Udemy Business

Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

Computer Vision with OpenCV | Deep Learning CNN Projects

Name: Computer Vision with OpenCV | Deep Learning CNN Projects
Rating: 4.3 (44 reviews)

Learn Python OpenCV 4,Computer Vision and Deep Learning Projects from scratch to expert level| Deep Learning CNN Project

Created byGoeduhub Technologies

Last updated 3/2021

English

What you'll learn

Computer vision and Image Processing
Image Processing operations using Opencv
Face Detection and work with Live Camera
Convolutional Neural Network Concept
Project-Handwritten digits Classifier
Project: Dogs vs Cats classifier
Project: Real time Object Detection using YOLOv3
Project: Social Distancing Detector COVID-19
Project: MNIST Fashion Classifier

Course content

10 sections • 38 lectures • 5h 13m total length

Getting Started with Google Colab8:47
Image Processing vs Computer Vision8:03
Reference Notes: http://goeduhub.com/10572/difference-between-image-processing-and-computer-vision?show=10572#q10572
Introduction and working of OpenCV8:26
Reference Notes: http://goeduhub.com/10108/working-of-opencv?show=10108#q10108
You can download anaconda software and install it.
Then create a virtual environment and install opencv.
http://goeduhub.com/35/introduction-and-installation-opencv-python-for-beginners?show=35#q35

Image read and display using OpenCV12:01
Reference notes: http://goeduhub.com/133/image-operations-display-resize-color-changing-opencv-python?show=133#q133
Image Properties13:12
Reference Notes: http://goeduhub.com/133/image-operations-display-resize-color-changing-opencv-python?show=133#q133
Image resize and write using OpenCV3:49
Reference Notes: http://goeduhub.com/133/image-operations-display-resize-color-changing-opencv-python?show=133#q133
ROI and Color Changing using OpenCV4:51
Reference Notes: http://goeduhub.com/133/image-operations-display-resize-color-changing-opencv-python?show=133#q133
Horizontal & Vertical flipping of images3:24
Reference Notes: http://goeduhub.com/137/flipping-horizontally-vertically-horizontally-vertically?show=137#q137
Drawing function in OpenCV14:58
Reference Notes: http://goeduhub.com/10216/drawing-functions-opencv-rectangle-ellipse-polygon-puttext?show=10216#q10216
Draw Rectangle using OpenCv4:58
Reference Notes: http://goeduhub.com/10187/draw-rectangle-using-opencv?show=10187#q10187

Working with Live Camera15:00
Face Detection in Image14:41
Face Detection in Live Camera7:41
Learn to perform live face detection with OpenCV by capturing video, converting frames to grayscale, applying a cascade classifier, and drawing bounding boxes in real time.
Display Only Face from image and Save5:08
Learn to detect a face in an image and display only the face region using OpenCV, with code to crop and save the face output.

Why CNN6:37
https://www.goeduhub.com/5634/what-is-convolutional-neural-network?show=5634#q5634
What is CNN4:36
https://www.goeduhub.com/5634/what-is-convolutional-neural-network?show=5634#q5634
Convolution Layer8:30
https://www.goeduhub.com/5634/what-is-convolutional-neural-network?show=5634#q5634
Relu Layer2:49
https://www.goeduhub.com/5634/what-is-convolutional-neural-network?show=5634#q5634
Pooling Layer4:00
Explore the pooling layer in deep learning, learning how maximum pooling and average pooling reduce convolution outputs using window sizes (2x2, 3x3) and strides (1, 2), with padding as needed.
Flattening Layer2:05
Learn how to flatten convolutional outputs into a one-dimensional vector to feed a neural network, turning matrices into a fully connected multilayer perceptron for classification.
Fully Connected Layer12:20
Explore how convolutional layers extract features from images using convolution, relu, and max pooling, then flatten the results and feed them to a fully connected multilayer perceptron for classification.

Project introduction and Data Preprocessing13:53
https://www.goeduhub.com/10481/implement-cnn-using-keras-in-mnist-dataset-in-tensorflow2?show=10481#q10481

Here find source code in .py file because .ipynb is not uploading.

link of my colab file--https://colab.research.google.com/drive/1ItHMGZTi3wHdk5Jq_TgXRbKkjaib0Jt5?usp=sharing
Model creation4:52
Build Model and Prediction on images7:35
Build a CNN model and train with a compiled optimizer and loss, using sparse categorical crossentropy and accuracy; preprocess new images to 28 by 28, normalize, and predict.

Introduction-Objects Detection with YOLO v3 and OpenCV5:23
Refer this link for code and details
http://goeduhub.com/9736/object-detection-using-yolo-algorithm?show=9736#q9736
Implementation-Objects Detection on Image with YOLO v3 and OpenCV-part17:28
Refer this link for code and details
http://goeduhub.com/9736/object-detection-using-yolo-algorithm?show=9736#q9736
Implementation-Objects Detection on Image with YOLO v3 and OpenCV-part211:41
Implement object detection on images using YOLO v3 with OpenCV, converting images to blob format, running the DNN, applying non-maximum suppression, and visualizing bounding boxes with class labels.
Implementation-Objects Detection on Live Video with YOLO v3 and OpenCV3:13
Learn to implement YOLO v3 algorithm online video with OpenCV, capturing live video, processing frames, creating blobs, running the network, and drawing bounding boxes for detections with a 0.5 confidence threshold.

Introduction to Cat Dog Classifier7:40
Develop a cat and dog classification model with a CNN, load and preprocess the dataset, build and train the model, and evaluate performance on training and validation sets.
Preprocess data6:32
Prepare data by loading and pre-processing images, converting them into batches, and dividing pixel values by 255 to scale to 0-1 for training and validation.
Build a Model4:57
Data Augmentation and Final Model12:11
Learn how data augmentation and dropout reduce overfitting in a cnn-based cat and dog classifier, improving validation performance in a deep learning cnn project.

Introduction to Social Distancing Detector COVID-191:26
https://www.goeduhub.com/10498/social-distancing-detection-python-machine-learning-learning?show=10498#q10498
Human Detecting using YOLO19:17
https://www.goeduhub.com/10498/social-distancing-detection-python-machine-learning-learning?show=10498#q10498
Calculating Distance and Category of Risk9:17
https://www.goeduhub.com/10498/social-distancing-detection-python-machine-learning-learning?show=10498#q10498
Drawing rectangle and line of different zones10:39
https://www.goeduhub.com/10498/social-distancing-detection-python-machine-learning-learning?show=10498#q10498

Requirements

Basic programming skills in Python would be beneficial.
WebCam if you want to learn the video streaming content

Description

OpenCV-Python is an appropriate tool for fast prototyping of Computer Vision problems.

Hands-on Computer Vision with OpenCV from scratch to real-time project development.

Computer Vision is the hottest field in the era of Artificial Intelligence. It is making enormous advances in Self-driving cars, Robotics, Medical as well as in various image correction apps.

Computer Vision is showing us the future of technology and we can't even imagine what will be the end of its possibilities.

OpenCV library uses NumPy and all its array structures convert to and from NumPy arrays.

OpenCV is used to develop real-time computer vision applications. It is capable of processing images and videos to identify objects, faces, or even handwriting.

You will learn the topics:

The key concepts of computer Vision & OpenCV
Basic operations: Image read and display, Image Properties, Image resize and write, ROI and Color Mapping, Horizontal & Vertical flipping of images.
Drawing function in OpenCV
Working with Live Camera
Object detection: haarcascade face detection in images and Live camera
Convolutional Neural Network (CNN)
Deep Learning with Keras
Project: Handwritten Digit Classification using MNIST
Project: Fashion Classifier using FNIST
Project: Dogs vs Cats classifier
Project: Object Detection using YOLOv3
Project: Social Distancing Detector COVID-19

Feel free to message us on Udemy if you have any questions about the course!

So, are you ready to get started? Enroll now and start the process of becoming a Master in Computer Vision using Deep Learning today!

Who this course is for:

Python Developers, who want to upgrade in Computer Vision and Deep Learning.
Freshers Interested in Computer Vision and Deep Learning.
Engineering Students Who Want to Make Their Carrier in Computer Vision and Deep Learning.
Passion to learn computer vision from scratch

Computer Vision with OpenCV | Deep Learning CNN Projects

What you'll learn

Explore related topics

Course content

Introduction to Computer vision and OpenCV3 lectures • 25min

Image Operations using OpenCV7 lectures • 57min

Face Detection and Working with Live Camera4 lectures • 43min

Convolutional Neural Network7 lectures • 41min

Keras API1 lecture • 6min

Project- Handwritten Digits Recognition using CNN, Keras3 lectures • 26min

Project-Object Detection using YOLO v3 Algorithm4 lectures • 28min

Project Cat Dog Classifier4 lectures • 31min

Project- MNIST Fashion Clothing Classifier1 lecture • 15min

Project-Social Distancing Detector4 lectures • 41min

Requirements

Description

Who this course is for: