Mailman 3 May 2016 - scikit-image

Re: Most efficient way to calculate average value of labelled objects within an image
by Juan Nunez-Iglesias 17 May '16

17 May '16

This seems like a job for skimage.measure.regionprops...? On Fri, May 13, 2016 at 8:03 PM, Tamas H. <tomio2009(a)gmail.com> wrote: > How about this: maskimg is the image with the labels, img is the image you > want to analyze, then: > > for i in range(1, maskimg.max()): > img[ maskimg==i].mean() > ... > > On Fri, May 13, 2016 at 11:54 AM, 'Robin Wilson' via scikit-image < > scikit-image(a)googlegroups.com> wrote: > >> Hi, >> >> I have a labelled image, where each individual connected object has a >> unique integer value (eg. as produced from skimage.measure.label), and I >> want to get the mean value of these pixels from another image (eg. the >> image that I originally segmented before labelling). >> >> What is the most efficient way to do this? The naive way is to loop over >> the values in the image calculating it for each one - but I assume that >> numpy (or skimage itself) has a far better way of doing this... >> >> Thanks, >> >> Robin >> >> Dr Robin Wilson >> Research Fellow >> University of Southampton, UK >> >> -- >> 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. >> To post to this group, send email to scikit-image(a)googlegroups.com. >> To view this discussion on the web, visit >> https://groups.google.com/d/msgid/scikit-image/87b5d106-00d9-44bf-a89b-bff0… >> <https://groups.google.com/d/msgid/scikit-image/87b5d106-00d9-44bf-a89b-bff0…> >> . >> For more options, visit https://groups.google.com/d/optout. >> > > -- > 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. > To post to this group, send email to scikit-image(a)googlegroups.com. > To view this discussion on the web, visit > https://groups.google.com/d/msgid/scikit-image/CAM07sM6eXVGkdh1TFLPOYYBYGjc… > <https://groups.google.com/d/msgid/scikit-image/CAM07sM6eXVGkdh1TFLPOYYBYGjc…> > . > > For more options, visit https://groups.google.com/d/optout. >

1 0

Lessons learnt while developing scikit-image
by Stéfan van der Walt 14 May '16

14 May '16

Hi folks, I forgot to mention this, but here's a short talk I gave recently about lessons learnt while developing scikit-image: Slides: https://docs.google.com/presentation/d/1wz8ibYR_kN_P7zbaxKXEexWNAZBulX1Ep-y… Video: https://www.youtube.com/watch?v=KRfWQtlQfS8 Perhaps you have other lessons to add? Let me know! Also, you'll see a small showcase of scikit-image usage at the end of the slides. I was thinking of adding a section to the website for those--what do you all say? Regards Stéfan

1 0

Addition of 'Edge Drawing' and 'Edge Drawing Parameter Free' algorithms to skimage?
by Robin Wilson 14 May '16

14 May '16

Hi, I'm currently in the process of implementing the Edge Drawing algorithm (see http://ceng.anadolu.edu.tr/CV/EdgeDrawing/) in Python, and am just starting to implement the additions required to produce the Edge Drawing Parameter Free (http://ceng.anadolu.edu.tr/CV/EDPF/) algorithm too. In summary, these are quite interesting and useful edge detection algorithms that use a 'joining the dots' approach, and so produce nicely connected edges. The Parameter Free version also seems to work remarkably well for an algorithm that doesn't require any parameters! Would the addition of these algorithms to skimage be of interest? The implementation isn't quite finished yet, and could do with some tidying (potentially with advice from some of the skimage maintainers), but it shouldn't be too long until they are in a fit state. Cheers, Robin Dr Robin Wilson Research Fellow University of Southampton, UK

2 2

Re: Most efficient way to calculate average value of labelled objects within an image
by Robin Wilson 13 May '16

13 May '16

Hi, I probably didn't explain it very well, but that was the sort of loop I meant when I said "loop over all of the values of the image calculating it for each one" (values was probably a bad choice of word, I meant individual label values). I was wondering whether there was a more efficient way to do this using some sort of clever numpy or skimage function? That is, without manually looping over each label value (ie. 0 to the number of labels). Cheers, Robin On Friday, 13 May 2016 12:01:55 UTC+1, Egor Panfilov wrote: > > Hello Robin! > > Without any doubts, there is a better way to do this. You could take a > look at the informative documentation section on Indexing ( > http://docs.scipy.org/doc/numpy/reference/arrays.indexing.html#). > > The most simple and common solution could be: > > import numpy as np > > >> arr = np.random.rand(9).reshape((3, 3)) > > labels = (arr > 0.5).astype(np.uint) > > >> print(arr) > > print(labels) > > >> for label in np.unique(labels): > > mask = labels == label > > print(label, np.mean(arr[mask])) > > > Egor > > 2016-05-13 12:54 GMT+03:00 'Robin Wilson' via scikit-image < > scikit...(a)googlegroups.com <javascript:>>: > >> Hi, >> >> I have a labelled image, where each individual connected object has a >> unique integer value (eg. as produced from skimage.measure.label), and I >> want to get the mean value of these pixels from another image (eg. the >> image that I originally segmented before labelling). >> >> What is the most efficient way to do this? The naive way is to loop over >> the values in the image calculating it for each one - but I assume that >> numpy (or skimage itself) has a far better way of doing this... >> >> Thanks, >> >> Robin >> >> Dr Robin Wilson >> Research Fellow >> University of Southampton, UK >> >> -- >> 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...(a)googlegroups.com <javascript:>. >> To post to this group, send email to scikit...(a)googlegroups.com >> <javascript:>. >> To view this discussion on the web, visit >> https://groups.google.com/d/msgid/scikit-image/87b5d106-00d9-44bf-a89b-bff0… >> <https://groups.google.com/d/msgid/scikit-image/87b5d106-00d9-44bf-a89b-bff0…> >> . >> For more options, visit https://groups.google.com/d/optout. >> > >

2 1

Most efficient way to calculate average value of labelled objects within an image
by Robin Wilson 13 May '16

13 May '16

Hi, I have a labelled image, where each individual connected object has a unique integer value (eg. as produced from skimage.measure.label), and I want to get the mean value of these pixels from another image (eg. the image that I originally segmented before labelling). What is the most efficient way to do this? The naive way is to loop over the values in the image calculating it for each one - but I assume that numpy (or skimage itself) has a far better way of doing this... Thanks, Robin Dr Robin Wilson Research Fellow University of Southampton, UK

3 2

regioinfill
by Raphael 04 May '16

04 May '16

hi folks, Is there something like this http://www.mathworks.com/help/images/ref/regionfill.html found in mathlab in Scikit image? Thanks Raphael

1 0

Re: Please share your use cases
by Josh Warner 04 May '16

04 May '16

I know of uses of the package for: - Feature extraction prior to machine learning, applied to medical images (single modality as well as registered multi-spectral images), including essentially every tool in `skimage.measure`. - Medical image segmentation of 3d and multi-spectral 3d volumes - mostly with random walker - Generation of 3d-printable meshes from volumes using marching_cubes for teaching or pre-operative visualization - Interactive line profile averaging of speleothem micrographs using the viewer - Enhancement of micrograph images, using adaptive local histogram equalization - ... oh, and panorama stitching ;) Josh On Tuesday, May 3, 2016 at 5:30:48 AM UTC-5, stefanv wrote: > > On Sun, 1 May 2016 at 00:14 Nadav Horesh <nadavh.horesh(a)gmail.com> wrote: > >> My company (Visionsense) make stereoscopic medical video cameras for >> endoscopic surgeries. I use a mix of opencv and scikit-image functions to >> test and tune the image processing pipeline. Attached here a snapshot of a >> utility I built for this purpose based on skimage widgets and plugins. As a >> no-programmer, these tools are much more accessible and tailored to my >> needs than the Qt widgets, and the line-profile tool is invaluable image >> exploration tool. >> > > Thank you very much for your example, Nadav! > > Stéfan >

1 0

Re: Please share your use cases
by Stéfan van der Walt 03 May '16

03 May '16

On Sun, 1 May 2016 at 00:14 Nadav Horesh <nadavh.horesh(a)gmail.com> wrote: > My company (Visionsense) make stereoscopic medical video cameras for > endoscopic surgeries. I use a mix of opencv and scikit-image functions to > test and tune the image processing pipeline. Attached here a snapshot of a > utility I built for this purpose based on skimage widgets and plugins. As a > no-programmer, these tools are much more accessible and tailored to my > needs than the Qt widgets, and the line-profile tool is invaluable image > exploration tool. > Thank you very much for your example, Nadav! Stéfan

1 0

Re: blob detection and dust removal
by Raphael Okoye 03 May '16

03 May '16

hi Vighnesh, Thats an interesting question..never really given it a thought. I think this http://scikit-image.org/docs/dev/auto_examples/plot_label.html or the help in section 3.3.4.1.2 given here http://www.scipy-lectures.org/packages/scikit-image/ might work. As how to create the mask image to mask dust particles, I'm currently not sure how to implement that in scikit image. Thanks a lot. 3.3.4.1.2 On 2 May 2016 at 13:54, Vighnesh Birodkar <vighneshbirodkar(a)gmail.com> wrote: > regionprops takes a labelled image as input. The question still remains, > how will you generate the image in which the interested regions are > labelled accordingly. You need to make that part of your algorithm exclude > the dust particles. > > On Mon, May 2, 2016 at 3:34 PM, Raphael Okoye <raphael(a)aims.ac.za> wrote: > >> hi Vighnesh >> >> I plan to use this guy >> http://scikit-image.org/docs/dev/auto_examples/plot_regionprops.html. >> The documentation on regionprops ( >> http://scikit-image.org/docs/dev/api/skimage.measure.html#regionprops) >> says I can get parameters such as co-ordinate positions, equivalent >> diameter etc >> >> But first I need to think of a way to exclude the dust particles, that >> is the main challenge. >> >> Thanks >> Raphael >> >> On 2 May 2016 at 02:30, Vighnesh Birodkar <vighneshbirodkar(a)gmail.com> >> wrote: >> >>> How do you plan to find the position of the real crystals ? Maybe the >>> function you will use to find the original crystals will take a mask >>> argument ? >>> >>> On Mon, May 2, 2016 at 1:07 AM, Raphael Okoye <raphael(a)aims.ac.za> >>> wrote: >>> >>>> hi Vighnesh, >>>> >>>> Further processing involves getting the size and positions of real >>>> crystals (I want to use the positions to estimate the pair correlation >>>> function and then using the pair correlation function to estimate the >>>> structure factor) The image comes from a sequence of time lapse images. >>>> There are dust particles of various sizes in the images so if they are not >>>> eliminated, a false structure factor will be determined. The median filter >>>> took care of the very little ones but didn’t work for the bigger ones. >>>> >>>> Thanks a lot. >>>> >>>> Raphael >>>> >>>> On 1 May 2016 at 21:27, Vighnesh Birodkar <vighneshbirodkar(a)gmail.com> >>>> wrote: >>>> >>>>> Hi >>>>> >>>>> That really depends on your application. What's your motivation for >>>>> removing these dust particles ? How are these images going to be processed >>>>> further ? >>>>> >>>>> Thanks >>>>> Vighnesh >>>>> >>>>> On Monday, May 2, 2016 at 12:13:27 AM UTC-4, Raphael wrote: >>>>>> >>>>>> hi Vighnesh, >>>>>> >>>>>> Thanks a bunch!! I see my error now. >>>>>> >>>>>> Actually that blob you detected a dust particle. Which operation >>>>>> would you suggest to erase it? I tried morphological erosion but it doesn't >>>>>> take it away. >>>>>> >>>>>> Thanks >>>>>> Raphael >>>>>> >>>>>> On 1 May 2016 at 18:27, Vighnesh Birodkar <vighnesh...(a)gmail.com> >>>>>> wrote: >>>>>> >>>>>>> Hello Raphael >>>>>>> >>>>>>> The error here is because the output of blob_doh in a numpy array of >>>>>>> blobs, it is not an image meant for display. If you notice the example the >>>>>>> blobs are being drawn separately inside the for loop. If no blobs are being >>>>>>> detected, you can adjust the threshold. Lowering the threshold will make >>>>>>> the function detect more blobs. It is clarified futher in the documentation >>>>>>> >>>>>>> http://scikit-image.org/docs/dev/api/skimage.feature.html#skimage.feature.b… >>>>>>> >>>>>>> I was able to detect one blob in your image with the default >>>>>>> threshold value. See: >>>>>>> >>>>>>> https://gist.github.com/vighneshbirodkar/c16515126e648cf92f08d3319d3a023e >>>>>>> >>>>>>> Find the result attached. >>>>>>> >>>>>>> Thanks >>>>>>> Vighnesh >>>>>>> >>>>>>> On Saturday, April 30, 2016 at 2:02:51 AM UTC-4, Raphael wrote: >>>>>>> >>>>>>>> hi folks, >>>>>>>> >>>>>>>> Got a problem removing dust and identifying blobs/crytals. Kindly >>>>>>>> see my code below >>>>>>>> >>>>>>>> >>>>>>>> from __future__ import division, print_function >>>>>>>> import matplotlib.pyplot as plt >>>>>>>> import numpy as np >>>>>>>> from skimage import io, feature, color, measure, draw, >>>>>>>> img_as_float, exposure >>>>>>>> from skimage.filters.rank import median >>>>>>>> from skimage.feature import blob_dog, blob_log, blob_doh >>>>>>>> from skimage.morphology import disk >>>>>>>> >>>>>>>> #raw image >>>>>>>> image_raw = >>>>>>>> img_as_float((io.imread('/home/raphael/Documents/ScikitImage/Run >>>>>>>> 4-2_00061cropped.tif'))) (RawImage.tif attached) >>>>>>>> plt.imshow(image_raw) >>>>>>>> >>>>>>>> #converted to grayscale >>>>>>>> >>>>>>>> img_gray = >>>>>>>> color.rgb2gray(io.imread('/home/raphael/Documents/ScikitImage/Run >>>>>>>> 4-2_00061cropped.tif')) >>>>>>>> plt.imshow(image_gray) >>>>>>>> >>>>>>>> >>>>>>>> #applied median filter to take out small dust particles. But the >>>>>>>> big dust particle on the top right corner still persists (see median1.png >>>>>>>> attached) >>>>>>>> img_filtered=median(img_gray,disk(10)) >>>>>>>> plt.imshow(img_filtered) >>>>>>>> >>>>>>>> >>>>>>>> #applied adapthist to make image more clearer (see adaptive.png) >>>>>>>> >>>>>>>> img_equalized=exposure.equalize_adapthist(img_filtered) >>>>>>>> plt.imshow(img_equalized) >>>>>>>> >>>>>>>> #trying to detect the crystals/blobs. I followed the example here >>>>>>>> http://scikit-image.org/docs/dev/auto_examples/features_detection/plot_blob… >>>>>>>> But this gave an error. matplotlib was not happy with the data type >>>>>>>> blobs_doh = blob_doh(img_equalized, max_sigma=30, threshold=.1) >>>>>>>> plt.imshow(blobs_doh) >>>>>>>> >>>>>>>> My problems are: >>>>>>>> >>>>>>>> 1. I could not get the dust particle out especially the really big >>>>>>>> one on the top right. How can I get it out? >>>>>>>> >>>>>>>> 2. I could not detect the crystals/blobs in the image using blob_doh >>>>>>>> >>>>>>>> Any ideas/suggestions is highly appreciated. Thank you! >>>>>>>> >>>>>>> -- >>>>>>> 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/VtkzL9ZCY6Q/unsubscribe >>>>>>> . >>>>>>> To unsubscribe from this group and all its topics, send an email to >>>>>>> scikit-image...(a)googlegroups.com. >>>>>>> To post to this group, send email to scikit...(a)googlegroups.com. >>>>>>> To view this discussion on the web, visit >>>>>>> https://groups.google.com/d/msgid/scikit-image/0fd22d80-4549-470f-b61b-f48d… >>>>>>> <https://groups.google.com/d/msgid/scikit-image/0fd22d80-4549-470f-b61b-f48d…> >>>>>>> . >>>>>>> >>>>>>> For more options, visit https://groups.google.com/d/optout. >>>>>>> >>>>>> >>>>>> -- >>>>> 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/VtkzL9ZCY6Q/unsubscribe >>>>> . >>>>> To unsubscribe from this group and all its topics, send an email to >>>>> scikit-image+unsubscribe(a)googlegroups.com. >>>>> To post to this group, send email to scikit-image(a)googlegroups.com. >>>>> To view this discussion on the web, visit >>>>> https://groups.google.com/d/msgid/scikit-image/b9ede614-1c9d-4a22-a681-fab4… >>>>> <https://groups.google.com/d/msgid/scikit-image/b9ede614-1c9d-4a22-a681-fab4…> >>>>> . >>>>> >>>>> For more options, visit https://groups.google.com/d/optout. >>>>> >>>> >>>> -- >>>> 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/VtkzL9ZCY6Q/unsubscribe. >>>> To unsubscribe from this group and all its topics, send an email to >>>> scikit-image+unsubscribe(a)googlegroups.com. >>>> To post to this group, send email to scikit-image(a)googlegroups.com. >>>> To view this discussion on the web, visit >>>> https://groups.google.com/d/msgid/scikit-image/CAFCvXeMTH9ke7Cv%3DucywhtaWP… >>>> <https://groups.google.com/d/msgid/scikit-image/CAFCvXeMTH9ke7Cv%3DucywhtaWP…> >>>> . >>>> >>>> For more options, visit https://groups.google.com/d/optout. >>>> >>> >>> -- >>> 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/VtkzL9ZCY6Q/unsubscribe. >>> To unsubscribe from this group and all its topics, send an email to >>> scikit-image+unsubscribe(a)googlegroups.com. >>> To post to this group, send email to scikit-image(a)googlegroups.com. >>> To view this discussion on the web, visit >>> https://groups.google.com/d/msgid/scikit-image/CAD82iYrA%2BgP0K2zopnj8Cp_Jg… >>> <https://groups.google.com/d/msgid/scikit-image/CAD82iYrA%2BgP0K2zopnj8Cp_Jg…> >>> . >>> >>> For more options, visit https://groups.google.com/d/optout. >>> >> >> -- >> 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/VtkzL9ZCY6Q/unsubscribe. >> To unsubscribe from this group and all its topics, send an email to >> scikit-image+unsubscribe(a)googlegroups.com. >> To post to this group, send email to scikit-image(a)googlegroups.com. >> To view this discussion on the web, visit >> https://groups.google.com/d/msgid/scikit-image/CAFCvXePXM93QLh9PFO%2B9GZxTH… >> <https://groups.google.com/d/msgid/scikit-image/CAFCvXePXM93QLh9PFO%2B9GZxTH…> >> . >> >> For more options, visit https://groups.google.com/d/optout. >> > > -- > 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/VtkzL9ZCY6Q/unsubscribe. > To unsubscribe from this group and all its topics, send an email to > scikit-image+unsubscribe(a)googlegroups.com. > To post to this group, send email to scikit-image(a)googlegroups.com. > To view this discussion on the web, visit > https://groups.google.com/d/msgid/scikit-image/CAD82iYo%2BxaeFKMf6vzKe5xgn8… > <https://groups.google.com/d/msgid/scikit-image/CAD82iYo%2BxaeFKMf6vzKe5xgn8…> > . > > For more options, visit https://groups.google.com/d/optout. >

1 0

Re: blob detection and dust removal
by Vighnesh Birodkar 03 May '16

03 May '16

regionprops takes a labelled image as input. The question still remains, how will you generate the image in which the interested regions are labelled accordingly. You need to make that part of your algorithm exclude the dust particles. On Mon, May 2, 2016 at 3:34 PM, Raphael Okoye <raphael(a)aims.ac.za> wrote: > hi Vighnesh > > I plan to use this guy > http://scikit-image.org/docs/dev/auto_examples/plot_regionprops.html. The > documentation on regionprops ( > http://scikit-image.org/docs/dev/api/skimage.measure.html#regionprops) > says I can get parameters such as co-ordinate positions, equivalent > diameter etc > > But first I need to think of a way to exclude the dust particles, that is > the main challenge. > > Thanks > Raphael > > On 2 May 2016 at 02:30, Vighnesh Birodkar <vighneshbirodkar(a)gmail.com> > wrote: > >> How do you plan to find the position of the real crystals ? Maybe the >> function you will use to find the original crystals will take a mask >> argument ? >> >> On Mon, May 2, 2016 at 1:07 AM, Raphael Okoye <raphael(a)aims.ac.za> wrote: >> >>> hi Vighnesh, >>> >>> Further processing involves getting the size and positions of real >>> crystals (I want to use the positions to estimate the pair correlation >>> function and then using the pair correlation function to estimate the >>> structure factor) The image comes from a sequence of time lapse images. >>> There are dust particles of various sizes in the images so if they are not >>> eliminated, a false structure factor will be determined. The median filter >>> took care of the very little ones but didn’t work for the bigger ones. >>> >>> Thanks a lot. >>> >>> Raphael >>> >>> On 1 May 2016 at 21:27, Vighnesh Birodkar <vighneshbirodkar(a)gmail.com> >>> wrote: >>> >>>> Hi >>>> >>>> That really depends on your application. What's your motivation for >>>> removing these dust particles ? How are these images going to be processed >>>> further ? >>>> >>>> Thanks >>>> Vighnesh >>>> >>>> On Monday, May 2, 2016 at 12:13:27 AM UTC-4, Raphael wrote: >>>>> >>>>> hi Vighnesh, >>>>> >>>>> Thanks a bunch!! I see my error now. >>>>> >>>>> Actually that blob you detected a dust particle. Which operation >>>>> would you suggest to erase it? I tried morphological erosion but it doesn't >>>>> take it away. >>>>> >>>>> Thanks >>>>> Raphael >>>>> >>>>> On 1 May 2016 at 18:27, Vighnesh Birodkar <vighnesh...(a)gmail.com> >>>>> wrote: >>>>> >>>>>> Hello Raphael >>>>>> >>>>>> The error here is because the output of blob_doh in a numpy array of >>>>>> blobs, it is not an image meant for display. If you notice the example the >>>>>> blobs are being drawn separately inside the for loop. If no blobs are being >>>>>> detected, you can adjust the threshold. Lowering the threshold will make >>>>>> the function detect more blobs. It is clarified futher in the documentation >>>>>> >>>>>> http://scikit-image.org/docs/dev/api/skimage.feature.html#skimage.feature.b… >>>>>> >>>>>> I was able to detect one blob in your image with the default >>>>>> threshold value. See: >>>>>> >>>>>> https://gist.github.com/vighneshbirodkar/c16515126e648cf92f08d3319d3a023e >>>>>> >>>>>> Find the result attached. >>>>>> >>>>>> Thanks >>>>>> Vighnesh >>>>>> >>>>>> On Saturday, April 30, 2016 at 2:02:51 AM UTC-4, Raphael wrote: >>>>>> >>>>>>> hi folks, >>>>>>> >>>>>>> Got a problem removing dust and identifying blobs/crytals. Kindly >>>>>>> see my code below >>>>>>> >>>>>>> >>>>>>> from __future__ import division, print_function >>>>>>> import matplotlib.pyplot as plt >>>>>>> import numpy as np >>>>>>> from skimage import io, feature, color, measure, draw, img_as_float, >>>>>>> exposure >>>>>>> from skimage.filters.rank import median >>>>>>> from skimage.feature import blob_dog, blob_log, blob_doh >>>>>>> from skimage.morphology import disk >>>>>>> >>>>>>> #raw image >>>>>>> image_raw = >>>>>>> img_as_float((io.imread('/home/raphael/Documents/ScikitImage/Run >>>>>>> 4-2_00061cropped.tif'))) (RawImage.tif attached) >>>>>>> plt.imshow(image_raw) >>>>>>> >>>>>>> #converted to grayscale >>>>>>> >>>>>>> img_gray = >>>>>>> color.rgb2gray(io.imread('/home/raphael/Documents/ScikitImage/Run >>>>>>> 4-2_00061cropped.tif')) >>>>>>> plt.imshow(image_gray) >>>>>>> >>>>>>> >>>>>>> #applied median filter to take out small dust particles. But the big >>>>>>> dust particle on the top right corner still persists (see median1.png >>>>>>> attached) >>>>>>> img_filtered=median(img_gray,disk(10)) >>>>>>> plt.imshow(img_filtered) >>>>>>> >>>>>>> >>>>>>> #applied adapthist to make image more clearer (see adaptive.png) >>>>>>> >>>>>>> img_equalized=exposure.equalize_adapthist(img_filtered) >>>>>>> plt.imshow(img_equalized) >>>>>>> >>>>>>> #trying to detect the crystals/blobs. I followed the example here >>>>>>> http://scikit-image.org/docs/dev/auto_examples/features_detection/plot_blob… >>>>>>> But this gave an error. matplotlib was not happy with the data type >>>>>>> blobs_doh = blob_doh(img_equalized, max_sigma=30, threshold=.1) >>>>>>> plt.imshow(blobs_doh) >>>>>>> >>>>>>> My problems are: >>>>>>> >>>>>>> 1. I could not get the dust particle out especially the really big >>>>>>> one on the top right. How can I get it out? >>>>>>> >>>>>>> 2. I could not detect the crystals/blobs in the image using blob_doh >>>>>>> >>>>>>> Any ideas/suggestions is highly appreciated. Thank you! >>>>>>> >>>>>> -- >>>>>> 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/VtkzL9ZCY6Q/unsubscribe >>>>>> . >>>>>> To unsubscribe from this group and all its topics, send an email to >>>>>> scikit-image...(a)googlegroups.com. >>>>>> To post to this group, send email to scikit...(a)googlegroups.com. >>>>>> To view this discussion on the web, visit >>>>>> https://groups.google.com/d/msgid/scikit-image/0fd22d80-4549-470f-b61b-f48d… >>>>>> <https://groups.google.com/d/msgid/scikit-image/0fd22d80-4549-470f-b61b-f48d…> >>>>>> . >>>>>> >>>>>> For more options, visit https://groups.google.com/d/optout. >>>>>> >>>>> >>>>> -- >>>> 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/VtkzL9ZCY6Q/unsubscribe. >>>> To unsubscribe from this group and all its topics, send an email to >>>> scikit-image+unsubscribe(a)googlegroups.com. >>>> To post to this group, send email to scikit-image(a)googlegroups.com. >>>> To view this discussion on the web, visit >>>> https://groups.google.com/d/msgid/scikit-image/b9ede614-1c9d-4a22-a681-fab4… >>>> <https://groups.google.com/d/msgid/scikit-image/b9ede614-1c9d-4a22-a681-fab4…> >>>> . >>>> >>>> For more options, visit https://groups.google.com/d/optout. >>>> >>> >>> -- >>> 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/VtkzL9ZCY6Q/unsubscribe. >>> To unsubscribe from this group and all its topics, send an email to >>> scikit-image+unsubscribe(a)googlegroups.com. >>> To post to this group, send email to scikit-image(a)googlegroups.com. >>> To view this discussion on the web, visit >>> https://groups.google.com/d/msgid/scikit-image/CAFCvXeMTH9ke7Cv%3DucywhtaWP… >>> <https://groups.google.com/d/msgid/scikit-image/CAFCvXeMTH9ke7Cv%3DucywhtaWP…> >>> . >>> >>> For more options, visit https://groups.google.com/d/optout. >>> >> >> -- >> 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/VtkzL9ZCY6Q/unsubscribe. >> To unsubscribe from this group and all its topics, send an email to >> scikit-image+unsubscribe(a)googlegroups.com. >> To post to this group, send email to scikit-image(a)googlegroups.com. >> To view this discussion on the web, visit >> https://groups.google.com/d/msgid/scikit-image/CAD82iYrA%2BgP0K2zopnj8Cp_Jg… >> <https://groups.google.com/d/msgid/scikit-image/CAD82iYrA%2BgP0K2zopnj8Cp_Jg…> >> . >> >> For more options, visit https://groups.google.com/d/optout. >> > > -- > 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/VtkzL9ZCY6Q/unsubscribe. > To unsubscribe from this group and all its topics, send an email to > scikit-image+unsubscribe(a)googlegroups.com. > To post to this group, send email to scikit-image(a)googlegroups.com. > To view this discussion on the web, visit > https://groups.google.com/d/msgid/scikit-image/CAFCvXePXM93QLh9PFO%2B9GZxTH… > <https://groups.google.com/d/msgid/scikit-image/CAFCvXePXM93QLh9PFO%2B9GZxTH…> > . > > For more options, visit https://groups.google.com/d/optout. >

1 0