Computer Vision with Python

Mastering Computer Vision with the Python programming Language

In this class you will learn how to build Computer Vision algorithms for Image classification and Object detection using the Python Programming Language. We will first go through Neural Networks Basics: what are Neural networks , what is the theory behind neural networks , then we will talk about binary classifiers like an SVM for classifying the MNIST datasets, Students will learn how to classify the hand written digits of the MNIST dataset into multiple classes. We will discuss the different types of edge detectors to detect edges in images. After this we will discuss convolutionnal neural networks: how are they built, what are the most common and efficient CNN architectures and how do you implement them in Python. The topic of Object detection and Exhaustive search will also be dealt with. The last part of the class will be an example application of building and training a custom built Convolutionnal neural Network on the cloud to classify images from an open source dataset. All the steps from getting data, reading the data , building the network and training the network on the cloud will be carefully explained so that the student has a working example to be able to reuse or modify for its own purpose.

What you’ll learn

  • Computer Vision.
  • Neural Networks.
  • Object detection.
  • Build and Train your own Computer Vision Model.

Course Content

  • Neural Networks Basics –> 5 lectures • 17min.
  • Predicting Digits with MNIST –> 3 lectures • 7min.
  • Edge Detectors –> 3 lectures • 3min.
  • Convolutionnal Neural networks –> 5 lectures • 14min.
  • Build and Train a Convolutionnal Neural network for classification –> 4 lectures • 22min.

Computer Vision with Python

Requirements

In this class you will learn how to build Computer Vision algorithms for Image classification and Object detection using the Python Programming Language. We will first go through Neural Networks Basics: what are Neural networks , what is the theory behind neural networks , then we will talk about binary classifiers like an SVM for classifying the MNIST datasets, Students will learn how to classify the hand written digits of the MNIST dataset into multiple classes. We will discuss the different types of edge detectors to detect edges in images. After this we will discuss convolutionnal neural networks: how are they built, what are the most common and efficient CNN architectures and how do you implement them in Python. The topic of Object detection and Exhaustive search will also be dealt with. The last part of the class will be an example application of building and training a custom built Convolutionnal neural Network on the cloud to classify images from an open source dataset. All the steps from getting data, reading the data , building the network and training the network on the cloud will be carefully explained so that the student has a working example to be able to reuse or modify for its own purpose.

Get Tutorial