CCO - 750 - Foundations of Computer Vision

Total of Credits: 8
Hours for Theoretical Classes: 60
Hours for Exercises or Seminars: 60

Objective

At the end of the course, the student should be able to: apply filters to images in the spatial and frequency domains; segment coherent regions in images; identify borders, lines and salient points in images; match salient points detected in images and videos; track objects in images and videos; employ machine learning methods for image classification and object recognition

Catalog Description

Intensity transformations and image filtering: histogram processing; correlation and convolution; linear and non-linear spatial filters; the Fourier transform; image filtering in the frequency domain; morphological operators
Salient points detection: detecting lines and circles using the Hough transform; image pyramids; Harris corner detection; the SIFT and SURF algorithms
Matching salient points and tracking objects: geometrical transformations; the RANSAC method; the mean-shift and cam-shift algorithms; optical flow
Image segmentation: global and local optimal thresholding; the k-means algorithm; gaussian mixture models; superpixels
Image classification and object detection methods: the HOG algorithm; the k-neighbors classifier; the SVM classifier; deep Learning concepts.

Bibliography

Szeliski, “Computer Vision: Algorithms and Applications”, Springer, 2010 (http://szeliski.org/Book/). (disponível on-line).
A. Forsyth and J. Ponce, "Computer Vision: A Modern Approach", Prentice Hall, 2003. (disponível na BCo).
C. Gonzalez and R. E. Woods, “Digital Image Processing” (3rd Edition), Prentice-Hall, 2008. (disponível na BCo).
Ballard and C. Brown, “Computer Vision”, Prentice Hall, 1982. (disponível na BCO - UFSCar)
Kaebler and G. Bradski, “Learning OpenCV - Computer Vision in C++ with the OpenCV library” (1st. Edition), O’Reilly, 2017.
Nixon, A. S. Aguado, “Feature Extraction & Image Processing for Computer Vision”, (2nd Edition), Academic Press, 2008.