answer - DENOISING PICTURES OF INSPECTED METALLIC SURFACES...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
DENOISING PICTURES OF INSPECTED METALLIC SURFACES TO IDENTIFY SURFACE DEFECTS . Tirthankar Dasgupta In industries where steel products are manufactured by some rolling or extrusion operation, it is not trivial to detect the presence of defects on the surface of the product. One such defect is called a ‘seam’, which is essentially a type of crack along the surface of the metal and can be discovered only when a specific test called a ‘hot upset test’ is performed. To perform this test, a sample piece of the product is pressed from two ends under high temperature and consequently there is a bulge at the middle (See figure-1). If there is a ‘seam’, it will be evident from a crack along that bulge. However, quite often experts receive pictures as an evidence of such tests but are unable to reach a conclusion owing to the high degree of noise in the picture. The Bayesian technique of de-noising using Ising priors can prove to be quite handy in such a scenario. FIGURE-1 : HOT UPSET TESTING
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 10/23/2011 for the course ISYE 8843 taught by Professor Vidakovic during the Spring '11 term at Georgia Institute of Technology.

Page1 / 4

answer - DENOISING PICTURES OF INSPECTED METALLIC SURFACES...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online