Object Recognition Lecture

Intro and Overview Object Recognition Lecture

Image Processing

Basic Image Access Operations
Basic Filter Operations
Gaussian Filter and Derivatives of Gaussian
Rectangular- and Gaussian Low Pass Filtering
Noise Suppression
Gaussian and Difference of Gaussian Pyramid

Features

Global Image Features
Similarity Measures
Histogram-based Image Retrieval
Multidimensional Receptive Field Histograms
Histogram-based Naive Bayes Recognition
Example: Naive Bayes Object Recognition
Local Image Features
Example: Harris-Förstner Corner Detection
Example: Create SIFT Descriptors with openCV
Histogram of Oriented Gradients: Step-by-Step
HOG-based Pedestrian Detection

Object Recognition

Object Recognition

Deep Learning

Convolutional Neural Networks
Animations of Convolution and Deconvolution
Convolutional Neural Networks for Object Recognition
Object Detection

Face Detection and Recognition

Face Detection
Face Recognition using FaceNet

Pose Estimation

Multi-Person 2D Pose Estimation using Part Affinity Fields

References

References

Powered by Jupyter Book

Index

By Prof. Dr. Johannes Maucher
© Copyright 2021.