Politecnico di Torino
Politecnico di Torino
Politecnico di Torino
Academic Year 2014/15
Computer vision
Master of science-level of the Bologna process in Computer Engineering - Torino
Master of science-level of the Bologna process in Cinema And Media Engineering - Torino
Teacher Status SSD Les Ex Lab Tut Years teaching
Montrucchio Bartolomeo ORARIO RICEVIMENTO A2 ING-INF/05 40 0 20 0 8
SSD CFU Activities Area context
ING-INF/05 6 C - Affini o integrative A11
Subject fundamentals
The course is taught in Italian.

Image capture, processing and understanding are required for many practical applications. In particular, Computer Vision refers to computing properties of the 3D world from 2D images. Among main applications, we quote industrial inspection, surveillance, biometric identification, human body motion capture for entertainment, medicine or sport performance enhancement, satellite and UAV images analysis, 3D scanning, and robotic navigation. The course will provide the elements of the most used image processing and analysis techniques, and will illustrate some popular application.
Expected learning outcomes
The course will supply the main elements about:
- Sensor and optical systems
- Optical systems' models and transfer functions
- Frequency analysis of images
- Enhancement and reconstruction of images corrupted by noise, motion blur, atmospheric turbulence, etc.
- Techniques for image segmentation and feature extraction
- 2D and 3D objects recognition
- Motion analysis
Using this knowledge, and based on several examples, the student should be able to design image analysis and computer vision applications.
Prerequisites / Assumed knowledge
Basics of analysis, 1D signal processing, linear algebra, probability theory.
Main topics.
- Imaging systems (1 cr)
- Image processing. 2D transforms and transfer function(1,0 cr)
- Image enhancement and image restoration (0.5 cr)
- Image segmentation and feature extraction (0.5 cr)
- 2D and 3D object recognition (1 cr)
- Motion analysis(0.5 cr)
- Case studies(1.5 cr)
Delivery modes
The laboratory sessions will build on the material covered in the class, and aim to solidify your understanding of concepts through hands-on experimentation. Project will be assigned individually or to small groups. The results will be evaluated and will contribute to the final mark.
Texts, readings, handouts and other learning resources
Course transparencies and other material at http://didattica.polito.it
Suggested textbooks:
- R.C. Gonzales and R.E. Woods: Digital Image Processing, Pearson International Edition, 2008
- C. Steger, M. Ulrich, C. Wiedermann: Machine Vision Algorithms and Applications, Wiley-VCH, 2008
- G.C. Holst and T.S. Lomheim: CMOS/CCD Sensors and Camera Systems, SPIE Press, 2007
- E.R. Davies, Machine Vision: Elsevier, 2005
Assessment and grading criteria
The exam is composed by a written part, in which it will be required to answer to questions and to solve exercises. If required by the teacher there will be also an oral exam.
It is required to book for the exam and to have an identity card during the exam.
No computers, mobile phones or smartphone, books or notes will be allowed during the exam.
A mandatory work, from one or more students together, is required, in order to create a graphic application using the knowledge got during the course.

Programma definitivo per l'A.A.2014/15

© Politecnico di Torino
Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY
WCAG 2.0 (Level AA)