This document discusses machine vision and image analysis techniques used in various applications. It covers topics such as:
- Common applications of computer vision like marketing, social media profiling, and surveillance.
- How digital images and video are represented as arrays of pixels and numerical values.
- Image filtering techniques that apply mathematical functions to pixels in a neighborhood to modify images.
- Convolutional neural networks that use learned filters to extract features from images for tasks like image classification.
- Popular computer vision models like ImageNet and COCO that classify objects in images into hundreds of categories.
- Techniques for detecting and tracking objects in video, including people counting demos.
2. “Data Science” Applications
• Marketing
• Social media profiling
• Media coverage
• In-store behavior
• Digital asset management
• OCR
• Keyword tagging
• Face tagging
• Remote sensing
• DeepSolar
• Plant health
• Military
• Internet of things
• Surveillance
• Manufacturing
• Smart homes
3. What is a Digital Image? Video?
Abstractly
• 2-d array of pixels
• Pixels
• Number grayscale
• Triplet (e.g. RGB)
• N values
• Channels
Concretely
• File representations
• PNG, JPG, etc.
• MP4, MPEG, etc.
• Memory representations
• Row-major
• Column-major
• Integer, float, etc.
12. Deep Learning
Model training
• Learn weights (e.g. convolution
coefficients)
• Thousands/millions of examples
• Backpropagation
• Hours to days
Inference
• Model file + weight file
• Few MB to hundreds of MB
• Milliseconds to seconds
13. Image Classification
Class Probability
0-2 0.000011
4-6 0.000008
8-13 0.000187
15-20 0.001444
25-32 0.313656
38-43 0.683580
48-53 0.001012
60+ 0.000101
Age Classification