Vision AI Efforts in Attribute Detections and Measurements explores how computer vision and machine learning can be applied in real-world manufacturing environments to improve quality assurance and dimensional verification without disrupting existing workflows.
This session is divided into two applied case studies. The first focuses on attribute detection, where Vision AI is used to automatically identify image quality issues as well as wrong or missing visual attributes in production images. Attendees will see how these models helped standardize inspections across multiple facilities, reduced manual review effort, and increased confidence in downstream decision-making by ensuring only usable, high‑quality images were processed further. Real production examples will be shared to illustrate how attribute‑level visibility directly impacted quality outcomes.
The second case study covers vision‑based measurements, highlighting work done to measure screen door dimensions directly from images. By combining machine learning predictions with computer vision techniques, the system was able to estimate key dimensions within tight tolerances and flag out‑of‑spec components before packaging. Results from production testing including accuracy ranges and practical limitations will be discussed.
The talk emphasizes results, lessons learned, and business impact, rather than implementation details. The format is presentation‑driven with visual examples, measurement outcomes, and discussion prompts designed to encourage audience engagement around where Vision AI delivers value - and where it still struggles - in industrial settings.
Use with AI
Copy this session's complete context to paste into ChatGPT, Claude, or any AI assistant.
Preview context block
## Session: Vision AI Efforts in Attribute Detections and Measurements **Track:** Production and Operations | **Time:** 3:10 PM–3:55 PM | **Room:** 275 | **Type:** Success Story **Conference:** CIRAS AI Summit for Iowa — May 6, 2026, Scheman Building, Iowa State University, Ames IA ### Speaker(s) **Vijay Kalivarapu** — Vision AI Efforts in Attribute Detections and Measurements, Pella Corporation (Pella, IA) Vijay Kalivarapu has a Ph.D. majoring in Mechanical Engineering and co-majoring in Human-Computer Interaction from Iowa State University. He is currently a Senior Artificial Intelligence Engineer at Pella Corporation, based in Pella, Iowa, where he applies computer vision and machine learning to manufacturing quality and measurement challenges. His work focuses on vision‑based image quality assessment, wrong and missing attribute detection, and dimensional measurements in production environments. Vijay has led multiple industrial Vision AI initiatives that emphasize scalable deployment, measurable accuracy, and business impact. In this session, he shares results, lessons learned, and practical insights from applying Vision AI to real manufacturing problems that highlight where these approaches deliver value and where limitations remain. ### Session Description Vision AI Efforts in Attribute Detections and Measurements explores how computer vision and machine learning can be applied in real-world manufacturing environments to improve quality assurance and dimensional verification without disrupting existing workflows. This session is divided into two applied case studies. The first focuses on attribute detection, where Vision AI is used to automatically identify image quality issues as well as wrong or missing visual attributes in production images. Attendees will see how these models helped standardize inspections across multiple facilities, reduced manual review effort, and increased confidence in downstream decision-making by ensuring only usable, high‑quality images were processed further. Real production examples will be shared to illustrate how attribute‑level visibility directly impacted quality outcomes. The second case study covers vision‑based measurements, highlighting work done to measure screen door dimensions directly from images. By combining machine learning predictions with computer vision techniques, the system was able to estimate key dimensions within tight tolerances and flag out‑of‑spec components before packaging. Results from production testing including accuracy ranges and practical limitations will be discussed. The talk emphasizes results, lessons learned, and business impact, rather than implementation details. The format is presentation‑driven with visual examples, measurement outcomes, and discussion prompts designed to encourage audience engagement around where Vision AI delivers value - and where it still struggles - in industrial settings. ### Other sessions in the Production and Operations track - Natural Language Search for Member Benefits (3:10 PM–3:55 PM) - Industrial AI Success Stories: Because Even My Title Needed Machine Learning (10:20 AM–11:05 AM) - Tabular Foundation Models Meet Manufacturing: A Practical Exploration (11:15 AM–12:00 PM) - AI Attribute Intelligence: Automating Detection, Extraction, and Standardization at Scale (1:20 PM–2:05 PM) ### Suggested prompts for this session - "What questions should I prepare to ask the speaker(s) at this session?" - "Create a structured note-taking template for this session focused on actionable takeaways" - "Based on this session description, what background reading should I do to get the most value?" - "After I attend, help me create an action plan for implementing what I learned" - "How does this session connect to the other sessions in the Production and Operations track?"