Introduction to Computer Vision with Convolutional Neural Networks


Date:  Tuesday, May 17 (Main Conference Day 1)

Start Time: 11:25 am

End Time: 12:30 pm

This presentation covers the basics of computer vision using convolutional neural networks. We will begin by introducing some important conventional computer vision techniques and then transition to explaining the basics of machine learning and convolutional neural networks (CNNs) and showing how CNNs are used in visual perception. We will illustrate the building blocks and computational elements of neural networks through examples. You will leave his session with a good overview of how modern computer vision algorithms are designed, trained and used in real-world applications.

Track

Session Speakers

  • Mohammad Haghighat is an engineering leader with over a decade of experience in artificial intelligence and computer vision. He has worked on a variety of projects in academia and industry using conventional CV/ML algorithms as well as deep neural networks. These include AI-based features for smart appliances and video analytics for surveillance systems. Mohammad has developed solutions for anomaly detection and prediction, image embedding and classification, object detection and tracking, face recognition, gender and age recognition from face and body images, privacy-preserving cloud-based biometric identification and multimodal biometrics. He earned his Ph.D. in ECE from the University of Miami, and has published numerous papers in international conferences.


Share

Introduction to Computer Vision with Convolutional Neural Networks