Thank you for reporting your experience with installing JAL. It is valueable for improving PacMan's heuristics in future versions.
--- Bj�rn Helgason <[EMAIL PROTECTED]> wrote: > I was going to look at dendrite and your examples but ran into the same > problems of being without JAL so I finally gave in and tried to install JAL > > Got the libraries and got the run/ pacage manager option straight away. > > Found wget quickly and installed it. > Had some problem finding a site to download and install unzip > Once both wget and unzip where installed and working I was still getting the > report on HTTP Cmd and Unzip > By the way wget was working but the report said always both wget and unzip > not working > > Anyway after wget and unzip were there and working - I was still getting > report from J configure it was not - > I needed to point configure at the web browser - mozilla in my case - and > then it started working - looks like it anyway. > > Now JAL seems to be up and running at this place. > I can not test it further until next week and in the meantime I will also > try to install JAL and possibly some of the addons in other places I have > computers I work on. > > 2007/3/16, Björn Helgason <[EMAIL PROTECTED]>: > > > > That looks really interesting. > > I am pretty sure this can be useful. > > " Outliers are atypical (by definition), infrequent observations" > > I have to admit that I do not understand the technique yet but I will > > certainly give it a try. > > > > Also I have found after going through some hundreds of images that some > > methods are more reliable than others and using only those who are more > > reliable and combine it with this I will be getting pretty close to > > certainty I guess. > > > > I have tried different sizes of the kern 8 8;16 16;20 20; 24 24 - the > > total image being 512 512. > > It looks like 24 24 is giving me best results. Is there any rule to how > > big the kern size should be? > > > > 2007/3/15, Oleg Kobchenko <[EMAIL PROTECTED]>: > > > > > > I tried to run this set of data through Dendrite > > > cluster analysis to filter the error results and > > > got a new average of 327.75 363.5. > > > > > > See details in the "Error Filter" topic at > > > http://www.jsoftware.com/jwiki/Essays/Dendrite/Applications > > > > > > > > > --- Bj�rn Helgason <[EMAIL PROTECTED]> wrote: > > > > > > > I accidentally divided by 5 instead of 6 but that does not change the > > > > question > > > > > > > > > > > > > > > > a=.328 364;127 478;159 1;328 363;327 365;328 362 > > > > 6%~+/>a > > > > 266.167 322.167 NB. correct answer should be 328 363 > > > > > > > > > > > > a=.247 235;0 0;244 433;129 304;246 236;291 48 > > > > 6%~+/>a > > > > 192.833 209.333 NB. correct answer should be 247 235 > > > > > > > > > > > > 2007/3/15, Björn Helgason <[EMAIL PROTECTED]>: > > > > > > > > > > Lets say I use different methods to find the point and the correct > > > answer > > > > > should be 328 363 > > > > > > > > > > Even if the majority are correct or close to it the mean may not be > > > a good > > > > > answer > > > > > > > > > > > > > > > a=.328 364;127 478;159 1;328 363;327 365;328 362 > > > > > 5%~+/>a > > > > > 319.4 386.6 > > > > > > > > > > Any suggestions to get a better approximation? > > > > > > > > > > 2007/3/15, Björn Helgason < [EMAIL PROTECTED] >: > > > > > > > > > > > > I am trying different sizes of the kern and different filters. > > > > > > > > > > > > I created a form to show the images and different filtering and > > > various > > > > > > results of finding the object. > > > > > > I try it out with finding patterns equal to different numbers and > > > > > > combinations of numbers as well as the actual kern without filter. > > > > > > > > > > > > It takes time to do the manual checking to see what settings give > > > best > > > > > > results and are accurate. > > > > > > > > > > > > > > > > > > 2007/3/14, Oleg Kobchenko < [EMAIL PROTECTED] >: > > > > > > > > > > > > > > The listed image formats should not produce any > > > > > > > difference since they all are lossless compressions. > > > > > > > You can verify creating images in different formats, > > > > > > > loading in J and then subtracting the values. > > > > > > > > > > > > > > Regarding image recognition, although the simple difference > > > minimum > > > > > > > method may work, it is not very stable and depends on > > > > > > > accuracy of defining the kernel and the chosen threshold, > > > > > > > which is different for every instance. > > > > > > > > > > > > > > It would be nice to see how other methods fair, > > > > > > > such as cross-correlation, as listed by Devon McCormick > > > > > > > > > > > > > > > > > http://www.jsoftware.com/pipermail/general/2007-March/029123.html > > > > > > > > > > > > > > You can go iteratively, tweaking a working algorithm > > > > > > > with different ideas to see what's improving. > > > > > > > For example, I like the idea of normalization (first link) > > > > > > > > > > > http://www.owlnet.rice.edu/~elec431/projects96/pictomaniacs/previous.html<http://www.owlnet.rice.edu/%7Eelec431/projects96/pictomaniacs/previous.html> > > > > > > > <http://www.owlnet.rice.edu/%7Eelec431/projects96/pictomaniacs/previous.html > > > > > > > > > > > > > > > > > > You can apply it to the method you use now to see if it will > > > > > > > eliminate the mismatch. > > > > > > > > > > > > > > > > > > > > > --- Bj�rn Helgason < [EMAIL PROTECTED]> wrote: > > > > > > > > > > > > > > > When extracting an image to work with from a Dicom file I have > > > three > > > > > > > options > > > > > > > > > > > > > > > > dcm2pnm - Convert DICOM images to PPM/PGM, PNG, TIFF or BMP > > > > > > > > > > > > > > > > +obt --write-24-bit-bmp > > > > > > > > write 24-bit truecolor BMP > > > > > > > > > > > > > > > > +ot --write-tiff > > > > > > > > write 8-bit (monochrome) or 24-bit (color) > > > TIFF > > > > > > > > > > > > > > > > +on --write-png > > > > > > > > write 8-bit (monochrome) or 24-bit (color) > > > PNG > > > > > > > > > > > > > > > > > > > > > > > > I have up to now used bmp and am reasonably happy with the > > > results. > > > > > > > > > > > > > > > > I am wondering if the other forms TIFF or PNG would give me > > > better > > > > > > > results. > > > > > > > > Would I need different technique to find the object I am > > > looking for > > > > > > > in the > > > > > > > > image? > > > > > > > > > > > > > > > > The method Oleg sent in earlier finds the object most of the > > > time in > > > > > > > the BMP > > > > > > > > images. > > > > > > > > Actually only found one image so far where it missed the > > > object and > > > > > > > gave > > > > > > > > another fairly similar looking location. ____________________________________________________________________________________ Sucker-punch spam with award-winning protection. Try the free Yahoo! Mail Beta. http://advision.webevents.yahoo.com/mailbeta/features_spam.html ---------------------------------------------------------------------- For information about J forums see http://www.jsoftware.com/forums.htm
