JOB : PhD position - INRIA and SME company - Grenoble, France
Vision List Digest:
Article 11,
Volume 27, Issue 4
From: "Daniela Hall"
Post-Followup: submission@VISLIST.com
Name of the company: VIT S.A. , St. Egreve, France, 38120
Name of academic partner: Lear team, INRIA Rhone-Alpes, St. Ismier, France, 38334
TITLE:
Learning techniques for automatic defect classification of electronic
components on printed circuit boards (PCB)
Description of PhD position (collaboration between company and academic
partner (these CIFRE)):
Automated optical inspection (AOI) equipment market is defined as camera
based fully automated inspection systems that are used to inspect
printed circuit boards. VIT S.A. is a leading provider of such solutions
that enhance the yield of electronic assembly. By locating defects
quickly and precisely, PCB assembly manufacturers can efficiently and
economically fix, review and classify defects. In addition to defect
inspection, SMT inspection equipment is increasingly being used to
control and improve the production processes, thus providing value
through productivity and quality enhancements.
VIT's customers require 100% defect detection and classification rate
with a small false call rate within restricted cycle time. This is an
extremely challenging problem. Particular difficulties are high
variability of components and differences in manufacturing processes.
This thesis explores machine learning techniques in order to improve
defect detection and classification of VIT's inspection machines.
Research issues include reliable detection and classification of objects
presenting strong variabilities, learning techniques to improve
classification performance, data mining issues and processing time
optimisations.
The successful candidate holds a MSc in computer science, mathematics or
related engineering sciences. Training in computer vision and artificial
intelligence is a must. Excellent English language skills are
mandatory.This PhD position requires good programming skills in C++. The
candidate should take responsibility, be autonomous, and be sensitive to
the defect detection problems of AOI market. The mission is to transfer
newest technological findings for the benefit of the company's products.
The scholarship has a duration of 3 years with a brut income of 2000
Euros per month. Desired starting date: September to November 2008.
VIT S.A. employs 140 people situated on two sites in France, 1 in the
US, 1 in Singapore and 1 in Bulgaria. The R&D division is situated near
Grenoble in the French Alps. A global distribution network and
collaborations with known research institutions ensure ViTechnology's
position among the 3 top players in the SMT market world wide.
The LEAR project-team ( http://lear.inrialpes.fr
) is a research group
hosted by INRIA Grenoble - Rhône-Alpes Research Centre near Grenoble.
LEAR's research focuses on machine learning and statistical modelling
based approaches to visual object recognition, scene interpretation, and
image and video indexing. Understanding the content of everyday images
and videos is one of the major outstanding challenges of computer
vision. At present the extent to which we can do this is limited, but we
believe that significant advances will be made over the next few years
by combining emerging statistical learning techniques with state of the
art image descriptors, and this new capability will lead to a boom in
applications.
Application procedure and information request:
please send CV and cover letter to mailto:dhall@vitechnology.com
http://www.vislist.com