Computer Vision Tutorials Index
Overview of computer vision and its Applications
- Computer Vision – Introduction
- A Quick Overview to Computer Vision
- Applications of Computer Vision
- Image Formation Tools & Technique
- Digital Photography
- Satellite Image Processing
- Lidar(Light Detection and Ranging)
- Synthetic Image Generation
- Image Stitching & Composition
- Fundamentals of Image Formation
- Image Formats
- Beginner’s Guide to Photoshop Tools
Image Processing & Transformation
- Digital Image
- Digital Image Processing Basics
- Digital image color spaces
- RGB, HSV,
- Image Transformation:
- Pixel Transformation
- Geometric transformations
- Fourier Transforms for Image Transformation
- Intensity Transformation
- Image Enhancement Techniques
- Histogram Equalization
- Color correction
- Contrast Enhancement
- Image Sharpening
- Edge Detection
- Noise Reduction & Filtering Technique
- Morphological operations
- Image Denoising Techniques
- Denoising of colored images using opencv
- Total Variation Denoising
- Wavelet Denoising
- Non-Local Means Denoising
Feature Extraction and Description:
- Feature detection and matching with OpenCV-Python
- Boundary Feature Descriptors
- Region Feature Descriptors
- Interest point detection
- Local feature descriptors
- Harris Corner Detection
- Scale-Invariant Feature Transform (SIFT)
- Speeded-Up Robust Features (SURF)
- Histogram of Oriented Gradients (HOG)
- Principal Component as Feature Detectors
- Local Binary Patterns (LBP)
- Convolutional Neural Networks (CNN)
Deep Learning for Computer Vision
- Convolutional Neural Networks (CNN)
- Introduction to Convolution Neural Network
- Types of Convolutions
- Strided Convolutions
- Dilated Convolution
- Flattened Convolutions
- Spatial and Cross-Channel convolutions
- Depthwise Separable Convolutions
- Grouped Convolutions
- Shuffled Grouped Convolutions
- Continuous Kernel Convolution
- What is a Pooling Layers?
- Introduction to Padding
- Data Augmentation in Computer Vision
- Deep ConvNets Architectures for Computer Vision
- ImageNet Dataset
- Transfer Learning for Computer Vision
- What is Transfer Learning?
- Residual Network
- Inception Network
- MobileNet
- EfficientNet
- Visual Geometry Group Network (VGGNet)
- FaceNet Architecture
- AutoEncoders
- How Autoencoders works
- Encoder and Decoder network architecture
- Latent space representation
- Implementing an Autoencoder in PyTorch
- Autoencoders for Computer Vision:
- Feedforward Autoencoders
- Deep Convolutional Autoencoders
- Variational autoencoders (VAEs)
- Denoising autoencoders
- Sparse autoencoders
- Adversarial Autoencoder
- Applications of Autoencoders
- Dimensionality reduction and feature extraction using autoencoders
- Image compression and reconstruction techniques
- Anomaly detection and outlier identification with autoencoders
- Generative Adversarial Network (GAN)
- Deep Convolutional GAN
- StyleGAN – Style Generative Adversarial Networks
- Cycle Generative Adversarial Network (CycleGAN)
- Super Resolution GAN (SRGAN)
- Selection of GAN vs Adversarial Autoencoder models
- Real-Life Application of GAN
- Image and Video Generation using DCGANs
- Conditional GANs for image synthesis and style transfer
- VAEs for image generation and latent space manipulation
- Evaluation metrics for generative models
Object Detection and Recognition
- Introduction to Object Detection and Recognition
- Traditional Approaches for Object Detection and Recognition
- Feature-based approaches: SIFT, SURF, HOG
- Sliding Window Approach
- Selective Search for Object Detection
- Haar Cascades for Object Detection
- Template Matching
- Object Detection Techniques
- Bounding Box Predictions in Object Detection
- Intersection over Union
- Non – Max Suppression
- Anchor Boxes in Object Detection
- Region Proposals in Object Detection
- Feature Pyramid Networks (FPN)
- Contextual information and attention mechanisms
- Object tracking and re-identification
- Neural network-based approach for Object Detection and Recognition
- R Proposals in Object Detection | R – CNN
- Fast R-CNN
- Faster R – CNN
- Single Shot MultiBox Detector (SSD)
- You Look Only Once(YOLO) Algorithm in Object Detection
- Object Recognition in Video
- Evaluation Metrics for Object Detection and Recognition
- Intersection over Union (IoU)
- Precision, recall, and F1 score
- Mean Average Precision (mAP)
- Object Detection and Recognition Applications
- Object Detection and Self-Driving Cars
- Object Localization
- Landmark Detection
- Face detection and recognition
- What is Face Recognition Task?
- DeepFace Recognition
- Eigen Faces for Face Recognition
- Emojify using Face Recognition with Machine Learning
- Face detection and landmark localization
- Facial expression recognition
- Hand gesture recognition
- Pedestrian detection
- Object Detection with Detection Transformer (DETR) by Facebook
- Vehicle detection and tracking
- Object detection for autonomous driving
- Object recognition in medical imaging
Image Segmentation
- Introduction to Image Segmentation
- Point, Line & Edge Detection
- Thresholding Technique for Image Segmentation
- Contour Detection & Extraction
- Graph-based Segmentation
- Region-based Segmentation
- Region and Edge Based Segmentation
- Watershed Segmentation Algorithm
- Semantic Segmentation
- Deep Learning Approaches to Image Segmentation
- Fully convolutional networks (FCN)
- U-Net architecture for semantic segmentation
- Mask R-CNN for instance segmentation
- Encoder-Decoder architectures (e.g., SegNet, DeepLab)
- Evaluation Metrics for Image Segmentation
- Pixel-level evaluation metrics (e.g., accuracy, precision, recall)
- Region-level evaluation metrics (e.g., Jaccard Index, Dice coefficient)
- Mean Intersection over Union (mIoU)
- Boundary-based evaluation metrics (e.g., average precision, F-measure)
3D Reconstruction
- Structure From Motion for 3D Reconstruction
- Monocular Depth Estimation Techniques
- Fusion Techniques for 3D Reconstruction
- LiDAR | Light Detection and Ranging
- Depth Sensor Fusion
- Volumetric Reconstruction
- Point Cloud Reconstruction
Computer Vision Interview Questions
- Computer Vision Interview
Computer Vision Projects
Computer Vision Tutorial
Computer vision, a fascinating field at the intersection of computer science and artificial intelligence, which enables computers to analyze images or video data, unlocking a multitude of applications across industries, from autonomous vehicles to facial recognition systems.
This Computer Vision tutorial is designed for both beginners and experienced professionals, covering both basic and advanced concepts of computer vision, including Digital Photography, Satellite Image Processing, Pixel Transformation, Color Correction, Padding, Filtering, Object Detection and Recognition, and Image Segmentation.