Object Recognition: Deep Learning and Machine Learning for Computer Vision

Object recognition is enabling innovative systems like self-driving cars, image based retrieval, and autonomous robotics. The machine learning and deep learning these systems rely on can be difficult to train, evaluate, and compare. In this webinar we explore how MATLAB addresses the most common challenges encountered while developing object recognition systems. This webinar will cover new capabilities for deep learning, machine learning and computer vision. We will use real-world examples to demonstrate: - Training models using large image datasets - Training deep neural networks from scratch - Using transfer learning to re-use trained deep networks for new tasks - Exploring the tradeoffs between machine learning and deep learning Related Resources: - What is Computer Vision? https://bit.ly/3NDmjbc - Get the example code used in this video: https://bit.ly/3VnTTZP Chapters: 0:00 What is object recognition and when do I want to use it? 0:31 Demo #1: Scene Classification 0:43 The Machine Learning Workflow for Object Recognition 6:46 Classification Learner App for experimentation with different machine learning algorithms 9:00 Export an object recognition model from the Classification Learner App 10:27 Demo #1 Takeaways 11:22 The Deep Learning Workflow for Object Recognition 12:45 Demo #2: Fine-tune a pre-trained deep learning model (transfer learning) 18:00 Visualizing and removing mis-identified images from training data 19:06 Transfer Learning 19:53 Real-world object recognition with the transfer learned model and a deployable video player 20:30 Demo #2 Takeaways 21:36 Demo #3: Deep Learning and Machine Learning combined approach for object recognition 25:03 Demo #3 Conclusion 25:13 Machine Learning vs. Deep Learning object recognition overall comparison -------------------------------------------------------------------------------------------------------- Get a free product trial: https://goo.gl/ZHFb5u Learn more about MATLAB: https://goo.gl/8QV7ZZ Learn more about Simulink: https://goo.gl/nqnbLe See what's new in MATLAB and Simulink: https://goo.gl/pgGtod © 2024 The MathWorks, Inc. MATLAB and Simulink are registered trademarks of The MathWorks, Inc. See www.mathworks.com/trademarks for a list of additional trademarks. Other product or brand names may be trademarks or registered trademarks of their respective holders.