Computer Vision
Description
Computer vision is a field of study that focuses on enabling computers to interpret and understand visual data from the world, such as images and videos. This can include tasks such as image recognition, object detection, and scene understanding. It involves the development of algorithms and techniques that enable a computer to extract information from visual data and make decisions based on that information. Applications of computer vision include self-driving cars, image search, and facial recognition.
What will you learn
-
Understand basic computer vision algorithms, the proper use of shape and Shape related cue features for Computer Vision Applications.
-
Apply and develop various object detection methods.
-
Analyse different Object detection algorithms used in Computer Vision.
Requirements
- Basics of Programming
- OpenCV.
- Machine learning
Lessons
- 76 Lessons
- 12:36:55 Hours
- CV Introduction00:03:04
- syllabus
- Introduction to Numpy and Image Section00:00:42
- NumPy Arrays00:16:50
- What is an image?00:05:54
- Images and NumPy00:12:24
- NumPy and Image Problems with solutions00:08:46
- Introduction to Images and OpenCV Basics00:02:38
- Opening Image files in a notebook00:19:30
- Opening Image files with OpenCV00:10:50
- Drawing on Images - Part 1 (Basic Shapes)00:10:01
- Drawing on Images Part Two Text and Polygons00:09:30
- Direct Drawing on Images with a mouse - Part One00:09:37
- Direct Drawing on Images with a mouse Part Two00:02:42
- Direct Drawing on Images with a mouse Part Three00:10:27
- Image Basics Assessment Problems with solutions00:05:16
- Introduction to Image Processing00:00:40
- Color Mappings00:06:48
- Blending and Pasting Images00:14:16
- Blending and Pasting Images-200:15:56
- Image Thresholding00:17:42
- Blurring and Smoothing00:06:44
- Blurring and Smoothing-200:19:46
- Morphological Operators00:15:28
- Gradients00:13:41
- Histograms-100:12:35
- Histograms - 200:12:20
- Histograms-300:08:13
- Image Processing Assessment and Solutions00:08:32
- Introduction to Video Basics00:01:06
- Connecting to Camera00:14:15
- Using Video Files00:07:01
- Drawing on Live Camera00:16:46
- Video Basics Assessment00:01:37
- Video Basics Assessment Solutions00:05:01
- Introduction to Object Detection00:02:28
- Template Matching00:17:42
- Harris Corner Detection00:14:10
- Corner Detection - Shi Tomasi Detection00:06:27
- Edge Detection00:09:29
- Grid Detection00:08:17
- Contour Detection00:11:12
- Feature Matching-100:12:26
- Feature Matching -200:18:29
- Watershed Algorithm - 100:11:50
- Watershed Algorithm - Part Two00:20:15
- Custom Seeds with Watershed Algorithm00:18:56
- Face Detection00:09:12
- Face Detection - 200:14:31
- Detection Assessment Problem & Solution00:07:11
- Introduction00:00:35
- Optical Flow00:05:38
- Optical Flow - Part One00:18:36
- Optical Flow - Part Two00:10:58
- MeanShift and CamShift Tracking Theory00:05:48
- MeanShift and CamShift Tracking 200:14:42
- Overview - various Tracking API Methods00:06:51
- Tracking APIs00:06:53
- Introduction00:02:30
- Machine Learning Basics00:06:55
- Understanding Classification Metrics00:14:13
- Deep Learning Topics00:01:25
- Understanding a Neuron00:05:13
- Understanding a Neural Network00:06:31
- Cost Functions00:03:41
- Gradient Descent and Back Propagation00:03:21
- Keras Basics00:18:03
- MNIST Data00:04:42
- Convolutional Neural Networks - 100:18:54
- Convolutional Neural Networks - 200:04:24
- Keras Convolutional Neural Networks with MNIST00:17:09
- Keras Convolutional Neural Networks with CIFAR 1000:12:00
- Deep Learning on Custom Images - 100:14:51
- Deep Learning on Custom Images - 200:19:35
- Deep Learning and Convolutional Neural Networks Assessment Problem & Solution00:07:08
- YOLO v3 with Python00:17:06
About instructor
Reviews
