Automated Inspection with Computer Vision.png

AICV_jupyterOpenCV.tar.gz

load_image

annotation

color_spaces

thresholding

smoothing

masking

jup_smooth

morphology

blob_detection

jup_fiducials

edge_detection

jupyter_masking_edge_detection

corner_detection

jupyter_corner_detection

homographies

jup_homographies

topography

jup_topography

tensor_manipulation

neural_network_building_blocks

training_neural_network

jup_train_nn

cnn_building_blocks

cnn_for_classification

pretrained_classification_cnn

jup_train_classification_cnn

transfer_learning

jup_finetune_classification_CNN

cnn_for_object_detection

jup_pretrained_object_detection

cnn_for_semantic_segmentation

jup_pretrained_semantic_segmentation

annotation_formats

spa_train_mlp

prj_jup_create_train_mlp_classification

Computer vision is essential for developers who wish to learn practical skills, e.g., in industrial manufacturing, automated inspection of products is crucial for quality assurance.

In this course, you’ll apply computer vision and machine learning to analyze images for automated inspection. You’ll start by learning image I/O operations, thresholding, smoothing, and masking. You’ll learn feature detection using template matching and morphology. You’ll use the Sobel and Canny Edge Detectors, Harris Corner Detector, and Hough transform. You’ll learn about 2D transformations, including perspective and affine transformation, and 3D-to-2D projections. You’ll perform topography with a laser line to inspect the 3D shape of an object. Lastly, you’ll train convolutional neural networks for object detection and image segmentation and annotate datasets using CVAT.

By the end of this course, you will have the skills to build inspection systems for industrial applications using computer vision and machine learning.

Automated Inspection with Computer Vision

A flat object can appear blurred by motion, and we need to sharpen the image.

A flat object can have any orientation in the image.

A flat object can appear in the image with different scale factors.

The image of a cylindrical object must be warped so that the text on the object is readable.

**(Select all that apply.)** In which situation could a homography be applied to register the image of an object to inspect?

(Select all that apply.) In which situation could a homography be applied to register the image of an object to inspect?

**(True or False)** Only images of rectangular objects can be transformed by homographies.

(True or False) Only images of rectangular objects can be transformed by homographies.

What is the minimum number of feature point correspondences needed for an affine transformation?

What is the minimum number of feature point correspondences needed for an affine transformation?

**(True or False)** The feature points in the warped image can be defined arbitrarily.

(True or False) The feature points in the warped image can be defined arbitrarily.

**(True or False)** The perspective transformation is a special case of the affine transformation.

(True or False) The perspective transformation is a special case of the affine transformation.

The camera axis is perpendicular to the object surface. The object can be rotated in the plane.

The object is close enough to the camera that parallel lines in the plane of the object appear converging in the image.

No feature point can be detected in the image.

The object is far enough from the camera that parallel lines in the plane of the object appear parallel in the image.

**(Select all that apply.)** In which situation could we apply an affine transformation to register the image of a flat object? 

(Select all that apply.) In which situation could we apply an affine transformation to register the image of a flat object?

How many matches are required to perform a perspective transformation?

How many matches are required to perform a perspective transformation?

**(True or False)** The image returned by ```cv2.warpPerspective()``` must have the same dimensions as the original image.

(True or False) The image returned by <code>cv2.warpPerspective()</code> must have the same dimensions as the original image.

Introduction

Getting Started with Images

Image I/O and Annotations

Color Spaces and Thresholding

Convert Color Spaces, Threshold

Smoothing and Masking

Detection of Features

Image Registration

3D Vision

Getting Started with Neural Networks

Convolutional Neural Networks

Project: Create and Train a CNN for Classification

Object Detection and Semantic Segmentation

Dataset Annotation

Final Remarks

Quiz: Homographies