Mailman 3 June 2016 - scikit-image

Haarcascades implementation
by Abdeali Kothari 13 Jun '16

13 Jun '16

Hi, I recently switched from opencv to skimage as I found it much more pythonic and easier to install. There is one feature which I seem to be missing - The Haarcascades and CascadeClassifier[1]. Is there plan to add this in skimage ? I'm quite new to haarcascades, but my understanding is that first there are HAAR features that are found from the image and then these features are classified using multiple weak classifiers (using adaboost) to "detect" an object. It seems to me that to get this functionality I would need skimage (to create the haar features) and sklearn (for the adaboost setup). I found issues/1431[2] which seems to talk about creating HAAR features. Am I on the right track ? Is there already some example code available which uses skimage and sklearn using one of the haarcascadde xml files provided by opencv ? Regards, Abdeali JK [1] - http://docs.opencv.org/master/d7/d8b/tutorial_py_face_detection.html#gsc.ta… [2] - https://github.com/scikit-image/scikit-image/issues/1431

2 3

Segmentation Fault when running Censure demo
by michael.obrien＠ul.ie 12 Jun '16

12 Jun '16

Hi all, I've new to computer vision and I hope you don't mind helping me out. I was interested in trying the demo http://scikit-image.org/docs/dev/auto_examples/features_detection/plot_cens… so I downloaded the notebook and py script. Im running on Ubuntu 14.04 and python 2.7.6. *Some background:* To install scikit-image I needed to install Cython and update pip. I had previously used the apt-get install method but it reported scikit-image version as 0.9 and couldn't find the CENSURE module or the astronaut data when I tried to run the notebooks so I removed that and used cython -> pip install (after upgrading pip) When I run the notebook I am notified the kernel needs to be restarted and when I run the py script I get the following michael@michael-VirtualBox:~/Downloads$ python plot_censure.py Traceback (most recent call last): File "plot_censure.py", line 11, in <module> from skimage import data File "/usr/local/lib/python2.7/dist-packages/skimage/data/__init__.py", line 12, in <module> from ..io import imread, use_plugin File "/usr/local/lib/python2.7/dist-packages/skimage/io/__init__.py", line 7, in <module> from .manage_plugins import * File "/usr/local/lib/python2.7/dist-packages/skimage/io/manage_plugins.py", line 28, in <module> from .collection import imread_collection_wrapper File "/usr/local/lib/python2.7/dist-packages/skimage/io/collection.py", line 14, in <module> from ..external.tifffile import TiffFile File "/usr/local/lib/python2.7/dist-packages/skimage/external/tifffile/__init__.py", line 1, in <module> from .tifffile import imsave, imread, imshow, TiffFile, TiffWriter, TiffSequence File "/usr/local/lib/python2.7/dist-packages/skimage/external/tifffile/tifffile.py", line 153, in <module> from . import _tifffile RuntimeError: module compiled against API version a but this version of numpy is 9 Segmentation fault (core dumped) When I run import numpy inumpy.__version__ '1.8.2'

2 1

Fwd: [scikit-learn] EuroSciPy 2016 Call for Papers Extended
by Nelle Varoquaux 08 Jun '16

08 Jun '16

This email may be of interest! ---------- Forwarded message ---------- From: federico vaggi <vaggi.federico(a)gmail.com> Date: 8 June 2016 at 01:43 Subject: [scikit-learn] EuroSciPy 2016 Call for Papers Extended To: Scikit-learn user and developer mailing list <scikit-learn(a)python.org> Hi everyone, The call for contributions (talks, posters, sprints) is still open until June 24th. EuroSciPy 2016 takes place in Erlangen, Germany, from the 23 to the 27 of August and consists of two days of tutorials (beginner and advanced tracks) and two days of conference representing many fields of science, with a focus on Python tools for science. A day of sprints follows (sprints TBA). The keynote speakers are Ga?l Varoquaux (you might have heard of him) and Abby Cabunoc Mayes and we can expect a rich tutorial and scientific program! Videos from previous years are available at https://www.youtube.com/playlist?list=PLYx7XA2nY5GeQCCugyvtnHMVLdhYlrRxH and https://www.youtube.com/playlist?list=PLYx7XA2nY5Gcpabmu61kKcToLz0FapmHu We are particularly eager to receive proposals from newcomers. EuroSciPy is a very welcoming conference, and we are very curious to hear how you use Python/machine learning in your every day research. Visit us, register and submit an abstract on our website! https://www.euroscipy.org/2016/ SciPythonic regards, The EuroSciPy 2016 team _______________________________________________ scikit-learn mailing list scikit-learn(a)python.org https://mail.python.org/mailman/listinfo/scikit-learn

1 0

PhD position in Bioimage Informatics at Mines ParisTech / Institut Curie, Paris, France
by Thomas Walter 08 Jun '16

08 Jun '16

PhD position in Bioimage Informatics at Mines ParisTech / Institut Curie, Paris, France Title: Machine Learning for Multi-cell-line Drug Screening Duration: 3 years Starting date: October 2016 Description: The objective of drug screening is to identify new molecules active against diseases, such as cancer. For this, a large number (typically hundreds or thousands) of experiments are performed on a cell line, which is supposed to be representative for the disease. In High Content Screening, the readout consists in images: for each individual drug, the effect is measured by fluorescence microscopy, giving thus a comprehensive description of the cellular phenotypes induced by the drug exposure. Such data sets are therefore large and complex and typically challenging to analyze. The traditional way of scoring for drug effects from images can be divided into five steps [1]: (1) image segmentation (identification of cells and cellular compartments); (2) feature extraction for each individual cell; (3) classification of single cells into phenotypic classes (such as cell death, mitosis, interphase, etc.); (4) description of the population phenotype (e.g. the percentage of cells in each phenotypic class); and (5) analysis of phenotypic similarities between different drug exposures based on the phenotypic profiles, e.g. by clustering approaches. This family of workflows has been successfully applied to large-scale screens [2], [3] in the past. In this PhD thesis, we want to explore new methods for the analysis of such data sets, applicable in the case where multiple cell lines with potential different basic properties are screened against large drug panels. References [1] T. Walter, M. Held, B. Neumann, J.-K. Hériché, C. Conrad, R. Pepperkok, and J. Ellenberg, “Automatic identification and clustering of chromosome phenotypes genome wide RNAi screen by time-lapse imaging”, J. Struct. Biol., vol. 170, no. 1, pp. 1–9, Apr. 2010. [2] Z. E. Perlman, M. D. Slack, Y. Feng, T. J. Mitchison, L. F. Wu, and S. J. Altschuler, “Multidimensional drug profiling by automated microscopy”, Science, vol. 306, no. 5699, pp. 1194–8, Nov. 2004. [3] L. Loo, L. F. Wu, and S. J. Altschuler, “Image-based multivariate profiling of drug responses from single cells”, Nat. Methods, vol. 4, no. 5, pp. 445–453, 2007. Candidate profile: The candidate should have a strong background in image analysis, computer vision and/or machine learning. Basic knowledge in biology and/or bioinformatics is an advantage, but not a requirement. Good interdisciplinary communication skills and a fundamental interest in biological and medical applications are expected. The project also involves a fair amount of programming (ideally in Python or R). Application Applications should be addressed to Thomas.Walter(at)mines-paristech.fr, and should contain a CV, a motivation letter, degrees and grades and any further useful information. Working Environment The project will take place at the Centre for Computational Biology (CBIO — http://cbio.ensmp.fr) under the supervision of Thomas Walter ( http://cbio.ensmp.fr/~twalter) and in collaboration with the Reyal group at the Institut Curie. The CBIO is a research center of Mines ParisTech, an important French engineering school, and is directed by Jean-Philippe Vert ( http://cbio.ensmp.fr/~jvert). The main topic is machine learning, applied to problems in biology. There is also an official partnership with the Curie Institute, a major hospital and research facility dedicated to cancer. Both the Curie Institute and the Centre for Computational Biology are situated in the heart of Paris, in an exciting and scientifically stimulating environment.

1 0

ImportError: No module named skimage.io
by Georgios Samaras 03 Jun '16

03 Jun '16

I am trying to do this: sudo pip install -U scikit-image but I am getting: Cleaning up... Exception: Traceback (most recent call last): File "/usr/lib/python2.7/dist-packages/pip/basecommand.py", line 122, in main status = self.run(options, args) File "/usr/lib/python2.7/dist-packages/pip/commands/install.py", line 278, in run requirement_set.prepare_files(finder, force_root_egg_info=self.bundle, bundle=self.bundle) File "/usr/lib/python2.7/dist-packages/pip/req.py", line 1091, in prepare_files req_to_install.check_if_exists() File "/usr/lib/python2.7/dist-packages/pip/req.py", line 811, in check_if_exists self.satisfied_by = pkg_resources.get_distribution(self.req) File "/usr/local/lib/python2.7/dist-packages/pkg_resources/__init__.py", line 535, in get_distribution dist = get_provider(dist) File "/usr/local/lib/python2.7/dist-packages/pkg_resources/__init__.py", line 415, in get_provider return working_set.find(moduleOrReq) or require(str(moduleOrReq))[0] IndexError: list index out of range Storing debug log for failure in /home/gsamaras/.pip/pip.log -------------------------------------------------------------------------------------------------------------------------------------------------------- How to fix this? For more, see this SO question <https://stackoverflow.com/questions/37623259/unable-to-import-caffe>.

1 1