This project has created an experimental software platform, using the API of a commercial Crowdsourcing platform (Amazon's mechanical turk, http://mturk.com/), to support the systematic investigation of the system's performance for various types of CAD/CAM tasks.
Micro-outsourcing, or crowdsourcing, is a neologism for the act of taking a task traditionally performed by an employee or contractor,and outsourcing it to an undefined, generally large group of people, in the form of an open call [http://en.wikipedia.org/wiki/Crowdsourcing]. For example, the public may be invited to develop a new technology, carry out a design task, refine an algorithm or help capture, systematize or analyze large amounts of data. In MTurk these tasks are referred to as Human Intelligence Tasks (HITs). These are problems that humans find simple, but computers find extremely difficult. For example a HIT related to a photograph could be: "Is there a dog in this photograph?"
Recently the use of Crowdsourcing to deliver HITs has demonstrated a feasible way of providing cheap, robust, content based, Image analysis. This proposal's objective is to investigate if a similar approach can be used to solve the geometric reasoning problems found in Mechanical CAD/CAM.
|
Dr. Ananda Prasanna Jagadeesan Research Assistant, DMEM Strathclyde University Glasgow ananda.jagadeesan@strath.ac.uk |
Head of the Department, DMEM Strathclyde University Glasgow |
Mr. Jan Wanzel Edinburgh University Edinburgh |
|
Dr Andrew Lynn Online learning courseware developer, DMEM Strathclyde University Glasgow |
Dr. Xiu Yan Senior lecturer, DMEM Strathclyde University Glasgow |
Research Fellow, DMEM Strathclyde University Glasgow |
|
Dr. William Regli Drexel University Philadelphia , USA |
Dr. Andrew Sherlock ShapeSpace Ltd Edinburgh |
Crowdsourcing Canonical Views of 3D Models
Paper Virman
Validation of Purdue Engineering Shape Benchmark clusters by Crowdsourcing
Paper plm paper
Appendix plm0-appendix-A
PLM09 Conference presentation slides PLM09_ppt_Perdue_Crowdsourcing
Techrep08-01.pdf: "Feasibility Study for the “Crowdsourcing” of geometric reasoning in mechanical CAD", Jan Wenzel, 2008
http://en.wikipedia.org/wiki/Crowdsourcing
http://en.wikipedia.org/wiki/Mturk
http://en.wikipedia.org/wiki/Clickworkers
http://en.wikipedia.org/wiki/Galaxyzoo
http://gow.epsrc.ac.uk/ViewGrant.aspx?GrantRef=EP/F067291/1
CrowsdSourced HITs (under construction)
- Canonical views of parts
- Group most similar parts
- Cluster parts
-
Packing 2D shapes
a) Regular shapes
b) Irregular shapes
Additional similarity HIT Screenshot
