Lectures in Italian, books in English
The aim is to provide basics and algorithms for the localization of elements of interest in digital images acquiring real scenes. More sophisticated methods for information extraction from images are detailed which are also the basis of computer vision.
Knowledge and understanding: the student must demonstrate knowledge and understanding of the fundamentals of treatments of digital images and of the implementations of efficient algorithms for the manipulation and the extraction of information.
Ability to apply knowledge and understanding: the student must demonstrate the ability to use their acquired knowledge to solve real problems on real images. Moreover, he/she must demonstrate to own adequate knowledge to postulate and discuss original solutions to real case studies.
Autonomy of judgment: the student should be able to assess independently the results coming from the scientific literature and from commercial solutions proposed in the field of digital image processing.
Communication skills: the student should be able to discuss approaches and algorithms in the field of study using academic rigor and appropriate terms. He/She must grab the key aspects of solutions in the literature and be able to illustrate and summarise their principles of working.
Learning skills: students must be able to update and deepen topics and applications about image and video processing applied to varied and diverse research fields.
A good approach and knowledge of the procedural programming is required as well as for basic data structures, with reguard to C/C++ programming language. Having attended a language programming course and passed the exam is therefore strongly required to successfully pass the exams of this course.
In addition, basic notions of linear algebra is strongly required to understand the algorithms presented during the course. Precisely, vectors and matrices together with the algebraic operations to work with them will be considered as previous knowledge of the students and no lessons will be dedicated to them.
The extended program of the course is organized in the following lessons:
Supervised and unsupervised Learning
Pinhole camera model
Image sensing and acquisition
Point transforms, histograms etc.
Fourier Transform and sampling
Filtering in the frequency domain
Region splitting e merging
Morphological Image Processing
The course is focused on the concept of digital image and therefore on the acquisition and digitization of the observed scene.
Starting from the digital image, a wide range of methods and algorithms for point image transformations, filtering in the spatial domain and in the frequency domain are illustrated. Furthermore, numerous algorithms for the analysis of the contours, segmentation are shown, and finally, methods for transforming images by mathematical morphology are overviewed.
An introduction to the basic concepts of Artificial Intelligence and Machine Learning is foreseen which constitute a fundamental basis in modern techniques of image processing and computational vision.
Teaching consists of 48 hours lectures, organised in lessons of 2 hours according to the academic calendar. Each lecture can be a theoretical and practical lesson, given by the teacher and related to one of the topics of the course. The theoretical lessons aim at giving the student the knowledgebase of algorithms for image processing and the technical and scientific basics for the understanding and the implementation of them. During the course, practical lessons are provided. They are collegial in nature, take place in the classroom and are given by the teacher who proposes solutions to practical exercises meant to verify the adoption and implementation of the theoretical topics presented in the previous lessons. The resolution of such exercises allows the students to verify his/her understanding of the theoretical concepts and his/her ability to proposed alternative implementations
The attendance is strongly encouraged, although it is optional. The exam is the same for all student, no matter of the rate of the attendance of the lessons (exception to this rule is for students who constantly attend the lesson and who have access to the partial tests).
 GONZALEZ R., WOODS R., "Digital Image Processing", 3rd ed, Prentice Hall, 2008.
 FORSYTH D.A, PONCE J., “Computer Vision - a Modern Approach”, Pearson, 2011.
 Lecture slide on the e-learning.
The final exam, available also in English, consists in a written test including both theoretical and practical topics. The rating assigned, 30 points in total, is equally divided between the two parts. The exam takes place entirely in the laboratory. The practical part, which is mandatory to successfully pass the exam, is taken at the computer and asks the student to implement a procedure for a case study for which an image is provided. The evaluation takes into account the how the proposed solution matches with the algorithm required and the visual quality of the output provided. The evaluation can be enhanced if the student shows a good programming approach, the originality of the proposed answer and the usage of data structures. The theoretical part consists in a question with open answer. The evaluation considers the maturity of the student in summarising with exhaustive and formal details the answer to the questions provided. Useful to successfully passing the exam is the usage of an appropriate terminology and the ability to discuss logical linkages among the theoretical topics.
The learning material is provided, in English, through the e-learning platform at the following weblink http://e-scienzeetecnologie.uniparthenope.it. To access the published material, the student must be regularly registered at the platform and subscribed at the course.
The teacher is always available at receiving the students during the lessons for clarification or doubts about the topics of the course. Conversely, an appointment between the student and the teacher must be agreed and scheduled by email.