tasks, image registration
Introduction, Data structure for image analysis; Shape representation; Image preprocessing; Image formats; Recognition; Feature extraction; Processing primitives; Modeling (e.g. quad applications); Local and global operations; Clustering: hierarchical and non-hierarchical methods, clustering using neural networks and genetic algorithms; Classifications; Nearest neighbors; Neural nets; Image enhancement; Segmentation application and measurement; Image storage and retrieval; Applications. Weekly practice in the lab.
This course include an overview of Computer Graphics applications; Graphics Output Primitives and its attributes; Geometric Transformations; Three-Dimensional Object Representations; Graphical User Interface and its attributes; Introduction to OpenGL programming in C++ and its applications; Overview of well-known Computer Graphics software.
Introduction to the foundation of pattern recognition algorithms. Covering theoretical foundations of classification and pattern recognition and discuss applications in character, speech and face recognition, and some applications in automation and robotics. A list topics include: Bayesian decision theory, discriminate functions for normal class distribution, pattern estimation and supervised learning, nonparametric techniques linear discriminant functions and learning, unsupervised learning and clustering, neural networks including multilayer perceptrons, stochastic algorithms (such as genetic algorithms), and cellular automata. Weekly practice in the lab.
This course introduces and explains the basic concepts of networking and discuss the practical aspects of network programming, including: General overview of networking theory; Internet Addressing using a programming language such as java or C#; Data Streams, Serialization, Exception handling; User Datagram protocol: DatagramPacket, DatagramSocket , Sending and receiving UDP packets, Building an UDP Client/Server; Transmission Control Protocol: TCP sockets, ServerSockets; Creating a TCP Client/Server ;Multi-Threaded Applications, Synchronization; Implementing Application protocols. Weekly practice in the lab
A deeper look to C++ programming. Advanced topics include pointers and strings memory management (dynamic memory allocation), object oriented design, classes and data abstraction, operator overloading, inheritance, virtual functions and polymorphism, and templates. Other topics are, exception handling, file processing, standard templates library, detailed bits and strings operations, and the pre-processor, I/O Streams.
This course aims to develop the students’ understanding of research topics related to digital image processing domain including: Image quality issues. Image enhancements. Noising-Denoising. Image restoration. Image representation and descriptors. Image pre-processing. Image segmentation. Pattern recognition in images.