Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 1 views

    Exercise 2 PDF

    Uploaded by

    Faizal meeran

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Exercise 2 PDF

    Uploaded by

    Faizal meeran
    1 views3 pages

    Original Title

    Exercise_2.pdf

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    1 views3 pages

    Exercise 2 PDF

    Uploaded by

    Faizal meeran

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 3

    ME5405 Machine Vision

    Exercise 2: Binary Image and Color Image Processing

    Question 1.
    Figures 1(a) and 1(b) show the scanned image of a document and its histogram respectively.
    Figures 1(c) show an improved image of Figure 1(a). Figure 1(d) is the histogram of the image in
    Figure 1(c).

    (i) Comment on the quality of the image shown in Figure 1(a).


    (ii) Looking at the histogram shown in Figure 1(b), suggest a good threshold value to
    generate a binary image of the image in Figure 1(a). Explain your choice of the threshold
    value.
    (iii) Propose an image processing technique to obtain the image in Figure 1(c) which is an
    improvement over the image in Figure 1(a).

    (b)

    (a)

    (d)

    (c)

    Figure 1
    Question 2.
    For a given image, the gray level values of the object and background pixels are distributed
    according to the following probability density function:
    3
    for
    4
    0 otherwise
    Sketch the two probability density functions and determine the range of possible thresholds. The
    values of a and b are 2 and 7 for the object pixels, respectively; and 1 and 5 for the background
    pixels, respectively.

    Question 3.
    Label the regions of the following binary digital image (Figure 2) using the Classical Connected
    Components Algorithm with 4- and 8- connectivity.

    Show the final image. Present the table of equivalence. Show how the equivalence is resolved
    during labelling.

    Comment on the difference between the final results achieved using 4- and 8- connectivity.
    Figure 2

    You might also like