Automated Optical Inspection and Defect Detection with Deep Learning

Event Type Start Time End Time
Presented via Webex 25 Nov 2020 - 2:00 PM GMT 25 Nov 2020 - 3:00 PM GMT

Overview

Automated inspection and defect detection are critical for high throughput quality control in production systems. They are widely adopted in many industries for detection of flaws on manufactured surfaces such as metallic rails, semiconductor wafers, contact lenses and so on.

Recent developments in deep learning have significantly improved our ability to detect defects. In this session, you will learn how to use MATLAB® to develop deep learning-based approaches to detect and localize different types of anomalies.

Highlights

  • Data access and preprocessing techniques including denoising, registration and intensity adjustment
  • Semantic segmentation and labeling of defects and abnormalities
  • Defect detection using MobileNetv2, Grad-CAM and other deep learning techniques
  • Deploying to multiple hardware platforms such as CPUs and GPUs

About the Presenter

Harshita Bhurat is the product manager for Image Processing and Computer Vision products. She has been at MathWorks for 8 years. In the past at MathWorks, she has managed the Robotics and Autonomous Systems and code generation products. Prior to joining MathWorks, Harshita was an embedded applications engineer at Broadcom, where she was a part of the team responsible for the development, integration, and deployment of Broadcom's High Definition ICs into turnkey Blu-ray and streaming service products. Harshita has over 15 years of experience in image and video processing and software for embedded systems. She holds a B.S. in computer engineering and M.S. in computer science from Illinois Institute of Technology, Chicago.

Agenda

Time Title

14:00

Welcome and Introduction

14:05

Automated Optical Inspection and Defect Detection with Deep Learning

14:40

Q&A

Product Focus

You are already signed in to your MathWorks Account. Please press the "Submit" button to complete the process.