~/lightning

Lightning Talk: Demystifying Challenges/Learnings in Converting an Old-school Textile Inspection Machine into a Smart System Using AI/ML

links:none on file
slides:none on file

Converted an old textile inspection rig into a working AI line that captures fabric at four pixels per mm² using a Basler camera + Pylon pipeline, trains with TensorFlow/Keras and OpenVINO, and runs inference at about 30 FPS on an Advantech IPC Core i5. Binary defect detection hits ~99% accuracy; multiclass labeling fails and models break on darker or patterned fabrics, folds, and higher motor speeds. Hardware fixes include an Arduino relay interface (would recommend a PLC) and region-specific SSD/network compatibility workarounds.

AI-written summary · about

  1. 0:00Introduction
  2. 0:34Project Objective
  3. 0:53Hardware Design
  4. 5:18Software Design
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.