Gain insights into automated inspection with computer vision. Learn image analysis, feature detection, edge detection, transformations, and neural networks to build industrial inspection systems for quality assurance.

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

Training neural networks and monitoring the evolution of the losses

Acting as a hub where we can download pretrained CNN weights

Locating objects (through a bounding box or a mask) in images from a dataset

Rating public image datasets so users know which ones are of the best quality

What is the use of the CVAT image annotation tool?

What is the use of the CVAT image annotation tool?

Search for a pretrained CNN that does exactly what you need.

Pass the images of defects through a generic pretrained CNN, and figure out how the CNN output maps with the type and location of the defect.

Annotate an image dataset of the product with all the known defect types, then use transfer learning or fine-tuning of a pretrained CNN on this dataset.

Get a pretrained CNN and train it on your defect dataset from scratch.

Suppose you need to locate defects in images of a unique product manufactured by your company, how can you leverage pretrained CNNs?

Suppose you need to locate defects in images of a unique product manufactured by your company, how can you leverage pretrained CNNs?

**(True or False)** The polygon annotation tool can only create quadrilaterals.

(True or False) The polygon annotation tool can only create quadrilaterals.

**(True or False)** With the polygon annotation tool, we must know in advance how many vertices the polygon will have, before selecting any point.

(True or False) With the polygon annotation tool, we must know in advance how many vertices the polygon will have, before selecting any point.

Objects of the same category or label get the same arbitrary color.

The object contrast is increased for a better visibility.

All objects found in a given image, no matter their label, get the same color.

What is the meaning of the highlighting color in the image annotation environment?

What is the meaning of the highlighting color in the image annotation environment?

**(True or False)** An object can partially occlude another object.

(True or False) An object can partially occlude another object.

**(Select all that apply.)** Which annotation format is supported by the CVAT annotation tool?

(Select all that apply.) Which annotation format is supported by the CVAT annotation tool?

Quiz: The CVAT image annotation tool

Quiz: The CVAT image annotation tool

Test your knowledge of the CVAT image annotation tool.

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: CVAT Annotation Tool