126 2 archive 5 disk0/00/00/01/26 2008-01-24 2009-06-22 11:44:50 2009-04-08 16:54:32 report show 0 Kuske Rachel Lyder David Samuel Jonathan Soteros Chris Wolfe David unpub food retail ipsw2 VisionSmart public The challenge was to find a reliable, non-intrusive means of detecting cracks in eggs. Intensity data from eggs were collected by VisionSmart for the group to analyse. Given the short time period three main questions were addressed. 1) Is there a feature of the intensity data which detects, and discriminates between pinholes, cage marks and cracks? 2) Are there ways to improve the current data collection process? 3) Are there other data collection methods which should be tried? A partial positive response to 1) is presented and describes the many problems that arose. Some answers to 2) and 3) are also presented. Eggs are prone to make deformities (cracks, pinholes, cage marks etc). It is not practical to manually 'candle' the eggs. One suggestion is to shine a narrow laser at the eggs and measure the resulting illumination. The problem is to devise an algorithm that takes this information and determines deformations. 1998-06-05 published 130 1 126 1 application/pdf en public

villetard.pdf

villetard.pdf 612966 http://www.maths-in-industry.org/miis/126/1/villetard.pdf