Image processing (Elaborazione delle Immagini)


AVVISO:

L'esame del 9 luglio e' rimandato di una settimana al 16 luglio, ore 10, sala riunioni II piano. Chi dovesse essere impossibilitato a venire in tale giorno, puo' contattarmi per fissare un giorno diverso, comunque successivo al 16 luglio.


Schedule of Classes (A.Y. 2017-2018)

From the 26th of February, Monday and Wednesday, Room delta, 2pm- 4:30pm


Aim


The course deals with the analysis and processing of still images. The goal is to convey conceptual instruments and basic algorithms which allow to know the principles of the image formation and coding, to improve the image quality, and to identify the elements of interest in real scene images.

Program


Introduction

Digital image processing: acquisition, storing, visualization

Visual system:

The eye, the retina, the perception of contrast, colors and movement

The color

Basic concepts of photometry and colorimetry

Digital images

Image formation, sampling and quantization

Image enhancement

Punctual and local processings
Linear and non-linear filters

Feature extraction and image segmentation

Histogram based segmentation methods
Non-supervised classification (Clustering)
Shape description (contours, regions)
Edge operators
Corner extractors
Key point descriptors
Line extraction (Hough transform)

Mathematical morphology

Basic morphological operators for binary images

Motion field

Optical flow approximations



Suggested books and supplementary material


  • DIP: R. C. Gonzalez, R. E. Woods: Digital Image Processing, Addison Wesley 1992.
  • DIP using MATLAB: R. C. Gonzalez, R. E. Woods, S.L. Eddins: Digital Image Processing using MATLAB
  • Richard Szeliski: Computer Vision: Algorithms and Applications, Springer 2010
  • Forsyth and Ponce: Computer Vision: A Modern Approach, Pearson 2011

  • Lecture notes and supplementary material



    Detailed program



    Lecture


    Topic

    Ref. Material

    Lesson


    1


    Image acquisition and formation

    chap. 1, par 2.3, 2.4 and 2.5 of DIP
    , and slides

    Theory


    2


    Percetive vision
    Radiometry,and Colorimetry

    cap. 2 and 6 of DIP,
    par. 3.1 and 3.2 and cap. 4,5,6 of Lecture Notes, and slides

    Theory


    3


    Intro to MATLAB

    cap. 1 of DIP using MATLAB, and Lab material

    Lab


    4


    Image histogram
    Point Processing

    par. 3.1,3.2 and intro 3.3 of DIP, and slides

    Theory


    5


    Image Processing Toolbox

    cap. 2 and 6 of DIP using MATLAB, and Lab material

    Lab


    6


    Color space, Image types
    Region processing

    cap. 6 and
    par 11.4 of DIP using MATLAB, and Lab material

    Lab


    7


    Image histogram
    Point Processing

    cap. 3 of DIP using MATLAB, and Lab material

    Lab


    8


    Image histogram
    Point Processing

    par. 3.1,3.2 and intro 3.3 of DIP, and slides

    Theory


    9


    Morphological image processing

    par 2.5, chap. 9 of DIP, and slides

    Theory and Lab


    10


    Geometric transformations

    par. 5.11 of DIP, slides , and Lab material

    Theory and Lab


    11


    Linear Spatial Filtering (Smoothing, Sharpening)
    Edge detector(Gradient, Laplacian, LoG, Canny)

    in cap. 3 and 10 of DIP, and , slides

    Theory


    12


    NON Linear spatial filtering (median, min, max, max-median, Extremum sharpening, modified trimmed filter))

    in cap. 3,5,10 of DIP, and , slides

    Theory


    13


    Linear and NON Linear spatial filtering (median, min, max, max-median, Extremum sharpening, modified trimmed filter))

    in cap. 3,5,10 of DIP using MATLAB, and Lab material

    Lab


    14


    Video Analysis

    slides

    Theory


    15


    Hough Transform

    cap. 10 of DIP and slides

    Theory


    16


    Corner detection and SIFT

    par. 4.1.1 and 4.1.2 of szeliski and slides ,

    Theory


    17


    Hough Transform
    Harris Corner detection

    cap. 10 of DIP using MATLAB, and Lab material

    Lab


    18


    SIFT

    slides Lab material

    Lab


    19


    Clustering (k-means, mean-shift and Arbib's methods)

    cap. "Segmentazione",
    chap. 9 of the Lecture Notes, slides,
    Lab material

    Theory


    20


    Optical Flow:
    Lucas Kanade

    Tutorial (only 2D Optical flow),
    slides,
    Lab material

    Theory



  • lella

    Links :

    • PhuSE Lab: Perceptual computing and Human Sensing Lab
    • DI: Department of Computer Science
    • UNIMI: Università degli studi di Milano