Overview
Dive into the second part of a deep facial recognition application tutorial series. Learn how to collect and prepare data for training a deep learning model using TensorFlow, based on the Siamese Neural Networks for One-shot Image Recognition paper. Explore techniques for gathering negative images from Labeled Faces in the Wild dataset, resizing OpenCV output frames for image collection, and capturing positive and anchor images. Follow along with step-by-step instructions on accessing webcam feeds, adjusting frame sizes, and saving images for your facial recognition project. Gain practical insights into building a robust dataset for developing an authentication system using deep learning and computer vision techniques.
Syllabus
- Start
- What's Covered
- Whiteboard Session
- Collect LFW Data
- Moving Images
- Access Webcam with OpenCV
- Changing OpenCV Frame Size
- Saving Images
- Wrap Up
Taught by
Nicholas Renotte