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 function used as a composition unit in a neural network

The gradient of the loss function in a neural network

It performs a matrix multiplication of a [3x3] matrix with a [3x4] matrix.

It performs an affine transformation: $y = Wx + b$ where $y$ is a four-dimensional vector, and $x$ is a three-dimensional vector.

It transforms a [3x4] matrix into a two dimensional point belonging to a line in the plane.

It flattens a 3x4 matrix into a 12 entries vector.

What is the operation performed by this linear layer: ```linear_layer = torch.nn.Linear(3, 4)```?

What is the operation performed by this linear layer: <code>linear_layer = torch.nn.Linear(3, 4)</code>?

Consider the following code snippet:
```Python
linear_layer = torch.nn.Linear(2, 3)
input_tsr = torch.randn(4, 2)
output_tsr = linear_layer(input_tsr) 
```
What would be the shape of `output_tsr`?

Consider the following code snippet:
<pre><code class="language-Python">linear_layer = torch.nn.Linear(2, 3)
input_tsr = torch.randn(4, 2)
output_tsr = linear_layer(input_tsr) 
</code></pre>
What would be the shape of <code>output_tsr</code>?

What would the output of the following code?
 ```Python
torch.nn.functional.relu(torch.tensor([-2.0, 3.0]))
```

What would the output of the following code?
<pre><code class="language-Python">torch.nn.functional.relu(torch.tensor([-2.0, 3.0]))
</code></pre>

To create an alternative output branch for a neural network

To improve neural network interpretability

What is the goal of using a dropout layer?

What is the goal of using a dropout layer?

Tensors and Neural Network Building Blocks

Tensors and Neural Network Building Blocks

Test your knowledge on tensors and neural network building blocks.

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: Tensors and Neural Network Building Blocks