This document discusses deep convolutional neural networks and their many uses for computer vision. It provides an overview of computer vision, conventional computer vision techniques, and deep learning. It then describes the key components of convolutional neural networks, including convolutional layers, pooling layers, and fully connected layers. The document traces the evolution of convolutional neural networks from early models in 1980 to more recent state-of-the-art models from 2012 onward. It highlights several applications of convolutional neural networks like object detection, segmentation, recognition, style transfer, and image generation. In conclusion, the document demonstrates convolutional neural networks have many uses in computer vision tasks.
DBA Basics: Getting Started with Performance Tuning.pdf
Deep convolutional neural networks and their many uses for computer vision
1. Deep Convolutional Neural
Networks and their Many Uses
for Computer Vision
Dr. Fares Al-Qunaieer
Lead Data Scientist
Saudi Information Technology Company (SITE)
2. Computer Vision
A field to develop algorithms that make machines and
computers “understand” the content of images and videos
Machine
Learning
Image
Processing
Computer
Vision
7. Convolutional Neural Networks (ConvNets)
Image by Aphex34 - Own work, CC BY-SA 4.0, https://commons.wikimedia.org/w/index.php?curid=45679374
• Neural Networks with convolution layers (and some more)
• Learn best kernels/filters from data instead of manually selected
15. Neocognitron (1980)
K. Fukushima: "Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position", 1980
16. LeNet-5 (1998)
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition, 1998
17. AlexNet (2012)
Krizhevsky, Alex; Sutskever, Ilya; Hinton, Geoffrey E. "ImageNet classification with deep convolutional neural networks". 2012
18. VGG Net (2014)
Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." 2014
19. GoogleNet – Inception (2014)
C. Szegedy et al., "Going deeper with convolutions," 2015
20. ResNet (2016)
K. He, X. Zhang, S. Ren and J. Sun, " Deep Residual Learning for Image Recognition," 2016
22. Objects Detection and Localization
Images source: https://towardsdatascience.com/r-cnn-fast-r-cnn-faster-r-cnn-yolo-object-detection-algorithms-36d53571365e
YOLO (You Only Look Once)
Faster RCNN (Region Based CNN)
https://www.youtube.com/watch?v=MPU2HistivI
23. Objects Segmentation
V. Badrinarayanan, A. Kendall and R. Cipolla, "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation," 2017
Ronneberger, O., Fischer, P., & Brox, T. “U-Net: Convolutional
Networks for Biomedical Image Segmentation” 2015
24. Face Recognition (FaceNet)
F. Schroff, D. Kalenichenko and J. Philbin, "FaceNet: A unified embedding for face recognition and clustering," 2015
Image source: https://omoindrot.github.io/triplet-loss
25. Style Transfer
L. A. Gatys, A. S. Ecker and M. Bethge, "Image Style Transfer Using Convolutional Neural Networks," 2016
26. Image Generation - GAN (Generative Adversarial Network)
Image source: Goodfellow et al; Karras, Laine, Aila / Nvidia
27. Other Applications
• Scene labelling
• Action recognition
• Human Pose estimation
• Document analysis
• Medical diagnosis
• And many more …