CENG466 Assignment 3
1. Boundary extraction
Use Hough
transform to extract the boundaries of the major shapes in the given images. If
possible, draw each boundary in a different color value, otherwise you may draw
the boundaries in black on a white background. You need to filter the image
(i.e. detect edges, etc.) before Hough transformation.
What to put into the report:
Describe your filtering scheme. Describe your parameter
space and your implementation of Hough transform. Explain how you extract the
boundaries. If you perform any post-processing on boundaries, describe
them.
Images:
The
images are Dilbert strips from http://www.dilbert.com/ . Detecting major
lines and boundaries of the dialog balloons will be enough.
2. Region Segmentation
Segment the
given images by region growing. On your output image, indicate every region by a
different color value, making it distinguishable from other neighboring regions.
Your plugin will get the number of seed pixels as its only argument; your
program must find the appropriate locations as seeds. You may preprocess your
image, you can enhance and/or transform the color space.
What to put into the report:
Describe the two important parts of your program; the seed
pixel finding algorithm and your ``similarity'' criterion, which you use in
growing your regions. Describe your preprocessing procedure, if you do
any.
Images:
The
images to test with your program contain smooth (i.e. not
textured) regions. The major segments of the sample images are given with
the image below:
- Cubes
(background, faces and shadows)
- Bill
Gates (background, face and large pieces from clothes)
- Neo
(background, helicopter regions and Neo)
3. Report
Your report should be less
than three pages, with no limitation in number of figures and tables, but it
must not get oversized (to make things easy, no cover pages). The reports should
be either in PostScript (ps.gz and ps.Z are also OK) or PDF (preferred) formats,
which means there's no need for a hardcopy. The report must include the items
explained above to be complete. You may also submit a hardcopy report, if it
gets huge in PostScript format, or if you cannot provide a PostScript file.
Submission
The assignment is due
14/12/2000 midnight and to be submitted with submit466. Late
submissions will be evaluated over 100 - 10d2 points where d
is the number of days passed over due date. The following items are required to
be submitted in a .tar file:
- The report, you can give a hardcopy if you cannot provide a
.ps file viewable with ghostview.
- A Makefile to compile your filters, based on the one provided, only
changes to SRCS1 (for part 1), SRCS2 (for part 2), CFLAGS, CC
and LDFLAGS are accepted, i.e. you can only change compiler/linker parameters
and source filenames. The output filenames must remain unchanged.
- Source files.
The tar file should not extract in a directory, i.e.
you should
cd myHomework; tar cvf ../submission.tar src1.c src2.c src3.c
Makefile report.pdf
rather thantar cvf submission.tar
myHomework/
Evaluation
The evaluation scheme is
the same as the evaluation in the previous two assignments. 
