A great Eye, lidless, wreathed in webcams.<\/p>\n
At Pumping Station: One (Chicago's Hackerspace) people often send\nmessages to the mailing list or ask on IRC if anyone is at the space or\nplans to be later. There's an opportunity there to solve problems\nautomatically rather than through human input. Member Eric Stein\ndesigned a Python \/ OpenCV based application (lidless) to monitor four\nvideo cameras in the space and offer a REST API, a web front end with\nhistorical graphs, and an IRC bot in the IRC channel to relay\ninformation about how busy the space is.<\/p>\n
This talk is a short demo of the application accompanied by motivations\nand high level archtechture breakdown. Following the demo\/archtechture\nI'll dive into the parts of the code that people are most interested in\nhearing about with Q&A.<\/p>\n","pubDate":"Thu, 10 Nov 2011 00:00:00 +0000","guid":"tag:pyvideo.org,2011-11-10:\/chipy\/lidless-video-analyzer-and-irc-bot.html","category":["ChiPy","image analysis"]},{"title":"SimpletITK: Advanced Image Analysis for Python","link":"https:\/\/pyvideo.org\/scipy-2014\/simpletitk-advanced-image-analysis-for-python.html","description":"
SimpleITK brings advanced image analysis capabilities to Python. In\nparticular, it provides support for 2D\/3D and multi-components images\nwith physical. SimpleITK exposes a large collection of image processing\nfilters from ITK, including image segmentation and registration.\nSimpleITK is freely available as an open source package under the Apache\n2.0 License.<\/p>\n
SimpleITK provides scientific image analysis, processing, segmentation\nand registration for biomedical, microscopy and other scientific fields\nby supporting multi-dimensional images with physical locations [1]. It's\nis a layer build upon the Insight Segmentation and Registration Toolkit\n(ITK) [2].<\/p>\n
While there are many Python packages to process 2D photographic images,\nscientific image analysis adds additional requirements. Images\nencountered in these domains often have anisotropic pixel spacing, or\nspatial orientations, and calculations are best performed in physical\nspace as opposed to pixel space.<\/p>\n
SimpleITK brings to Python a plethora of capabilities for performing\nimage analysis. Although SimpleITK was developed by the biomedical\nimaging community, it is also used for generic image processing. It\ndifferentiates from OpenCV in offering 3D images and multi-component\nimages, and it differentiates from scipy by offering the abstraction of\nimage classes and their associated data structures. This applies to\nimages modalities such as CT scans, MRI, fMRI, ultrasound, and in\nmicroscopy modalities such as confocal, SEM, TEM, and traditional bright\nand dark field.<\/p>\n
Among the key functionalities supported by SimpleITK are over 260\nadvanced image filtering and segmentation algorithms as well as access\nto scientific image file formats, including specialized formats such as\nDICOM, Nifti, NRRD, VTK and other formats that preserve 3D metadata.\nExample algorithms include Level Sets Segmentation including\nmulti-phase, Label Maps, Region Growing, Statistical Classification,\nAdvanced Thresholding, Geometrical Transformations, Deconvolution,\nAnti-Aliasing, Edge Detection, Mathematical Morphology on both labels\nand grayscale images and Fourier Analysis [4,5].<\/p>\n
SimpleITK is an open source project with an active community, that\nbuilds upon the large amount of image analysis experience of the ITK\ncommunity [3] working in biomedical images analysis since 1999, and that\ncontinues to grow year by year, aggregating state of the art algorithms\n.<\/p>\n
SimpleITK development is sponsored by the US National Library of\nMedicine.<\/p>\n","pubDate":"Mon, 14 Jul 2014 00:00:00 +0000","guid":"tag:pyvideo.org,2014-07-14:\/scipy-2014\/simpletitk-advanced-image-analysis-for-python.html","category":["SciPy 2014","image analysis"]}]}}