Mailman 3 July 2013 - scikit-image

Re: Failed to import LineModel, ransac
by Johannes Schönberger 18 Jul '13

18 Jul '13

@all You must download the latest development version on github to use the Line, Circle and EllipseModel and ransac. They were added just about 1 month ago. 0.9 is the dev version. 0.8 the stable version. Johannes Schönberger Am 18.07.2013 um 20:42 schrieb "Jean-Patrick Pommier" <jeanpatrick.pommier(a)gmail.com<mailto:jeanpatrick.pommier@gmail.com>>: The example using LineModel <http://scikit-image.org/docs/dev/auto_examples/plot_ransac.html> mentions skimage 0.9. To use LineModel, should I try to use the stable version ? 2013/7/18 Stéfan van der Walt <stefan(a)sun.ac.za<mailto:stefan@sun.ac.za>> We should update the online docs to point to the last stable version instead of to dev (as has been suggested by others in the past)--I see it causes some confusion. Stéfan On Thu, Jul 18, 2013 at 12:42 PM, Jean-Patrick Pommier <jeanpatrick.pommier(a)gmail.com<mailto:jeanpatrick.pommier@gmail.com>> wrote: > I forget to mention that skimage is running on ubuntu 13.04 and was > installed with easy_install. > > > 2013/7/18 Tony Yu <tsyu80(a)gmail.com<mailto:tsyu80@gmail.com>> >> >> >> >> >> On Wed, Jul 17, 2013 at 6:43 PM, Michael Aye <kmichael.aye(a)gmail.com<mailto:kmichael.aye@gmail.com>> >> wrote: >>> >>> I also have 0.9dev via EPD, and also do not have LineModel or ransac >>> inside the measure module. >> >> >> I didn't think EPD offered dev versions of packages. I can only see 0.8.2. >> In any case, it depends on how recently the dev version was updated. The >> RANSAC code was only merged into master about 2 months ago. (Any pulls from >> master in the last 4 months will be labeled 0.9dev.) >> >> Best, >> -Tony >> >>> On Wednesday, July 17, 2013 10:34:01 AM UTC-7, Jean-Patrick Pommier >>> wrote: >>>> >>>> Hi, >>>> >>>> >>>> When doing from ipython: >>>> >>>> print skimage.__version__ >>>> from skimage.measure import LineModel >>>> >>>> I get: >>>> >>>> >>>> --------------------------------------------------------------------------- >>>> ImportError Traceback (most recent call >>>> last) >>>> <ipython-input-55-c6b2bd2de1ce> in <module>() >>>> 1 print skimage.__version__ >>>> ----> 2 from skimage.measure import LineModel >>>> >>>> ImportError: cannot import name LineModel >>>> >>>> 0.9dev >>>> >>>> >>>> Is it a version problem ? >>>> >>>> Jean-Patrick >>>> >>>> >>> -- >>> You received this message because you are subscribed to the Google Groups >>> "scikit-image" group. >>> To unsubscribe from this group and stop receiving emails from it, send an >>> email to scikit-image+unsubscribe(a)googlegroups.com<mailto:scikit-image%2Bunsubscribe@googlegroups.com>. >>> >>> For more options, visit https://groups.google.com/groups/opt_out. >>> >>> >> >> >> -- >> You received this message because you are subscribed to a topic in the >> Google Groups "scikit-image" group. >> To unsubscribe from this topic, visit >> https://groups.google.com/d/topic/scikit-image/24fxSmErl1c/unsubscribe. >> To unsubscribe from this group and all of its topics, send an email to >> scikit-image+unsubscribe(a)googlegroups.com<mailto:scikit-image%2Bunsubscribe@googlegroups.com>. >> >> For more options, visit https://groups.google.com/groups/opt_out. >> >> > > > -- > You received this message because you are subscribed to the Google Groups > "scikit-image" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to scikit-image+unsubscribe(a)googlegroups.com<mailto:scikit-image%2Bunsubscribe@googlegroups.com>. > For more options, visit https://groups.google.com/groups/opt_out. > > -- You received this message because you are subscribed to a topic in the Google Groups "scikit-image" group. To unsubscribe from this topic, visit https://groups.google.com/d/topic/scikit-image/24fxSmErl1c/unsubscribe. To unsubscribe from this group and all of its topics, send an email to scikit-image+unsubscribe(a)googlegroups.com<mailto:scikit-image%2Bunsubscribe@googlegroups.com>. For more options, visit https://groups.google.com/groups/opt_out. -- You received this message because you are subscribed to the Google Groups "scikit-image" group. To unsubscribe from this group and stop receiving emails from it, send an email to scikit-image+unsubscribe(a)googlegroups.com<mailto:scikit-image+unsubscribe@googlegroups.com>. For more options, visit https://groups.google.com/groups/opt_out.

2 1

Re: Failed to import LineModel, ransac
by Jean-Patrick Pommier 18 Jul '13

18 Jul '13

The example using LineModel <http://scikit-image.org/docs/dev/auto_examples/plot_ransac.html>mentions skimage 0.9. To use *LineModel*, should I try to use the stable version ? 2013/7/18 Stéfan van der Walt <stefan(a)sun.ac.za> > We should update the online docs to point to the last stable version > instead of to dev (as has been suggested by others in the past)--I see > it causes some confusion. > > Stéfan > > On Thu, Jul 18, 2013 at 12:42 PM, Jean-Patrick Pommier > <jeanpatrick.pommier(a)gmail.com> wrote: > > I forget to mention that skimage is running on ubuntu 13.04 and was > > installed with easy_install. > > > > > > 2013/7/18 Tony Yu <tsyu80(a)gmail.com> > >> > >> > >> > >> > >> On Wed, Jul 17, 2013 at 6:43 PM, Michael Aye <kmichael.aye(a)gmail.com> > >> wrote: > >>> > >>> I also have 0.9dev via EPD, and also do not have LineModel or ransac > >>> inside the measure module. > >> > >> > >> I didn't think EPD offered dev versions of packages. I can only see > 0.8.2. > >> In any case, it depends on how recently the dev version was updated. The > >> RANSAC code was only merged into master about 2 months ago. (Any pulls > from > >> master in the last 4 months will be labeled 0.9dev.) > >> > >> Best, > >> -Tony > >> > >>> On Wednesday, July 17, 2013 10:34:01 AM UTC-7, Jean-Patrick Pommier > >>> wrote: > >>>> > >>>> Hi, > >>>> > >>>> > >>>> When doing from ipython: > >>>> > >>>> print skimage.__version__ > >>>> from skimage.measure import LineModel > >>>> > >>>> I get: > >>>> > >>>> > >>>> > --------------------------------------------------------------------------- > >>>> ImportError Traceback (most recent call > >>>> last) > >>>> <ipython-input-55-c6b2bd2de1ce> in <module>() > >>>> 1 print skimage.__version__ > >>>> ----> 2 from skimage.measure import LineModel > >>>> > >>>> ImportError: cannot import name LineModel > >>>> > >>>> 0.9dev > >>>> > >>>> > >>>> Is it a version problem ? > >>>> > >>>> Jean-Patrick > >>>> > >>>> > >>> -- > >>> You received this message because you are subscribed to the Google > Groups > >>> "scikit-image" group. > >>> To unsubscribe from this group and stop receiving emails from it, send > an > >>> email to scikit-image+unsubscribe(a)googlegroups.com. > >>> > >>> For more options, visit https://groups.google.com/groups/opt_out. > >>> > >>> > >> > >> > >> -- > >> You received this message because you are subscribed to a topic in the > >> Google Groups "scikit-image" group. > >> To unsubscribe from this topic, visit > >> https://groups.google.com/d/topic/scikit-image/24fxSmErl1c/unsubscribe. > >> To unsubscribe from this group and all of its topics, send an email to > >> scikit-image+unsubscribe(a)googlegroups.com. > >> > >> For more options, visit https://groups.google.com/groups/opt_out. > >> > >> > > > > > > -- > > You received this message because you are subscribed to the Google Groups > > "scikit-image" group. > > To unsubscribe from this group and stop receiving emails from it, send an > > email to scikit-image+unsubscribe(a)googlegroups.com. > > For more options, visit https://groups.google.com/groups/opt_out. > > > > > > -- > You received this message because you are subscribed to a topic in the > Google Groups "scikit-image" group. > To unsubscribe from this topic, visit > https://groups.google.com/d/topic/scikit-image/24fxSmErl1c/unsubscribe. > To unsubscribe from this group and all of its topics, send an email to > scikit-image+unsubscribe(a)googlegroups.com. > For more options, visit https://groups.google.com/groups/opt_out. > > >

1 0

Re: GLCM with scikit-image
by Neil 18 Jul '13

18 Jul '13

I wouldn't worry too much about the warning. Whenever you convert an image from floating point (64 bits per pixel) to bytes (8 bits per pixel), there may be a loss of precision. The lines: im = skimage.img_as_ubyte(im) im /= 32 are just a quick way to scale the pixel intensities to have 8 different levels. The first step converts the image from floats to bytes (this is where you get the warning). We now have an image with 256 levels (from 0 to 255). After dividing by 32, there are only 8 possible levels (from 0 to 7). It is likely that matlab use a different procedure for converting from a floating point image to an image with only 8 levels. The [0][0] is to specify which offset you want. The first 0 gives the index for the distances, and the second is the index for the angles. In this example, we are only computing one offset (distance=1 and angle=0). However, in many real-life applications you will want to compute the statistics for a number of offsets to capture differences in scale and orientation. Neil On Monday, 8 July 2013 14:00:11 UTC+1, ely...(a)mail.com wrote: > > Hi, > > Thanks a lot for the reply. > > Indeed graycoprops normalizes the gray-level co-occurrence matrix: > > “graycoprops normalizes the gray-level co-occurrence matrix (GLCM) so that > the sum of its elements is equal to 1. Each element (r,c) in the normalized > GLCM is the joint probability occurrence of pixel pairs with a defined > spatial relationship having gray level values r and c in the image. > graycoprops uses the normalized GLCM to calculate properties.” ( > http://www.mathworks.co.uk/help/images/ref/graycoprops.html) > > The modified script: > import skimage > > from skimage.io import imread > from skimage.feature import greycomatrix > from skimage.feature import greycoprops > > im = imread('C:/Users/Asher_dell/Desktop/ImgTemp/python.jpg', as_grey=True) > > im = skimage.img_as_ubyte(im) > im /= 32 > g = skimage.feature.greycomatrix(im, [1], [0], levels=8, symmetric=False, > normed=True) > > contrast= skimage.feature.greycoprops(g, 'contrast')[0][0] > energy= skimage.feature.greycoprops(g, 'energy')[0][0] > homogeneity= skimage.feature.greycoprops(g, 'homogeneity')[0][0] > correlation=skimage.feature.greycoprops(g, 'correlation')[0][0] > dissimilarity=skimage.feature.greycoprops(g, 'dissimilarity')[0][0] > ASM=skimage.feature.greycoprops(g, 'ASM')[0][0] > > > print('contrast is: ', contrast) > print('energy is: ', energy) > print('homogeneity is: ', homogeneity) > print('correlation is: ', correlation) > print('dissimilarity is: ', dissimilarity) > print('ASM is: ', ASM) > > > Output: > skimage.dtype_converter: WARNING: Possible precision loss when converting > from float64 to uint8 > contrast is: 0.301542207792 > energy is: 0.29069020973 > homogeneity is: 0.883463991917 > correlation is: 0.971624675221 > dissimilarity is: 0.243464091878 > ASM is: 0.0845007980331 > > Based on the output I have few more questions on the modified script: > - Does the "skimage.dtype_converter: WARNING: Possible precision loss when > converting from float64 to uint8" means that the output values are wrong? > - Can you please explain me why you use these lines: > > im = skimage.img_as_ubyte(im) > im /= 32 > - Why do you use the [0][0] when you call skimage.feature.greycoprops > (e.g.,skimage.feature.greycoprops(g, 'contrast')[0][0])? > > Thanks a lot again.

4 4

Re: Failed to import LineModel, ransac
by Stéfan van der Walt 18 Jul '13

18 Jul '13

We should update the online docs to point to the last stable version instead of to dev (as has been suggested by others in the past)--I see it causes some confusion. Stéfan On Thu, Jul 18, 2013 at 12:42 PM, Jean-Patrick Pommier <jeanpatrick.pommier(a)gmail.com> wrote: > I forget to mention that skimage is running on ubuntu 13.04 and was > installed with easy_install. > > > 2013/7/18 Tony Yu <tsyu80(a)gmail.com> >> >> >> >> >> On Wed, Jul 17, 2013 at 6:43 PM, Michael Aye <kmichael.aye(a)gmail.com> >> wrote: >>> >>> I also have 0.9dev via EPD, and also do not have LineModel or ransac >>> inside the measure module. >> >> >> I didn't think EPD offered dev versions of packages. I can only see 0.8.2. >> In any case, it depends on how recently the dev version was updated. The >> RANSAC code was only merged into master about 2 months ago. (Any pulls from >> master in the last 4 months will be labeled 0.9dev.) >> >> Best, >> -Tony >> >>> On Wednesday, July 17, 2013 10:34:01 AM UTC-7, Jean-Patrick Pommier >>> wrote: >>>> >>>> Hi, >>>> >>>> >>>> When doing from ipython: >>>> >>>> print skimage.__version__ >>>> from skimage.measure import LineModel >>>> >>>> I get: >>>> >>>> >>>> --------------------------------------------------------------------------- >>>> ImportError Traceback (most recent call >>>> last) >>>> <ipython-input-55-c6b2bd2de1ce> in <module>() >>>> 1 print skimage.__version__ >>>> ----> 2 from skimage.measure import LineModel >>>> >>>> ImportError: cannot import name LineModel >>>> >>>> 0.9dev >>>> >>>> >>>> Is it a version problem ? >>>> >>>> Jean-Patrick >>>> >>>> >>> -- >>> You received this message because you are subscribed to the Google Groups >>> "scikit-image" group. >>> To unsubscribe from this group and stop receiving emails from it, send an >>> email to scikit-image+unsubscribe(a)googlegroups.com. >>> >>> For more options, visit https://groups.google.com/groups/opt_out. >>> >>> >> >> >> -- >> You received this message because you are subscribed to a topic in the >> Google Groups "scikit-image" group. >> To unsubscribe from this topic, visit >> https://groups.google.com/d/topic/scikit-image/24fxSmErl1c/unsubscribe. >> To unsubscribe from this group and all of its topics, send an email to >> scikit-image+unsubscribe(a)googlegroups.com. >> >> For more options, visit https://groups.google.com/groups/opt_out. >> >> > > > -- > You received this message because you are subscribed to the Google Groups > "scikit-image" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to scikit-image+unsubscribe(a)googlegroups.com. > For more options, visit https://groups.google.com/groups/opt_out. > >

1 0

seeking advice on HoG applicability
by Lisa Torrey 18 Jul '13

18 Jul '13

Hi folks - I'm looking at an image classification problem, and wondering whether HoG should be applicable to it. If any of you are willing to take a look and give some advice, that would be wonderful. I have a machine learning background, but working with image data is a new area for me. The problem is to distinguish between two types of moss. Type 1 tends to consist of upright stalks with few or no branches. Type 2 tends to have secondary branches coming off the primary stalk. There's quite a bit of visual diversity within these types. I've linked some images below. Type 1: http://myslu.stlawu.edu/~ltorrey/moss/andrea_rothii.jpg http://myslu.stlawu.edu/~ltorrey/moss/mnium_spinulosum.jpg Type 2: http://myslu.stlawu.edu/~ltorrey/moss/climacium_americanum.jpg http://myslu.stlawu.edu/~ltorrey/moss/rhytidiadelphus_triquetrus.jpg When I came across the Dalal paper, I thought my problem might have something in common with the pedestrian detection problem, so I tried extracting HoG features and feeding them into an SVM classifier. This failed miserably - the SVM does no better than random guessing. I'm now trying to weigh potential reasons. The first possible reason on my list is the diversity among mosses of the same type. There isn't necessarily a "type 1 shape" and a "type 2 shape," at least not to the degree that there's a "pedestrian shape." Perhaps this means HoG isn't really the right approach to my problem after all? Other reasons may include: - I have much less data. (Just 77 positives and 78 negatives, compared to Dalal's 1239 and 12180.) - My images aren't all the same size, like the pedestrian images are. (I'm not sure if this would matter?) - My images are much higher resolution. (I've been downscaling them by a factor of 8, but the feature vectors are still enormous.) - I'm just using default parameters so far. (In the absence of any signal, tweaking seems unproductive.) Any thoughts or suggestions would be welcome! -Lisa

4 6

Re: Failed to import LineModel, ransac
by Jean-Patrick Pommier 18 Jul '13

18 Jul '13

I forget to mention that skimage is running on ubuntu 13.04 and was installed with easy_install. 2013/7/18 Tony Yu <tsyu80(a)gmail.com> > > > > On Wed, Jul 17, 2013 at 6:43 PM, Michael Aye <kmichael.aye(a)gmail.com>wrote: > >> I also have 0.9dev via EPD, and also do not have LineModel or ransac >> inside the measure module. > > > I didn't think EPD offered dev versions of packages. I can only see 0.8.2. > In any case, it depends on how recently the dev version was updated. The > RANSAC code was only merged into master about 2 months ago. (Any pulls from > master in the last 4 months will be labeled 0.9dev.) > > Best, > -Tony > > On Wednesday, July 17, 2013 10:34:01 AM UTC-7, Jean-Patrick Pommier wrote: >>> >>> Hi, >>> >>> >>> When doing from ipython: >>> >>> print skimage.__version__ >>> from skimage.measure import LineModel >>> >>> I get: >>> >>> ------------------------------**------------------------------**---------------ImportError Traceback (most recent call last)<ipython-input-55-**c6b2bd2de1ce> in <module>() 1 print skimage.__version__----> 2 from skimage.measure import LineModel >>> ImportError: cannot import name LineModel >>> >>> >>> 0.9dev >>> >>> >>> Is it a version problem ? >>> >>> Jean-Patrick >>> >>> >>> -- >> You received this message because you are subscribed to the Google Groups >> "scikit-image" group. >> To unsubscribe from this group and stop receiving emails from it, send an >> email to scikit-image+unsubscribe(a)googlegroups.com. >> >> For more options, visit https://groups.google.com/groups/opt_out. >> >> >> > > -- > You received this message because you are subscribed to a topic in the > Google Groups "scikit-image" group. > To unsubscribe from this topic, visit > https://groups.google.com/d/topic/scikit-image/24fxSmErl1c/unsubscribe. > To unsubscribe from this group and all of its topics, send an email to > scikit-image+unsubscribe(a)googlegroups.com. > For more options, visit https://groups.google.com/groups/opt_out. > > >

1 0

Failed to import LineModel, ransac
by Jean-Patrick Pommier 18 Jul '13

18 Jul '13

Hi, When doing from ipython: print skimage.__version__ from skimage.measure import LineModel I get: ---------------------------------------------------------------------------ImportError Traceback (most recent call last)<ipython-input-55-c6b2bd2de1ce> in <module>() 1 print skimage.__version__----> 2 from skimage.measure import LineModel ImportError: cannot import name LineModel 0.9dev Is it a version problem ? Jean-Patrick

3 2

Re: How to get a region chain code?
by Valeriy Sokolov 16 Jul '13

16 Jul '13

I would like to help with the implementation. I am going to make draft which will work for my current case. But I will need some guidance and review to add it to the skimage code base. It would be helpful if you have some approach in mind... I am going to get shape boundary pixels (with morphology) and then apply something like pixel grid graph traverse of the boundary with Cython. On Tue, Jul 16, 2013 at 12:46 PM, Stéfan van der Walt <stefan(a)sun.ac.za>wrote: > This is the third time in about a month that we have the need to determine > geometric properties of regions. The right solution here is to build a > region graph, like I described in the ticket (sorry, I can't check the > number from my phone right now). Would anyone be interested in helping to > implement that? > > In the meantime we can implement the border finding manually, and later > just slot in the new structure. > > Stéfan > On 16 Jul 2013 07:03, "Chintak Sheth" <chintaksheth(a)gmail.com> wrote: > >> Hi Valeriy, >> >> Wow a compression technique! That would surely be a great addition. >> >> > I am studying a shape descriptors and would like to compute a chain >> code description of a labeled shape. I was trying to look into docs but >> have not find a direct way to get this region property with skimage. Is >> there any way to do it in a few calls which I missed? >> > >> >> - Extract the boundary. `skimage.morphology.erosion` using >> `skimage.morphology.disk` structuring element with radius 1. Then subtract >> this from the original image. >> >> - Label the boundaries. If you already have a labeled image, then that >> saves you a function call else there is `label` function in >> `skimage.morphology`. >> >> - Use `np.transpose(np.where(label == 1))` to generate the indices of >> pixels marked as label 1. This will return a `list` of indices. You can >> simply use the first as the starting point. >> >> This should help set up the stage for the traversal. Hope this helps a >> bit. >> >> Chintak. >> >> -- >> You received this message because you are subscribed to the Google Groups >> "scikit-image" group. >> To unsubscribe from this group and stop receiving emails from it, send an >> email to scikit-image+unsubscribe(a)googlegroups.com. >> For more options, visit https://groups.google.com/groups/opt_out. >> >> >> > -- > You received this message because you are subscribed to the Google Groups > "scikit-image" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to scikit-image+unsubscribe(a)googlegroups.com. > For more options, visit https://groups.google.com/groups/opt_out. > > > -- Best regards, Valeriy Sokolov.

1 0

Re: How to get a region chain code?
by Valeriy Sokolov 16 Jul '13

16 Jul '13

On Tue, Jul 16, 2013 at 9:03 AM, Chintak Sheth <chintaksheth(a)gmail.com>wrote: > Hi Valeriy, > > Wow a compression technique! That would surely be a great addition. > Compression is cool no doubt, but I need it to turn the labeled shape into a polygon =) > > I am studying a shape descriptors and would like to compute a chain code > description of a labeled shape. I was trying to look into docs but have not > find a direct way to get this region property with skimage. Is there any > way to do it in a few calls which I missed? > > > > - Extract the boundary. `skimage.morphology.erosion` using > `skimage.morphology.disk` structuring element with radius 1. Then subtract > this from the original image. > I suppose `skimage.morphology.dilation` would work better. It will work in case we computing chain code for the line of 1-pixel width. > - Label the boundaries. If you already have a labeled image, then that > saves you a function call else there is `label` function in > `skimage.morphology`. > > - Use `np.transpose(np.where(label == 1))` to generate the indices of > pixels marked as label 1. This will return a `list` of indices. You can > simply use the first as the starting point. > > This should help set up the stage for the traversal. Hope this helps a bit. > The traverse is the most interesting part in this question =) The other things do not introduce order on the pixels and could be made with current skimage easily. > Chintak. > > -- > You received this message because you are subscribed to the Google Groups > "scikit-image" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to scikit-image+unsubscribe(a)googlegroups.com. > For more options, visit https://groups.google.com/groups/opt_out. > > > -- Best regards, Valeriy Sokolov.

1 0

Re: How to get a region chain code?
by Stéfan van der Walt 16 Jul '13

16 Jul '13

This is the third time in about a month that we have the need to determine geometric properties of regions. The right solution here is to build a region graph, like I described in the ticket (sorry, I can't check the number from my phone right now). Would anyone be interested in helping to implement that? In the meantime we can implement the border finding manually, and later just slot in the new structure. Stéfan On 16 Jul 2013 07:03, "Chintak Sheth" <chintaksheth(a)gmail.com> wrote: > Hi Valeriy, > > Wow a compression technique! That would surely be a great addition. > > > I am studying a shape descriptors and would like to compute a chain code > description of a labeled shape. I was trying to look into docs but have not > find a direct way to get this region property with skimage. Is there any > way to do it in a few calls which I missed? > > > > - Extract the boundary. `skimage.morphology.erosion` using > `skimage.morphology.disk` structuring element with radius 1. Then subtract > this from the original image. > > - Label the boundaries. If you already have a labeled image, then that > saves you a function call else there is `label` function in > `skimage.morphology`. > > - Use `np.transpose(np.where(label == 1))` to generate the indices of > pixels marked as label 1. This will return a `list` of indices. You can > simply use the first as the starting point. > > This should help set up the stage for the traversal. Hope this helps a bit. > > Chintak. > > -- > You received this message because you are subscribed to the Google Groups > "scikit-image" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to scikit-image+unsubscribe(a)googlegroups.com. > For more options, visit https://groups.google.com/groups/opt_out. > > >

1 0