http:^^www.cs.wisc.edu^~dyer^cs766.html

This data set contains WWW-pages collected from computer science departments of various universities

(say down to your shoulders), and finally interactively adjusting the
Intensity modification function in the Color Editor window under the
Windows button.  (You are also free to modify other things such as color
if you wish.)  When you have found a good grayscale transformation
save the result as a <B>color gif image</B> and
put it in the same directory where
the original image is.  Send me email telling me qualitatively what
intensity transformation you applied and why it improves the quality
of the image overall.  I'll then use this image in the "photo board"
of students in the class.  Feel free to use this image in your own
Web home page as well!
<P>
<LI><B><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><!WA17><A HREF="http://www.cs.wisc.edu/~dyer/cs766/hw1.ps">Homework #1: Skeletons</A></B> (Due: October 3)
  <UL>
    <LI>Learn about getting started with
    the <!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><!WA18><A HREF="http://www.cs.wisc.edu/~dyer/cs766/vista.html">Vista vision software</A>
    <LI>Read the <CITE>Introduction to Vista Programming</CITE> manual
    that is available at DOIT Documentation
    <LI>Corrections to the Original Assignment
      <UL>
	<LI>In Method 1, change condition 1 to be "at least 3 ..."
	instead of "at least 2 ...";  this will prevent some
	types of shapes from disappearing altogether
	<LI>In Method 1, condition 2 should also count as a 0-1 transition
	the case where NW=0 and N=1
	<LI>In Method 2, the 3 x 3 matrix c for city-block distance should have
	infinity (i.e., some large constant), not 0, in the four corners
	<LI>In Method 2, the 3 x 3 matrix c for chessboard distance should have
	0, not 1, in the center position
      </UL>
    <LI><B>TEST IMAGES</B> to be used:<pre>
    (1) <tt>/p/vision/images/hw1/DOIT.v</tt>
    (2) <tt>/p/vision/images/hw1/hand.v</tt></pre>
    <LI>To evaluate your thinning results, you might want to
    try the following additional experiment using the output of at least
    one of your tests:  (1) Convert your skeleton image to ubyte format using
    <b>vconvert</b>, (2) edit (you may need to use Emacs because vi is
    not "8-bit clean") the header of the new
    image file so that it contains the following lines right after the
    <tt>repn: ubyte</tt> line:<pre>
	component_interp: gradient
	low_threshold: 1
	high_threshold: 2</pre>
    (3) run <b>vlink</b> on this file, and then (4) <b>vsegedges</b>.  
    Try using the results on the image <tt>hand.v</tt>, for example, to
    see how well this approach might be used to determine the direction
    the index finger is pointing (for a HCI application, say).
    <LI>Note:  The thinning method may in fact delete entirely some shapes;
    e.g., a 2 x 2 block of 1's surrounded by all 0's will disappear
    <LI>The thinning algorithm is based on the papers: (1) T. Zhang and C. Suen,
    A fast parallel algorithm for thinning digital patterns,
    <CITE>Comm. ACM</CITE> <B>27</B>(3), 1984, 236-239, and
    (2) H. Lu and P. Wang, A comment on "a fast parallel algorithm
    for thinning digital patterns," <CITE>Comm. ACM</CITE> <B>29</B>(3),
    1986, 239-242.
    <LI><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><!WA19><A href="http://www.cs.wisc.edu/~dyer/cs766/hw1-result.html">Comparison of student results of the
    different methods</A> applied to the pointing hand image and a
    rotated version of this test image
  </UL>
<P>
<LI><B><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><!WA20><A HREF="http://www.cs.wisc.edu/~dyer/cs766/hw2.ps">Homework #2: Image Splining for Mosaics</A></B> (Due: October 24)
  <UL>
    <LI>Read the 3 papers:
    <UL>
      <LI>E. H. Adelson et al., Pyramid methods in image processing,
        <CITE>RCA Engineer</CITE> <B>29-6</B>, Nov/Dec 1984
      <LI>P. Burt and E. H. Adelson, The Laplacian pyramid as a compact
        image code, <CITE>IEEE Trans. Comm.</CITE> <B>31</B>, 1983, 532-540
      <LI>P. Burt and E. H. Adelson, A multiresolution spline
        with application to image mosaics, <CITE>ACM Trans. Graphics</CITE>
        <B>2</B>, 1983, 217-236
      </UL>
    <LI><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><!WA21><A HREF="http://www.cs.wisc.edu/~dyer/cs766/hw2-faqs.html">Hints and FAQs</A>
    <LI><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><!WA22><A HREF="http://www.cs.wisc.edu/~dyer/cs766/hw2-result.html">Some splined images</A>
	produced by students in the class
  </UL>
<P>
<LI><B><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><!WA23><A HREF="http://www.cs.wisc.edu/~dyer/cs766/hw3.ps">Homework #3: Segmentation by Snakes</A></B> (Due: November 9)
  <UL>
    <LI>Read the 2 papers:
      <UL>
      <LI>M. Kass, A. Witkin and D. Terzopoulos,
      Snakes: Active contour models,
      <I>Int. J. Computer Vision</I> <B>1</B>,
      1988, 321-331
      <LI>D. Williams and M. Shah, A fast algorithm for active contours
      and curvature estimation, <I>Computer Vision, Graphics, and Image
      Processing: Image Understanding</I> <B>55</B>, 1992, 14-26
      </UL>
    <LI><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><!WA24><A HREF="http://www.cs.wisc.edu/~dyer/cs766/hw3-faqs.html">Hints and FAQs</A>
  </UL>
<P>
<LI><B><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><!WA25><A HREF="http://www.cs.wisc.edu/~dyer/cs766/hw4.ps">Homework #4: Your Own Project</A></B> (Due: December 18)
  <UL>
    <LI> <!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><!WA26><A HREF="http://www.cs.wisc.edu/~dyer/cs766/proj.html">Student Project Titles and Abstracts</A>
    <LI> See <!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><!WA27><A HREF="http://www.cs.wisc.edu/~dyer/cs766/readings-supp.html">Supplementary Readings</A>
    for some additional papers that might help you select a topic. 
    <LI> <!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><!WA28><A HREF="http://www-leland.stanford.edu/class/cs223b/projects/index.html">Student projects done in Stanford vision course</A>
  </UL>
</UL>
<HR SIZE=3>

<H3><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><!WA29><IMG SRC="http://www.cs.wisc.edu/~dyer/images/flow.gif" WIDTH=40 HEIGHT=40> Computer Accounts</H3>
  <UL>
    <LI><B>Accounts</B><BR>
    Course accounts are on the Sun Sparcstations called <tt>sun1 - sun36</tt>
    in rooms 1358, 1363 and 1368.  Each account has a large disk space quota
    of 50MB so you can store images for homeworks and
    your project.  Be sure to delete old images and compress others
    (see <I>gzip(1)</I>), however,
    in order to save space.  
    <LI><B>Email</B><BR>
    Email sent to <!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><!WA30><A HREF="mailto:[e-mail]">cs766-1list</A>
    goes to everyone in the class including the instructor and TA
    <LI><B>Printers</B><BR>
    To print images you should use one of the laserprinters,