Kurssisisältö

Computer Vision Course Outline

1. Introduction to Computer Vision

What is Computer Vision?Fundamentals of Image Processing Linear algebra for image manipulation

2. Image Processing with OpenCV

Basic Transformations Fourier Transform Low-pass and High-pass Filters Noise Reduction and Smoothing Histogram Equalization Super-Resolution Techniques Edge Detection Corner and Blob Detection

3. Convolutional Neural Networks

Introduction to Convolutional Neural Networks Convolution Layers Pooling Layers Flattening Activation Functions Overview of Popular CNN Models Challenge: Building a CNN

4. Object Detection

Object Localization Object Detection Bounding Box Predictions Intersection Over Union (IoU) and Evaluation Metrics Non-Max Suppression (NMS)Anchor Boxes YOLO Model Overview Challenge: Object Detection with Custom Model and YOLO

5. Advanced Topics Overview

Transfer Learning in Computer Vision Overview of Face Recognition Overview of Image Generation

Edge Detection

Edges represent sudden changes in pixel intensity, which usually correspond to object boundaries. Detecting edges helps in shape recognition and segmentation.

Sobel Edge Detection

The Sobel operator calculates gradients (changes in intensity) in both the X and Y directions, helping detect horizontal and vertical edges.

Canny Edge Detection

The Canny Edge Detector is a multi-stage algorithm that provides more accurate edges by:

Applying Gaussian blur to remove noise.
Finding intensity gradients using Sobel filters.
Suppressing weak edges.
Using double thresholding and edge tracking.

A comparison of edge detection methods:

Tehtävä

Swipe to start coding

Apply both methods, Sobel and Canny:

Convert photo to grayscale;
Apply Sobel filter on X and Y directions with output depth cv2.CV_64F and kernel size 3;
Combine Sobel-filtered directions;
Apply a Canny filter with a threshold from 200 to 300.

Ratkaisu

Vaihda työpöytään todellista harjoitusta vartenJatka siitä, missä olet käyttämällä jotakin alla olevista vaihtoehdoista

Oliko kaikki selvää?

Kiitos palautteestasi!

Osio 2. Luku 7

Edge Detection

Edges represent sudden changes in pixel intensity, which usually correspond to object boundaries. Detecting edges helps in shape recognition and segmentation.

Sobel Edge Detection

The Sobel operator calculates gradients (changes in intensity) in both the X and Y directions, helping detect horizontal and vertical edges.

Canny Edge Detection

The Canny Edge Detector is a multi-stage algorithm that provides more accurate edges by:

Applying Gaussian blur to remove noise.
Finding intensity gradients using Sobel filters.
Suppressing weak edges.
Using double thresholding and edge tracking.

A comparison of edge detection methods:

Tehtävä

Swipe to start coding

Apply both methods, Sobel and Canny:

Convert photo to grayscale;
Apply Sobel filter on X and Y directions with output depth cv2.CV_64F and kernel size 3;
Combine Sobel-filtered directions;
Apply a Canny filter with a threshold from 200 to 300.

Ratkaisu

Vaihda työpöytään todellista harjoitusta vartenJatka siitä, missä olet käyttämällä jotakin alla olevista vaihtoehdoista

Oliko kaikki selvää?

Kiitos palautteestasi!

Osio 2. Luku 7

Vaihda työpöytään todellista harjoitusta vartenJatka siitä, missä olet käyttämällä jotakin alla olevista vaihtoehdoista