BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20270314T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20261106T151233Z
UID:B4873DB6-8282-4BE0-9B5A-7B19810AD9E0
DTSTART;TZID=America/New_York:20261120T130000
DTEND;TZID=America/New_York:20261120T143000
DESCRIPTION:Is AI ready to identify a faulty component\, pinpoint the probl
 em\, and run on a compact device such as a smart camera without human-inte
 rvention?\n\nThis talk presents two studies of industrial quality inspecti
 on. The first compares AI methods that rely on visual information with vis
 ion–language approaches that combine images and written descriptions\, e
 xamining accuracy\, reliability\, fault localization\, and computational r
 equirements. The second explores how written descriptions\, which can be g
 enerated using familiar AI tools such as ChatGPT and Perplexity AI\, can g
 uide the identification of faulty components without examples of faulty pr
 oducts or retraining the underlying model. Together\, these studies examin
 e AI’s inspection capabilities and the practical challenges of deploymen
 t on devices with limited computing resources.\n\nSpeaker(s): Atefeh Gilva
 ri\, \n\nRoom: 1118\, Bldg: Erie Hall\, 401 Sunset Avenue\, University of 
 Windsor\, Windsor\, Ontario\, Canada
LOCATION:Room: 1118\, Bldg: Erie Hall\, 401 Sunset Avenue\, University of W
 indsor\, Windsor\, Ontario\, Canada
ORGANIZER:moradiap@uwindsor.ca
SEQUENCE:28
SUMMARY:Vision–Language AI for Automated Manufacturing Quality Inspection
URL;VALUE=URI:https://events.vtools.ieee.org/m/591811
X-ALT-DESC:Description: &lt;br /&gt;&lt;p style=&quot;language: en-CA\; line-height: norm
 al\; text-align: left\; margin: 4.0pt .01in 4.0pt .01in\;&quot;&gt;&lt;span style=&quot;fo
 nt-size: 18pt\; font-family: Garamond\; color: rgb(0\, 0\, 0)\; font-weigh
 t: normal\; font-style: normal\;&quot;&gt;Is AI ready to identify a faulty compone
 nt\, pinpoint the problem\, and run on a compact device such as a smart ca
 mera without human-intervention? &lt;/span&gt;&lt;/p&gt;\n&lt;p style=&quot;language: en-CA\; 
 line-height: normal\; text-align: justify\; text-justify: inter-ideograph\
 ; margin: 4.0pt .01in 4.0pt .01in\;&quot;&gt;&lt;span style=&quot;font-size: 16pt\; font-f
 amily: Garamond\; color: rgb(0\, 0\, 0)\; font-weight: normal\; font-style
 : normal\;&quot;&gt;This talk presents two studies of industrial quality inspectio
 n. The first compares AI methods that rely on visual information with visi
 on&amp;ndash\;language approaches that combine images and written descriptions
 \, examining accuracy\, reliability\, fault localization\, and computation
 al requirements. The second explores how written descriptions\, which can 
 be generated using familiar AI tools such as ChatGPT and Perplexity AI\, c
 an guide the identification of faulty components without examples of fault
 y products or retraining the underlying model. Together\, these studies ex
 amine AI&amp;rsquo\;s inspection capabilities and the practical challenges of 
 deployment on devices with limited computing resources.&lt;/span&gt;&lt;/p&gt;
END:VEVENT
END:VCALENDAR

