Lectures in Italian, books in English
The aim is to provide basics and algorithms for the localisation of elements of interest in digital images acquiring real scenes. More sophisticated methods for information extraction from video sequences and techniques of computer vision will be also introduced and discussed.
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 judgement: 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 and video 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 og the course is organised in the following lessons:
• Lesson 1: Formation of images: Pinhole Camera; Thin len camera; Perspective camera; Intrinsic and Extrinsic parameters (  pp. 4-12; pp. 14-19)
• Lesson 2: Direct and Indirect Calibration ( pp. 22-29)
• Lesson 3: Fourier e Image Sampling: Sampling ( pp. 74-77); Fourier ( pp. 221- 275)
• Lesson 4: Stereo reconstruction: Stereo systems; Epipolar geometry; Triangulation for 3D reconstruction ( pp. 197-203;  pp. 168-174)
• Lesson 5: Binocular Vision: graph-based optimization (  211-214)
• Lesson 5: Filters: Finite Impulse Response (FIR): Infinite Impulse Response (IIR); Convolution ( pp. 107-108, 113-117;  pp. 146-156)
• Lesson 6: Filtering in domain space: Linear filtering techniques high-pass and low-pass. Non-Linear Filtering: median filter, k-median. High-Boost filter. Gaussiano filter; Derivatives; Gradient-based filtering; Laplacian filtering.( pp. 139-156; pp. 166-187; pp. 247-280;  pp. 51-66)
• Lesson 7: Image segmentation ( pp. 711-790;  Argomento 2); Segmentation region growing ( pp. 785-787); Splitting e merging segmentation ( pp. 788 - 790)
• Lesson 8: Hough Transform ( pp. 97-101;  Argomento 3)
• Lesson 9/10: Motion Tracking e Optical Flow ( Argomento 4;  pp. 191- 197)
• Lesson 11: Color image analysis: Color perception ( pp. 417-422); Grassman laws ( Argomento 5); Model spaces ( pp. 423 - 429); Clustering (Kmeans, MengHee Heng, IsoData, Ohlander, MinCut, Shi NormalizedCut ( Argomento 5)
• Lesson 12: Canny Edge Detector ( pp. 71-80); Harris ( pp. 81-84)
• Lesson 13 : Morphological Operators ( Argomento 1;  pp. 649-698)
• Lesson 14 : SIFT / Bag of words ( pp. 155-159)
The course focuses on digital images, starting from the how cameras acquire and digitalise the scene. From that, the course explores a wide collection of algorithms for the stereo-vision, edge detection, segmentation of objects to conclude with video sequences and motion analysis.
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).
. FORSYTH D.A, PONCE J., “Computer Vision - a Modern Approach”, Pearson, 2011.
 GONZALEZ R., WOODS R., "Digital Image Processing", 3rd ed, Prentice Hall, 2008.
 TRUCCO E., VERRI A., “Introductory techniques for 3-D computer vision”, Prentice Hall, 1998.
 RADKE R. J., “Computer Vision for Visual Effects”, Cambridge Press, 2012
 Lezioni 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 questions 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.