Teaching

Pattern Recognition

Lecture Curricula:

Introduction
Probability Review
Bayesian Decision Theory 1
Bayesian Decision Theory 2
Parametric Methods for Density Estimation
Nonparametric Methods for Density Estimation
Linear Discriminant Functions, Perceptron
Kernel Methods
Support Vector Machines
Image Classification Pipeline
Loss Functions and Optimization
Back Propagation and Neural Networks

Textbooks and references:

01. R. O. Duda, E. Hart, D. G. Stork, “Pattern Classification”, John Wiley and Sons, 2001
02. S. Theodoridis, K. Koutroumbas, “Pattern Recognition”, 4th edition, Academic Press, 2008.
03. C.M. Bishop, “Pattern Recognition and Machine Learning”, second edition, Springer, 2016
04. K.P. Murphy, “Machine Learning: A Probabilistic Perspective”, The MIT Press, 2012
05. K.P. Murphy, “Probabilistic Machine Learning: An Introduction”, The MIT Press, 2022
06. I. Goodfellow, Y. Bengio, A. Courville, “Deep Learning”, The MIT Press, 2016
07. Convolutional Neural Networks for Visual Recognition, http://cs231n.stanford.edu/, 2019
08. S. Nedevschi, “Pattern Recognition Systems – Lecture Notes”, TUCN 2022

Lab curricula:

Leat Mean Squares
RANSAC
Hough Transform
Distance Transform
Statistical Data Analysis
Principal Component Analysis
K-means Clustering
K-Nearest Neighbor Classifier
Naive Bayes Classifier
Perceptron Classifier
AdaBoost Method
Support Vector Machine

References:

01.   S. Nedevschi, R. Varga, F. Oniga, R. Brehar, I. Giosan, A. Petrovai, "Pattern Recognition Systems - Laboratory  Works", UTPRESS, 2023 
02.   S. Nedevschi, R. Varga, F. Oniga, R. Brehar, I. Giosan, A. Petrovai, "Sisteme de Recunoastere a Formelor - Lucrari de Laborator", UTPRESS, 2023

Additional matherials:

OpenCV 2.4.3 project - Visual Studio 2013; 
OpenCV 2.4.3 project - Visual Studio 2013 - simplified; 
OpenCV 3.1 project - Visual Studio 2015; 
Introduction to OpenCV [ro];
Introduction to OpenCV [eng]

Data files for Least Mean Squares
Data files for RANSAC
Data files for Hough Transform
Data files for Distance Transform
Data files for Statistical data Analysis
Data files for k-means Clustering
Data files for K-Nearest Neighbor Classifier
Data files for Naive Bayes Classifier
Data files for Perceptron Classifier
Data files for AdaBoost Method
Data files for Support Vector Machine

___________________________________________________________________________________________________

Image processing

Lecture Curricula:

Computer vision and applications. Vision system structure and functions. Image acquisition systems.
Image formation and sensing. Camera model
Binary image processing: Simple Geometric Properties.
Binary image processing: Labeling, Contour Tracing, Polygonal Approximation
Binary image processing: Mathematical Morphology
Grayscale image processing: Mathematical methods for grayscale image processing, Statistic features of the grayscale images, Histogram processing, Point Processing
Grayscale image processing: Convolution and Fourier Transform
Grayscale image processing: Noise in images
Grayscale image processing: Digital Filtering
Grayscale image segmentation: Edge based segmentation (first order differential methods).
Grayscale image segmentation: Edge based segmentation (second order differential methods, edge linking, contour closing,).
Stereo-vision basics. Epipolar geometry. Depth computation.
Color images: Color models. Color based segmentation.

Textbooks and references:

1. Rafael C. Gonzalez and Richard E. Woods, “Digital Image Processing”, 4th Edition, Pearson, March 30, 2017.
2. Rafael C. Gonzalez, Richard E. Woods and Steven L. Eddins , “Digital Image Processing Using MATLAB”, 2nd ed., Mc Graw Hill, 2010.
3. E. Trucco, A. Verri, “Introductory Techniques for 3-D Computer Vision”, Prentice Hall, 1998.
4. S. Nedevschi, R. Danescu, F. Oniga, T. Marita, Tehnici de viziune artificiala in conducerea automata a autovehiculelor, UTPRESS,  2012.
5. S. Nedevschi, "Image Processing - Lecture Notes", TUCN 2022.
6. S. Nedevschi, T. Marita, R. Danescu, F. Oniga, R. Brehar, I. Giosan, R. Varga, C. Vancea, "Image Processing - Laboratory Works" 2nd edition, UTPRESS, 2023.
7. S. Nedevschi, T. Marita, R. Danescu, F. Oniga, R. Brehar, I. Giosan, C. Vancea, R. Varga, "PROCESAREA IMAGINILOR -Îndrumător de laborator", Ediția a 2-a, UTPRESS, 2023. 


________________________________________________________________________________________________________

Deep Learning based Computer Vision

Lecture Curricula:

Introduction
Machine Learning Basics
Deep Neural Networks I
Deep Neural Networks II
Deep Neural Networks III
Convolutional Neural Networks
Recurrent Neural Networks
Attention and Transformers
Object Detection
Semantic Segmentation
Self Supervised Learning
Deep Generative Modeling
Detection with Transformers

Textbooks and references:

01. Gonzales, Woods, Digital Image Processing, 4th.Edition, Pearson, 2018;

02. Goodfellow, Bengio, Courville, Deep Learning, MIT Press, 2016, (http://www.deeplearningbook.org);
03. Bishop, Pattern Recognition and Machine Learning, Springer, 2016; 
04. Zhang, Lipton, Li, Smola, Dive into Deep Learning, Cambridge University Press, 2023;
05. Deisenroth, Faisal, Ong, Mathematics for Machine Learning;

06. Li(Stanford): Convolutional Neural Networks for Visual Recognition, http://cs231n.Stanford.edu; 
07. McAllestar: Fundamentals of Deep Learning, http://mcallester.github.io/ttic-31230/Fall2020/; 
08. Leal-Taixe, Niessner (TUM): Introduction to Deep Learning, http://niessner.github.io/I2DL/; 
09. A. Gaiger: Deep Learning, University of Tubingen; 
10. Grosse(UoT): Introduction to Neural Networks and Machine Learning,(http://www.cs.Toronto.edu/~rgrosse/courses/csc321_2018/); 
10. Abbeel, Chen, Ho, Srinivas (Berkeley): Deep Unsupervised Learning, (https://sites.google.com/view/Berkeley-cs294-158-sp20/home)

11. CVPR, ICCV, ECCV and WACV publications;
12. IEEE Transactions on Pattern Analyses and Machine Intelligence; 
13. IEEE Transactions on Intelligent Transportation Systems; 
14. IEEE Transactions on Image Processing

______________________________________________________________________________________

Computer Vision for Autonomous Systems

Lecture Curricula:

Introduction
Probability Review
Recursive State Estimation
Gaussian Filters
Nonparametric Filters
Robot Motion
Measurements
Mobile Robot Localization
Grid and Monte Carlo Localization
Occupancy Grid Mapping
Simultaneous Localization and Mapping
Planning and Collision Avoidance
Navigation

Textbooks and references:

01. S. Thrun, W. Burgard, D. Fox, “Probabilistic Robotics”, MIT Press, 2005
02. R. Siegwart, I. Nourbakhsh, “Autonomous Mobile Robots”, MIT Press, 2004
03. Emanuele Trucco, Alessandro Verri, “Introductory Techniques for 3-D Computer Vision”, Prentice Hall, 1998
04. S. Nedevschi, R. Danescu, F. Oniga, T. Marita, “Tehnici de viziune artificiala in conducerea automata a autovehiculelor“, UTPRESS,  2012
05. IEEE Transactions on Pattern Analyses and Machine Intelligence
06. IEEE Transactions on Image Processing
07. IEEE Transactions on Intelligent Transportation Systems
08. IEEE Transactions on Intelligent Vehicles
09. CVPR, ICCV, WACV, ECCV publications

_______________________________________________________________________________________