Gain insights into automated inspection using computer vision. Learn image analysis, feature detection, 2D/3D transformations, and train neural networks for object detection and image segmentation.

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

If we match a template whose shape is `(51, 51, 3)` on an image whose shape is `(500, 500, 3)`, what will be the match image shape?

If we match a template whose shape is <code>(51, 51, 3)</code> on an image whose shape is <code>(500, 500, 3)</code>, what will be the match image shape?

We match a template of shape `(31, 31)` (height and width, respectively) on a source image whose shape is `(512, 512)`. If a high match pixel is found in the match image at location (x, y) = `(200, 100)`, what is the corresponding pixel location of the feature in the source image?

We match a template of shape <code>(31, 31)</code> (height and width, respectively) on a source image whose shape is <code>(512, 512)</code>. If a high match pixel is found in the match image at location (x, y) = <code>(200, 100)</code>, what is the corresponding pixel location of the feature in the source image?

It can increase or decrease, depending on the blob shape.

After applying dilation to a binary image, what happens to the number of active pixels?

After applying dilation to a binary image, what happens to the number of active pixels?

To fill holes in blobs while keeping the shape approximately the same, what morphology operations should we apply?

To fill holes in blobs while keeping the shape approximately the same, what morphology operations should we apply?

The size of the largest holes in the blobs

The average of the blob's smallest dimensions

The smallest dimension of the largest spurious blob

The largest dimension of the largest spurious blob

In order to eliminate spurious blobs, what criterion should we use to determine the shape of the erosion kernel?

In order to eliminate spurious blobs, what criterion should we use to determine the shape of the erosion kernel?

It is an erosion followed by a dilation, using identical kernels.

It is an erosion followed by smoothing, using identical kernels.

It is a dilation followed by smoothing, using identical kernels.

It is a dilation followed by erosion, using identical kernels.

The product of the number of non-zero pixels and the active grayscale value

The moments of an image are defined by the following equation:
$m_{i,j}=\sum_{x} \sum_{y} x^i y^j I[x, y]$.

What does the image moment $m_{0,0}$ represent, for a binary image?

The moments of an image are defined by the following equation:
<math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>m</mi><mrow><mi>i</mi><mo separator="true">,</mo><mi>j</mi></mrow></msub><mo>=</mo><msub><mo>∑</mo><mi>x</mi></msub><msub><mo>∑</mo><mi>y</mi></msub><msup><mi>x</mi><mi>i</mi></msup><msup><mi>y</mi><mi>j</mi></msup><mi>I</mi><mo stretchy="false">[</mo><mi>x</mi><mo separator="true">,</mo><mi>y</mi><mo stretchy="false">]</mo></mrow><annotation encoding="application/x-tex">m_{i,j}=\sum_{x} \sum_{y} x^i y^j I[x, y]</annotation></semantics></math>mi,j​=∑x​∑y​xiyjI[x,y].
What does the image moment <math xmlns="http://www.w3.org/1998/Math/MathML"><semantics><mrow><msub><mi>m</mi><mrow><mn>0</mn><mo separator="true">,</mo><mn>0</mn></mrow></msub></mrow><annotation encoding="application/x-tex">m_{0,0}</annotation></semantics></math>m0,0​ represent, for a binary 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

Cats vs Dogs Classification with Convolutional Neural Networks

Dataset Annotation

Final Remarks

Recognize Handwritten Digits Using a Deep Neural Network

Quiz: Template Matching, Morphology, and Blob Detection