AIMS AND CONTENT

LEARNING OUTCOMES

The Digital Image Processing course provides students with the tools to understand the algorithms for the numerical, symbolic and semantic processing of digital images, distinguishing linear and non-linear methods, adaptive approaches and focusing on the criteria for evaluating the results. Students will learn to understand the most advanced approaches and methods, distinguishing established approaches from the most innovative and state-of-the-art solutions. One of the main objectives is to provide the student with the ability to orient himself in a critical and constructive way when faced with the offer of Internet sites that fail to grasp the complexity of the problem, propose confused, standardized and often limited approaches if not incorrect solutions in this specialist sector. Soft -skill competency of functional literacy (reading and critical use of sources), and ability to learn (self-learning). Another objective concerns the ability to analyze a problem, break it down into the main sub-parts and choose the most suitable approaches for each phase (soft-skills competence in project creation: orientation, problem solving and project planning). The practical SW laboratories allow the student to understand the theory and put it into practice with specialized tools capable of analyzing in detail all the steps and intermediate results of the most important state-of-the-art image processing algorithms. Sustainable Development Goals 4 (Quality Education) and 9 (Industry, Innovation and Infrastructure) of the 2030 Agenda are addressed, enabling the student to acquire strong skills to face the era of digital transformation related to various application fields of digital information sources.

AIMS AND LEARNING OUTCOMES

The course provides an introduction to digital image processing techniques. Analysis of digital images has several important applications e.g. remote sensing, biomedical imaging, telecommunications, character recognition, advertising photography, historical objects analysis. Nowadays, the available computational power allows almost everyone to leverage on high-performance algorithm for image processing.

In the first part, digital images will be introduced. Several color spaces are described and common techniques to change from one to another are provided.

Basic methods are presented, e.g. contrast enhancement, thresholding, histogram analysis, noise reduction, underlining the use of the discrete Fourier transform (DFT).

Classical techniques for edge detection, segmentation, mathematical morphology analysis, texture analysis are topics of the course.

During practical lessons, software for image processing such as GIMP, ImageJ, MatLab and libraries such as come OpenCV are used.

TEACHING METHODS

Combination of classical lessons and laboratory exercises.

SYLLABUS/CONTENT

• Digital Image Representation
• Color Spaces
• Image Filtering (linear and non-linear)
• Edge detection
• Image Segmentation
• Mathematical morphology
• Moments and Hough Transform
• Texture analysis
• Introduction to Deep Learning for Digital Image Processing/Regression/Recognition - Basic concepts - Convolutional Networks - application examples.

RECOMMENDED READING/BIBLIOGRAPHY

• C. OLEARI, Misurare il colore, Hoepli, II edizione, 2008

  R.M. HARALICK , L:G: SHAPIRO, Computer and Robot Vision, Vol. 1, Addison-Wesley, 1991.

  P. ZAMPERONI, Metodi dell'elaborazione digitale di immagini, Masson, 1990.

  D. H. BALLARD, C. M. BROWN, Computer vision, Prentice Hall, 1982.

  Petrou, Maria MP, and Costas Petrou. Image processing: the fundamentals. John Wiley & Sons, 2010.

  Shapiro, L., and G. Stockman. Computer Vision. Prentice-Hall Inc., New Jersey (2001)

  Jain, Anli K. Fundamentals of digital image processing. Prentice-Hall Inc., 1989

  Class slides can be downloaded from aulaweb. 

  Tests and solutions can be downloaded from aulaweb.

TEACHERS AND EXAM BOARD

LESSONS

LESSONS START

https://corsi.unige.it/en/corsi/10378/students-timetable

Class schedule

The timetable for this course is available here: Portale EasyAcademy

EXAMS

EXAM DESCRIPTION

• Written test
• Laboratory  test

Students with learning disorders ("disturbi specifici di apprendimento", DSA) will be allowed to use specific modalities and supports that will be determined on a case-by-case basis in agreement with the delegate of the Engineering courses in the Committee for the Inclusion of Students with Disabilities

ASSESSMENT METHODS

The written exam will allow to verify the learning of the topics of the program and the orientation and reasoning ability of the student.

The practical computer test will verify the ability to use the software seen during the practical laboratory exercises.