Sök i kursutbudet

Använda sökfunktionen för att hitta i Chalmers utbildningsutbud, både vad gäller kurser och program. När det finns en kurshemsida visas en hus-symbol som leder till denna sida. Tänk på att välja det läsår du vill se information om.
Sök program och utbildningsplaner


Institutionernas kurser för doktorander

​​​​​​​​​​​​​​​​​​​​

Kursplan för

Läsår
SSY095 - Image analysis
 
Kursplanen fastställd 2009-02-23 av programansvarig (eller motsvarande)
Ägare: MPBME
7,5 Poäng
Betygskala: TH - Fem, Fyra, Tre, Underkänt
Utbildningsnivå: Avancerad nivå
Huvudområde: Elektroteknik
Institution: 32 - ELEKTROTEKNIK


Undervisningsspråk: Engelska

Modul   Poängfördelning   Tentamensdatum
Lp1 Lp2 Lp3 Lp4 Sommarkurs
0107 Tentamen 7,5 hp Betygskala: TH   7,5 hp   17 Dec 2010 em H,  27 Apr 2011 em V,  24 Aug 2011 em V

I program

MPSYS SYSTEMS, CONTROL AND MECHATRONICS, MSC PROGR, Årskurs 2 
MPRSS RADIO AND SPACE SCIENCE, MSC PROGR - Earth observations, Årskurs 2 (valbar)
ITIDM INTELLIGENT SYSTEMS DESIGN, Årskurs 2 
MPBME BIOMEDICAL ENGINEERING, MSC PROGR, Årskurs 1 (obligatorisk)
MPBME BIOMEDICAL ENGINEERING, MSC PROGR, Årskurs 2 (valbar)
MPCOM COMMUNICATION ENGINEERING, MSC PROGR, Årskurs 2 (valbar)

Examinator:

Professor  Mikael Persson


Ersätter

ESS060   Bildanalys

Kursutvärdering:

http://document.chalmers.se/doc/299901576


Behörighet:

För kurser inom Chalmers utbildningsprogram gäller samma behörighetskrav som till de(t) program kursen ingår i.

Kursspecifika förkunskaper

A basic course in Signals and Systems (or the equivalent) including the Fourier Transform, linear filter theory (impulse response, transfer function, convolution, sampling theorem). Working knowledge of probability theory.

Syfte

The aim of this course is to learn methods and algorithms for interpreting images and image sequences in terms of their content and inherent properties (e.g. number of objects, size, shape, texture, color, and motion). Also, to integrate lecturing on theory with numerical exercising, practical demonstrations, and software based laborations for strengthening the students? capacity in solving real-life image analysis applications ranging from industrial inspection to medical diagnosis.

Lärandemål (efter fullgjord kurs ska studenten kunna)

- Explain and evaluate the characteristics of digital image information (spatial resolution, contrast resolution, temporal resolution, color resolution, spatial and temporal frequency properties, noise)
- Describe the duality between spatial and frequency domain description of imaging data, apply Fourier Theory for transforming between the two, and apply linear filtering in both domains as a means of improving subjective image quality.
- Explain and apply state-of-the-art image analysis algorithms optimized for solving quantitative measurement problems.
- Motivate and apply image processing and analysis software tools such as Matlab Image Processing Toolbox for implementing and testing algorithms.
- Suggest and implement at least one major application including real-life images (Project).

Innehåll

The course is comprised of three main blocks.
1. Linear system and probability theory with emphasis on image analysis:
Image characteristics (resolution, frequency content, noise degradation). Linear filter theory (impulse response, transfer function, convolution, Fourier Transformation, sampling theorem). Imaging as a stochastic process.
2. State-of-the-art image analysis algorithms:
Algorithms for quantifying image content with respect to number of objects, size (contour and area descriptors), boundary (B-Splines, Dynamic Programming, Hough Transform), shape (Moments, Active Shape Contours, Active Shape Modeling), texture (Fourier based techniques, algorithms based on second-order statistics, autocorrelation), color (color spaces, support vector machines), and motion (optical flow, level sets).
3. Applications:
Ultrasound imaging and image analysis of the human heart and great vessels. Time-lapse microscopy for characterising stem cell shape and motion. Color image analysis in clinical odontology.

Organisation

The course is organised as a number of integrated lectures, numerical exercises, and practical demonstrations. Besides this, there are three laboratory sessions and one project. The project may be carried out as a Teamwork by two students and is reported by a written document explaining the image analysis problem at hand, a motivation of the chosen theory and algorithms, and preliminary results and conclusions.

Litteratur

Image Processing, Analysis and Machine Vision
By Sonka, Hlavac and Boyle
PWS Publishing, Pacific Grove

Examination

Written exam with TH grading, laboratory sessions (pass/fail), and project.


Sidansvarig Publicerad: må 13 jul 2020.