Danh mục
Duocmmo Tedu Tin học văn phòng Laravel Cyberlearn Khoá học miễn phí Tất cả khoá học
Get link khoá học
Trang chủ
Development
Data Science
Computer Vision
Computer Vision Masterclass

Computer Vision Masterclass

Loại khoá học: Data Science

Learn in practice everything you need to know about Computer Vision! Build projects step by step using Python!

image
50.000 VND
90 VND
Đầy Đủ Bài Giảng
Học Online Tiện Lợi
Kích Hoạt Nhanh 2-5 Phút
Thanh toán tự động
Được phép tải xuống

Tổng quan

Nội dung khoá học

Đánh giá

Mô tả

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

Bạn sẽ học được gì

Yêu cầu

Nội dung khoá học

17 sections

Introduction

2 lectures
Course content
12:05
Google Drive folder
00:07

Face detection

18 lectures
Plan of attack
04:01
Images and pixels
04:27
Cascade classifier - intuition
09:45
Loading and pre-processing the image
12:05
Face detection with Haarcascade and OpenCV
12:45
Haarcascades parameters 1
07:04
Haarcascades parameters 2
08:50
Eye detection with haarcascades
10:24
HOMERWORK – detecting other objects
00:22
Homework solution
02:11
HOG (Histrograms of Oriented Gradients) – intuition
11:18
Face detection with HOG and Dlib
10:47
Face detection with CNN and Dlib
05:52
HOMEWORK – Haarcascade x HOG x CNN
00:18
Homework solution
05:03
Anaconda and PyCharm
03:01
Face detection on the webcam
08:07
Additional reading
00:08

Face recognition

19 lectures
Plan of attack
04:30
LBPH algorithm - intuition
09:25
Loading the faces dataset
09:56
Preprocessing the images
15:47
Training the LBPH classifier
04:38
Recognizing faces with LBPH
08:22
Evaluating the LBPH classifier
11:24
LBPH parameters
04:36
LBPH parameters – implementation
04:12
Detecting facial points
11:46
Detecting facial descriptors 1
14:22
Detecting facial descriptors 2
15:44
Calculating distances between faces
13:38
Recognizing faces with Dlib 1
11:55
Recognizing faces with Dlib 2
04:14
HOMEWORK
00:22
Homework solution
05:44
Face recognition on the webcam
04:48
Additional reading
00:08

Object tracking

8 lectures
Plan of attack
04:09
Object tracking vs. object detection
05:08
KCF and CSRT algorithms
06:47
Object tracking with KCF
14:22
Object tracking with CSRT
01:58
HOMEWORK
00:16
Homework solution
04:11
Additional reading
00:06

Neural networks for image classification

49 lectures
Plan of attack
03:04
Biological fundamentals
05:16
Artificial neuron
07:19
Perceptron
09:41
Weight update 1
11:29
Weight update 2
13:21
Introduction to multilayer neural networks
03:52
Activation functions
05:01
Hidden layer activation 1
05:28
Hidden layer activation 2
03:59
Output layer activation
04:40
Error calculation (loss function)
04:54
Basic algorithm
03:53
Gradient descent and derivative
08:56
Output layer delta
05:45
Hidden layer delta
07:27
Backpropagation and learning rate
06:30
Weight update with backprogation 1
06:23
Weight update with backprogation 2
07:39
Bias, error and multiple outputs
11:16
Hidden layers
10:47
Output layer with categorical data
04:36
Stochastic gradient descent
05:00
Deep learning
03:05
Pixels and neural networks
06:34
Importing the libraries
04:21
Extracting pixels from images 1
10:51
Extracting pixels from images 2
09:59
Extracting pixels from images 3
07:07
Extracting pixels from images 4
07:29
Normalizing the data
03:54
Creating the train and test sets
05:08
Building and training the neural network
11:45
Evaluating the neural network
12:37
Saving and loading the network
07:06
Classifying one single image
06:17
Extracting features from images
11:02
Feature extraction with OpenCV 1
06:20
Feature extraction with OpenCV 2
15:47
Feature extraction with OpenCV 3
07:07
Feature extraction with OpenCV 4
06:56
Feature extraction with OpenCV 5
07:07
Creating the train and test sets
04:16
Building and training the neural network
07:29
Evaluating the neural network
08:35
Saving, loading and classifying one single image
05:16
HOMEWORK
00:22
Homework solution
09:27
Additional reading
00:33

Convolutional neural networks for image classification

16 lectures
Plan of attack
01:55
Introduction to convolutional neural networks
07:18
Convolutional operation
10:04
Pooling
05:28
Flattening
06:31
Dense neural network
05:10
Importing the libraries
03:59
Loading the images
04:53
Creating the train and test dataset
11:25
Building and training the neural network
13:57
Evaluating the neural network
08:59
Saving and loading the network
02:43
Classifying one single image
06:34
HOMEWORK
00:28
Homework solution
10:00
Additional reading
00:20

Transfer learning and fine tuning

14 lectures
Plan of attack
02:14
Transfer learning – intuition
06:41
Importing the libraries and dataset
05:12
Creating the train and test dataset
03:36
Pre-trained neural network
12:04
Creating the custom dense layer
07:32
Building and training the neural network
06:17
Evaluating the neural network
06:13
Fine tuning – intuition
02:44
Fine tuning – implementation and evaluation
06:09
Saving, loading and classifying one single image
03:02
HOMEWORK
00:28
Homework solution
09:41
Additional reading
00:05

Neural networks for classification of emotions

12 lectures
Plan of attack
03:44
Importing the libraries and images
05:35
Creating the train and test dataset
04:20
Building and training the neural network
14:18
Saving and loading the model
01:29
Evaluating the neural network
04:58
Classifying one single image
08:17
Classifying multiple images
08:02
Classifying emotions in videos
11:24
HOMEWORK
00:23
Homework solution
05:39
Additional reading
00:05

Autoencoders

16 lectures
Plan of attack
02:34
Autoencoders – intuition
06:43
Importing the libraries and dataset
05:57
Visualizing the images
09:13
Preprocessing the images
05:28
Building and training a linear autoencoder
11:03
Encoding the images
08:29
Decoding the images
08:40
Encoding and decoding the test images
09:41
Convolutional autoencoders 1
06:05
Convolutional autoencoders 2
18:18
Convolutional autoencoders 3
08:21
Convolutional autoencoders 4
09:28
HOMEWORK
00:28
Homework solution
11:39
Additional reading
00:05

Object detection with YOLO

10 lectures
Plan of attack
02:04
YOLO – intuition
06:07
Downloading and compiling Darknet
05:51
Testing the detector
10:34
Darknet and GPU
08:40
Threshold and ext_output parameters
08:07
Detecting objects in videos
07:28
HOMEWORK
00:15
Homework solution
02:25
Additional reading
00:05

Recognition of gestures and actions

12 lectures
Plan of attack
02:56
Gestures and actions recognition – intuition
07:02
Importing the libraries and the image
08:34
Loading the pre-trained neural network
04:31
Predicting body points 1
17:25
Predicting body points 2
05:17
Detecting gestures in images
11:47
Detecting gestures in videos 1
06:06
Detecting gestures in videos 2
06:35
HOMEWORK
00:20
Homework solution
04:17
Additional reading
00:08

Deep dream

12 lectures
Plan of attack
02:45
Deep dream – intuition
06:09
Loading the InceptionNet network
12:05
Loading and preprocessing the image
08:58
Getting the activations
06:19
Calculating the loss
07:55
Gradient ascent 1
09:14
Gradient ascent 2
05:11
Generating images
07:43
HOMEWORK
00:15
Homework solution
02:30
Additional reading
00:04

Style transfer

14 lectures
Plan of attack
02:50
Style transfer – intuition
05:45
Loading VGG19 network
05:56
Loading and pre-processing the images
10:58
Building the neural network 1
16:35
Building the neural network 2
10:42
Building the neural network 3
15:07
Building the neural network 4
11:00
Training the neural network 1
15:40
Training the neural network 2
14:51
Visualizing the result
03:51
HOMEWORK
00:15
Homework solution
03:59
Additional reading
00:05

GANs (Generative adversarial networks)

12 lectures
Plan of attack
03:18
GANs – intuition
10:47
Loading the dataset
14:29
Building the generator 1
15:46
Building the generator 2
06:52
Building the discriminator
10:19
Calculating the loss
08:41
Training the GAN 1
12:30
Training the GAN 2
11:15
HOMEWORK
00:17
Homework solution
04:24
Additional reading
00:05

Image segmentation

14 lectures
Plan of attack
05:19
Image segmentation – intuition
09:19
Downloading the repository
03:49
Warning after Colab update
00:27
Importing the libraries
11:33
Loading the pre-trained neural network
09:01
Detecting objects
11:08
Removing the background 1
12:47
Removing the background 2
06:25
Segmentation in videos 1
09:17
Segmentation in videos 2
05:40
HOMEWORK
00:13
Homework solution
02:41
Additional reading
00:05

Final remarks

1 lectures
Final remarks
02:40

Congratulations!! Don't forget your Prize :)

1 lectures
Bonus: How To UNLOCK Top Salaries (Live Training)
00:44

Đánh giá của học viên

Chưa có đánh giá
Course Rating
5
0%
4
0%
3
0%
2
0%
1
0%

Bình luận khách hàng

Viết Bình Luận

Bạn đánh giá khoá học này thế nào?

Khoá học liên quan

Machine Learning A-Z: AI, Python & R + ChatGPT Prize [2024]

Machine Learning A-Z: AI, Python & R + ChatGPT Prize [2024]

140 VND
50.000 VND
THỰC CHIẾN THU THẬP DỮ LIỆU TỪ TRANG WEB BẰNG PYTHON - 2024

THỰC CHIẾN THU THẬP DỮ LIỆU TỪ TRANG WEB BẰNG PYTHON - 2024

25 VND
50.000 VND
Microservices with Spring Boot, Spring Cloud, Docker, K8s

Microservices with Spring Boot, Spring Cloud, Docker, K8s

1.499.000 VND
50.000 VND
Learn Automation of AutoCAD using python

Learn Automation of AutoCAD using python

999.000 VND
50.000 VND
Next.js 14 & React - The Complete Guide

Next.js 14 & React - The Complete Guide

185 VND
50.000 VND
Vuetify 2: Create an App with Vue JS 2 & Vuex - in 5 Hours!

Vuetify 2: Create an App with Vue JS 2 & Vuex - in 5 Hours!

1.499.000 VND
50.000 VND
Implementing Software Architecture of a Large-Scale System

Implementing Software Architecture of a Large-Scale System

90 VND
50.000 VND
Full Track to be Oracle APEX Developer [ English subtitles]

Full Track to be Oracle APEX Developer [ English subtitles]

185 VND
50.000 VND
C# Basics for Beginners: Learn C# Fundamentals by Coding

C# Basics for Beginners: Learn C# Fundamentals by Coding

130 VND
50.000 VND
Python 3: Deep Dive (Part 3 - Dictionaries, Sets, JSON)

Python 3: Deep Dive (Part 3 - Dictionaries, Sets, JSON)

1.699.000 VND
50.000 VND
Python 3: Deep Dive (Part 4 - OOP)

Python 3: Deep Dive (Part 4 - OOP)

2.399.000 VND
50.000 VND
Make an E-Commerce Website with Blazor WebAssembly in .NET 6

Make an E-Commerce Website with Blazor WebAssembly in .NET 6

1.499.000 VND
50.000 VND
Learn Multithreading with Modern C++

Learn Multithreading with Modern C++

90 VND
50.000 VND
Java Spring Boot E-Commerce Ultimate Course

Java Spring Boot E-Commerce Ultimate Course

110 VND
50.000 VND
.NET Core MVC - The Complete Guide 2024 [E-commerce] [.NET8]

.NET Core MVC - The Complete Guide 2024 [E-commerce] [.NET8]

90 VND
50.000 VND
MEAN Fullstack Trello clone: WebSocket, Socket IO

MEAN Fullstack Trello clone: WebSocket, Socket IO

70 VND
50.000 VND
image

Đăng ký get khoá học Udemy - Unica - Gitiho giá chỉ 50k!

Get khoá học giá rẻ ngay trước khi bị fix.

Get khoá học cho tôi