
UdemyPrice
No active coupon right now
View Course →No coupon right now. We'll tell you when there is one.
Mark your own learning status. Opening a course link does not establish enrollment.
Loading saved status…
This course is a broad survey of computer vision, built around 14 main techniques. It moves from classic tools such as face detection and object tracking to neural approaches including convolutional networks, transfer learning, YOLO and GANs.
Each technique is implemented step by step in Python, with the work done in Google Colab. The description positions it as a practical overview rather than a deep specialisation: by the end you should have tried each area, not mastered one.
The creative techniques, such as style transfer and Deep Dream, sit alongside the analytical ones, so the course covers both ends of the field.
Computer Vision is a subarea of Artificial Intelligence focused on creating systems that can process, analyze and identify visual data in a similar way to the human eye. There are many commercial applications in various departments, such as: security, marketing, decision making and production. Smartphones use Computer Vision to unlock devices using face recognition, self-driving cars use it to detect pedestrians and keep a safe distance from other cars, as well as security cameras use it to identify whether there are people in the environment for the alarm to be triggered.
In this course you will learn everything you need to know in order to get in this world. You will learn the step-by-step implementation of the 14 (fourteen) main computer vision techniques. If you have never heard about computer vision, at the end of this course you will have a practical overview of all areas. Below you can see some of the content you will implement:
Detect faces in images and videos using OpenCV and Dlib libraries
Learn how to train the LBPH algorithm to recognize faces, also using OpenCV and Dlib libraries
Track objects in videos using KCF and CSRT algorithms
Learn the whole theory behind artificial neural networks and implement them to classify images
Implement convolutional neural networks to classify images
Use transfer learning and fine tuning to improve the results of convolutional neural networks
Detect emotions in images and videos using neural networks
Compress images using autoencoders and TensorFlow
Detect objects using YOLO, one of the most powerful techniques for this task
Recognize gestures and actions in videos using OpenCV
Create hallucinogenic images using the Deep Dream technique
Combine style of images using style transfer
Create images that don't exist in the real world with GANs (Generative Adversarial Networks)
Extract useful information from images using image segmentation
You are going to learn the basic intuition about the algorithms and implement some project step by step using Python language and Google Colab
Advertisement
Tracking since 15 Nov — not enough history yet to tell you whether today's price is any good. Watch the course and we'll tell you when it drops.
This is what we recorded in US pricing — not every price this course has ever had, and prices differ by country.
No Korshub reviews yet.