Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Computer Vision - CNN for image classification

Computer Vision - CNN for image classification

One of the most important uses of self-driving automobiles is image categorization.

Where the semi and completely autonomous car industries are rapidly expanding, we now see self-driving cars from the likes of Tesla and Kia moving around everywhere.

We will be exploring the technology behind this and how computers see and classify images, from understanding waste types to identifying humans on the road against inanimate objects and signs.

We will build a traffic sign classification model using CNN.

Wale Ayandiran

June 08, 2022
Tweet

More Decks by Wale Ayandiran

Other Decks in Technology

Transcript

  1. Computer Vision -
    CNN for Image
    Classification
    by Wale Ayandiran
    Presented at AI Wales meetup, Tramshed Tech, Cardiff.
    08-06-2022

    View full-size slide

  2. We might start by identifying certain pictures of animals
    ourselves. Shall we?
    How does computer identify images
    with their labels?

    View full-size slide

  3. Can you tell these wild cats aparts?

    View full-size slide

  4. Leopard Cheetah
    Jaguar Tiger
    Image credit: Google

    View full-size slide

  5. Machine
    Learning

    View full-size slide

  6. Lion Cat
    Wolf
    Dog
    Fox

    View full-size slide

  7. Cat Lion
    Dog
    Arctic Fox
    Wolf
    Image credit: Google

    View full-size slide

  8. How are we as
    humans able to
    differentiate things
    easily?

    View full-size slide

  9. Recognizing Patterns
    How are we as humans able to
    differentiate things easily?

    View full-size slide

  10. Credit: MIT
    Feature Detection
    Low level feature detection to high level feature detection

    View full-size slide

  11. What do computers see?

    View full-size slide

  12. Images are matrix of
    numbers

    View full-size slide

  13. Images are matrix of numbers What computers see

    View full-size slide

  14. Images are matrix of numbers
    What computers see
    Credit: https://openframeworks.cc/ofBook/chapters/image_processing_computer_vision.html

    View full-size slide

  15. Credit: https://www.keithbcarter.com/think-differently/how-a-machine-sees
    Computer detects features of an image as matrix of
    numbers.

    View full-size slide

  16. How do we make computers
    identify images?
    Neural Networks.
    Neural networks are computing
    systems with interconnected nodes
    that work much like neurons in the
    human brain. Using algorithms, they
    can recognize hidden patterns and
    correlations in raw data, cluster and
    classify it, and – over time –
    continuously learn and improve.
    Credit: https://www.sas.com/en_us/insights/analytics/neural-networks.html

    View full-size slide

  17. A simple neural network includes an
    input layer, an output (or target) layer
    and, in between, a hidden layer. The
    layers are connected via nodes, and
    these connections form a “network” –
    the neural network – of interconnected
    nodes.
    How Neural Network Works
    Credit: https://www.sas.com/en_us/insights/analytics/neural-networks.html

    View full-size slide

  18. ● Artificial Neural Network (ANN)
    ● Convolutional Neural Network (CNN)
    ● Recurrent Neural Network (RNN)
    3 Popular Neural Networks

    View full-size slide

  19. Convolutional
    Neural Networks

    View full-size slide

  20. Learning Visual Features
    ➔ Filter extraction
    Applying filters and generating
    smaller pieces of image from the
    original image.
    ➔ Features Mapping
    Using the filters extracted to
    create a feature map of the
    image.

    View full-size slide

  21. Image credit: MIT

    View full-size slide

  22. Tiger
    Tiger’s eyes ? = Y
    Tiger’s nose ? = Y
    Tiger’s mouth/whiskers ? = Y
    Tiger’s paws ? = Y
    Tiger’s tail ? = Y
    Tiger’s head ? = Y
    Tiger’s body ? = Y
    Is it a Tiger ? = Y
    Image credit: Google

    View full-size slide

  23. Main parts of a CNN
    Three main parts to a CNN
    ➔ Convolution
    Application of filters to generate feature
    maps
    ➔ Non-linearity (ReLU)
    Replacing negative values with zero (0)
    often ReLU (Rectified Linear Unit)
    ➔ Pooling
    Reduces dimensions and distortions,
    making the model tolerant towards
    image variations.

    View full-size slide

  24. Feature Extraction Classification
    Image credit: codebasics

    View full-size slide

  25. Some limitations of CNN
    in Image classification
    ❏ Requires large datasets to train
    ❏ Can take a lot of time to train if there are several layers
    ❏ Can be computing power intensive.

    View full-size slide

  26. A CNN model to identify traffic signs
    https:/
    /bit.ly/traffic_cnn

    View full-size slide

  27. Thank You!
    Find slide and code link below
    Demo link:
    https:/
    /bit.ly/traffic_cnn
    Github
    https:/
    /github.com/waleCloud/solid-fortnight

    View full-size slide

  28. Wale Ayandiran.
    Software and AI Engineer.
    Find me at https://walecloud.me
    Twitter @walecloud

    View full-size slide