Real-World Computer Vision Applications

Common CV Challenges

Evaluation Metrics: IoU and mAP

Transfer Learning with Pretrained Vision Models

Image Segmentation: Semantic vs Instance

Object Detection and Bounding Boxes

Image Classification Task

Edge Detection and Classical Features

CNN Architecture for Vision Tasks

Pooling Layers and Downsampling

Feature Maps and Learned Visual Features

Convolution and Kernels Explained

Image Augmentation Techniques

Image Preprocessing Essentials

Color Spaces: RGB, Grayscale, HSV

How Digital Images Are Represented

What Computer Vision Is

Goal of Computer Vision

Stride and Padding

Image Classification Task

Grayscale vs Color

RGB Color Channels

Real-World CV Applications

Kernels and Filters

Object Detection Task

Images as Pixel Grids

Data Augmentation for Images

Pooling Layers

Vision Transformers Overview

Challenges in Computer Vision

Resolution and Aspect Ratio

Bounding Boxes and Localization

Traditional CV vs Deep Learning

Facial Recognition Basics

Preprocessing and Normalization

Optical Character Recognition

Evaluating with IoU

Edge and Texture Detection

Semantic vs Instance Segmentation

Receptive Field

Feature Extraction vs Fine-Tuning

Feature Maps

Convolution Basics

Transfer Learning in Vision

Common CNN Architectures

Flatten Feature Maps for Classifier

Non-Maximum Suppression Filter

RGB to HSV Conversion

Horizontal Flip with NumPy

Gradient Magnitude Computation

Rotate and Translate an Image

IoU of Two Boxes

Bounding Box Format Conversion

Segmentation Mask Representation

IoU for Segmentation

Blurring with an Averaging Kernel

Convolution Output Size Formula

Sobel Edge Detection Depth

Equalizing Image Contrast

Computing a Pixel Histogram

Padding a Color Image

Converting HWC to NCHW

Applying a 2D Convolution

Channel Mean/Std Normalization

Creating a Blank Image Array

Normalizing Pixels to [0,1]

Cropping an Image Region

Displaying an OpenCV Image

Resizing with OpenCV

RGB to Grayscale Conversion

Binary Thresholding

Real-World Applications of Computer Vision

Image Embeddings and Similarity

Optical Character Recognition (OCR)

Challenges in Computer Vision

Non-Maximum Suppression

Vision Transformers (ViT)

Image Preprocessing and Normalization

Transfer Learning with Pretrained Models

Intersection over Union (IoU)

Facial Recognition and Keypoint Detection

Receptive Field

Popular CNN Architectures

Data Augmentation for Images

Object Detection Frameworks

Edge Detection and Image Gradients

Classical Feature Descriptors (SIFT/HOG)

Semantic vs Instance Segmentation

Object Detection

Digital Image Representation

Image Classification

Stride and Padding

Convolution and Kernels

What is Computer Vision

Pooling Layers

Common CV Tasks Overview

Feature Maps and Channels

Resolution and Aspect Ratio

Color Spaces