Mailman 3 June 2019 - scikit-image

ImageXD - Call for Participation
by Stefan van der Walt 12 Jun '19

12 Jun '19

Dear colleagues, The Berkeley Institute for Data Science at the University of California, Berkeley invites you to attend ImageXD, a 3-day conference designed to discuss common problems in image processing across domains, ranging from academic disciplines such as astronomy, radiology, and materials sciences to computer vision for social good. The philosophy behind ImageXD is to approach the intrinsic computer vision and image processing problems as one community, thereby sharing expertise and insight gained from one application area to other areas. The next ImageXD meeting will take place in September 9-11, 2019, on the UC Berkeley campus. More event info can be found on the ImageXD website: http://imagexd.org ImageXD applicants will be selected to participate on the basis of the applicants' research abstract, science picture, and bio submission. The top eligible submissions will be invited to speak at the event. Top science picture submissions will be featured on the event website. Hackathons and round-table discussions will also provide several opportunities to invent new image analysis algorithms, computer vision workflows, and reproducible research using public repositories of scientific images. Registration closes on June 28, 2019. Abstracts submitted before the registration deadline will receive full consideration. We look forward to your application! Stéfan on behalf of the ImageXD Organizers

1 0

scikit-image 0.14.3
by Mark Harfouche 12 Jun '19

12 Jun '19

Announcement: scikit-image 0.14.3 ================================= As a reminder, 0.14.x is the final version of scikit-image with support for Python 2.7, and will receive critical bug fixes until Jan 1, 2020. If you are using Python 3.5 or later, you should upgrade to scikit-image 0.15.x. This is a bugfix release, and contains the following changes from v0.14.2: API Changes ----------- - morphology.local_maxima now returns a boolean array instead of uint8 (#3749, #3752) Bug Fixes --------- - _marching_cubes_lewiner_cy: mark char as signed (#3587, #3678) - Fix potential use of NULL pointer (#3696) - pypi: explicitly exclude Python 3.1, 3.2, and 3.3 (#3726) - Reduce default tolerance in threshold_li (#3622) (#3781) - Denoising functions now accept float32 images (#3449) (#3486) (#3880) Other Pull Requests ------------------- - BLD: pin cython's language_level (#3716) - Build tools: Upgrade xcode to 9.4 on v0.14.x branch (#3724) - Get rid of the requirements-parser dependency (#3534, #3727) - Add small galleries in the API (#2940, #3728) - Correctly ignore release notes auto-generated for docs (#3656, #3737) - Fix qt 5.12 pinning for 0.14.x branch. (#3744, #3753) - Minor fixes to documentation and testing infrastructure - backports #3870 and #3869 (#3881) - Set astropy minimum requirement to 1.2 to help the CIs. (#3767, #3770) - Avoid NumPy warning while stacking arrays. (#3768, #3771) - Fix human readable error message on a bad build. (#3223, #3790) - Unify LICENSE files for easier interpretation (#3791, #3792) - Documentation formatting / compilation fixes - Backport of #3838 to v0.14.x (#3885) - Fix build by using latest ``wheel`` package (scikit-image/scikit-image-wheels#10) 12 authors added to this release [alphabetical by first name] ------------------------------------------------------------- - Andrew Murray - Christoph Gohlke - Egor Panfilov - François Boulogne - Johannes Schönberger - Juan Nunez-Iglesias - Lars Grueter - Mark Harfouche - Matthew Bowden - Nehal J Wani - Nelle Varoquaux - Stefan van der Walt - Thomas A Caswell ... and, as always, a special mention to Matthias Bussonnier's Meeseeks Box, which remains invaluable for our backports. 4 committers added to this release [alphabetical by first name or login] ------------------------------------------------------------------------ - Josh Warner - Juan Nunez-Iglesias - Mark Harfouche - Stefan van der Walt 5 reviewers added to this release [alphabetical by first name or login] ----------------------------------------------------------------------- - Egor Panfilov - François Boulogne - Juan Nunez-Iglesias - Mark Harfouche - Stefan van der Walt

1 0

Contributing to Scikit
by Clement Ng 06 Jun '19

06 Jun '19

Hello everyone, I'm new to scikit-image (and scientific programming in Python), and eventually want to try implementing one of the requested features. I am somewhat familiar with contributing to open source, so mentorship in regards to how I can build towards picking and implementing a full feature in this code base would be appreciated! Are there any resources I should look into or should I just start trying to submit PRs for beginner-friendly issues? Thanks, Clement Ng

2 1

Nofima/Berkeley postdoc position
by Stefan van der Walt 06 Jun '19

06 Jun '19

Nofima is searching for a postdoctoral candidate experienced in image analysis and machine learning for a project to improve sustainability and minimize waste in the seafood industry. The position is in Tromsø, Norway, which draws visitors around the world for hiking, skiing, climbing and the spectacular northern lights. At: Nofima Location: Tromsø, Norway Web: www.nofima.no Position: Postdoctoral Researcher About the position: Nofima, the Norwegian food research institute, is searching for a candidate for a three-year postdoctoral project from the fall of 2019 at their Tromsø location. The project is in conjunction with UC Berkeley and Lund University. Start date is negotiable. The position has an excellent work-life balance, five-weeks’ vacation, and participation in the state health care system. Tromsø draws visitors from around the globe for the world class hiking, skiing, kayaking and climbing (https://www.instagram.com/visittromso/?hl=en). For more information, please contact kate.washburn(a)nofima.no Project Description: Nearly half of all edible seafood is wasted due to real or perceived quality problems. Currently, seafood characterization is very qualitative, which hinders research. The project will use state of the art MRI methods to develop quantitative descriptors of fish tissue. In particular, newly developed diffusion tensor imaging methods will be used to describe tissue structure at multiple length scales. This information will be used to improve processing and storage methods to minimize waste and improve sustainability in the fishing industry. MRI data will be correlated with hyperspectral imaging data with the aim of developing high throughput screening techniques. Responsibilities: • Improving MRI data analysis methods • Use machine learning to relate MRI data to quality attributes • Joint analysis and interpretation of MRI, hyperspectral and wet lab data • Assisting in data acquisition • Incorporating developed methods into the DiPy toolbox for dissemination • Publishing results in relevant academic journals and presenting results at relevant conferences Qualifications: • Doctoral degree in computer science, machine learning, physics, or other relevant discipline • Experience in programming • Experience in machine learning, image analysis, and neural networks • Experience in magnetic resonance is desirable, but not required • Fluent in both written and spoken English. Knowledge of Norwegian not required • Position will require some travel, and includes an overseas stay at UC Berkeley and at Lund University

1 0

Post-doc in biomedical analysis (JAPAN)
by Image Analysis 05 Jun '19

05 Jun '19

Dear all, We have an opening for a post-doc in biomedical analysis. We highly support and encourage the usage of Python (and of course scikit-image). We are looking forward to hearing from you. Best, Henrik Details: The Brain Image Analysis Unit at the Center for Brain Science (CBS), RIKEN, Japan, seeks highly motivated individuals who will contribute to the development and implementation of image processing and image analysis techniques with a focus on brain image data. The work will be done in a highly interdisciplinary research group consisting of scientists from the neural-scientific and medical research fields. The Brain Image Analysis Unit integrates deep learning techniques into new algorithms to improve state-of-the-art processing and analysis of brain imaging data. Emphasis is placed on developing methods for image registration, image stitching, tracking of neurons and axon fiber bundles, detection, and segmentation of structures and denoising, enhancement, and visualization of images. CBS website: https://cbs.riken.jp/en/faculty/bia/ Lab website: http://bia.riken.jp/ About the unit and the project The Brain Image Analysis Unit develops new algorithms for the processing and analysis of multi-modal brain imaging data such as two-photon, bright-field microscopy images, and MRI. We are in close collaboration with scientists from the neural-scientific and medical research fields. As a member of the Brain/MINDS project, the unit analyzes image data of the brain of the common marmoset monkey to help better understand the structure and function of the primate brain. Artificial intelligence plays an important role in contemporary image analysis. In particular, machine learning techniques such as deep learning are indispensable for the automated analysis of large image data-sets. The Brain Image Analysis Unit contributes to this exciting new field by integrating deep learning techniques into new algorithms to improve state-of-the-art processing and analysis of brain imaging data. Emphasis is placed on developing methods for image registration, image stitching, tracking of neurons and axon fiber bundles, detection, and segmentation of structures and denoising, enhancement, and visualization of images. Job description The selected candidate will join the interdisciplinary Brain/MINDS project, and as a member of the unit will contribute to the development and implementation of image processing and image analysis techniques with a focus on (marmoset) brain image data. The work will be done in a highly interdisciplinary research group consisting of scientists from the neural-scientific and medical research fields. The emphasis is on developing cutting-edge technologies that improve current state-of-the-art and publishing high impact work in top-tier journals in order to build a substantial resume and strong international collaborations. Experiences in biomedical image analysis is an advantage but not a requirement. This job may be a great opportunity to apply knowledge and expertise from the computer vision and/or image processing field to new problems in the biomedical field. Location Wako-City (Kanto district, 2-1 Hirosawa, Wako, Saitama 351-0198). RIKEN is located in very close proximity to the northern part of Tokyo. http://www.riken.jp/en/access/wako-map/. The RIKEN campus is quite large and offers cafeterias, coffee shops, and a convenient store. From the nearest train station, it is only a 12 min train ride to the Ikebukuro-Station (Tokyo). The Ikebukuro-Station is a hub which connects many famous places in Tokyo, including Shinjuku (9 min train ride), Shibuya (18 min train ride) or Akihabara (19 min train ride). Many people prefer to avoid crowded streets and trains in their daily life and are living in close proximity to RIKEN. However, those who prefer living close to the nightlife and entertainment spots in Tokyo benefit from commuting out of the city in the morning, and returning in the evening (significantly less crowded than the other way around). Qualifications The candidate should have or be expecting to receive a Ph.D., by the time of employment, in related fields and have relevant research skills and experience in developing algorithms for the analysis/processing of biological/medical/neural images, computer vision, machine learning, deep learning, optimization, simulation, or similar fields, demonstrated by high-quality publications good English communication skills proficiency in a programming language (such as C++/Python/JS) good communication skills and ability to cooperate Application & Employment Start: October, 2019 (negotiable). For further details, please refer to the job posting URL https://cbs.riken.jp/en/careers/20190530_w19047_bia_r.html

2 1

[New feature]Optical flow algorithms
by Riadh Fezzani 04 Jun '19

04 Jun '19

Hi everyone, I released today the first version of pyimof <https://pyimof.readthedocs.io/en/stable/>: a personal project providing the implementation of two algorithms for the estimation of dense optical flow (TV-L1 and iLK, see the documentation for more details). If you think that such features could be of any interest for scikit-image, I would be happy to make some PRs for their integration. Best regards, Riadh.

2 1

Only a few days left to submit! -- 2019 John Hunter Excellence in Plotting Contest
by Nelle Varoquaux 03 Jun '19

03 Jun '19

Hi everybody, There are only a few days left to submit to the 2019 John Hunter Excellence in Plotting Contest! If you're interested in participating, note that you have until June 8th to prepare your submission. In memory of John Hunter, we are pleased to be reviving the SciPy John Hunter Excellence in Plotting Competition for 2019. This open competition aims to highlight the importance of data visualization to scientific progress and showcase the capabilities of open source software. Participants are invited to submit scientific plots to be judged by a panel. The winning entries will be announced and displayed at the conference. John Hunter’s family and NumFocus are graciously sponsoring cash prizes for the winners in the following amounts: - 1st prize: $1000 - 2nd prize: $750 - 3rd prize: $500 - Entries must be submitted by June, 8th to the form at https://goo.gl/forms/cFTB3FUBrMPfQ7Vz1 - Winners will be announced at Scipy 2019 in Austin, TX. - Participants do not need to attend the Scipy conference. - Entries may take the definition of “visualization” rather broadly. Entries may be, for example, a traditional printed plot, an interactive visualization for the web, or an animation. - Source code for the plot must be provided, in the form of Python code and/or a Jupyter notebook, along with a rendering of the plot in a widely used format. This may be, for example, PDF for print, standalone HTML and Javascript for an interactive plot, or MPEG-4 for a video. If the original data can not be shared for reasons of size or licensing, "fake" data may be substituted, along with an image of the plot using real data. - Each entry must include a 300-500 word abstract describing the plot and its importance for a general scientific audience. - Entries will be judged on their clarity, innovation and aesthetics, but most importantly for their effectiveness in communicating a real-world problem. Entrants are encouraged to submit plots that were used during the course of research or work, rather than merely being hypothetical. - SciPy reserves the right to display any and all entries, whether prize-winning or not, at the conference, use in any materials or on its website, with attribution to the original author(s). SciPy John Hunter Excellence in Plotting Competition Co-Chairs Hannah Aizenman Thomas Caswell Madicken Munk Nelle Varoquaux

1 0