Select your language

   +(36) 88 624 023 | |    H-8200, Veszprem, Egyetem str. 10, Building I.

Select your language

Scholar: László Czúni

The purpose of the course is to learn the theory of elementary mechanisms of digital image processing. The first topic is the forming of images, including possible distortion effects. Then we discuss image transformations including color, geometry, and unitary transforms and linear and nonlinear filters. The detection of image features are important steps in object recognition, mostly the aim is to detect invariant features. At the end of the course neural network based image recognition is introduced.

1.      The forming of images

  • Seeing by waves in biological and machine vision systems
  • The role of optics, distortions
  • The projection, the basics of computer vision
  • Sampling, rescaling images

2.      Image transformation and applications

  • Color transformations and some applications
  • Geometrical transformations, coordinate transforms, camera calibration
  • Unitary transforms (Fourier, Cosine, Haramard, Karhunen Loewe), filtering in the frequency domain, compression

3.      Image filtering

  • Noise models
  • Linear and nonlinear filters
  • Image morphology

4.      Image measurements

  • Feature detection (e.g. SIFT, SURF)
  • Haar-like filters, cascade filtering

5.      Image recognition

  • Basic algorithms for classification and clustering
  • Bag of Words methods

6.      Neural networks in image processing

  • Deep learning/convolutional classification and autoencoder networks


Proposed reading

·         William K. Pratt - Digital Image Processing, John Wiley & Sons

·         Richard Szeliski: Computer Vision, Algorithms and Applications, Springer-Verlag

·         Cyganek & Siebert: An Introduction to 3D Computer Vision Techniques and Algorithms, John Wiley & Sons

·         Kristen Grauman, Bastian Leibe: Visual Object Recognition

·         Zhu, H., Meng, F., Cai, J., & Lu, S. (2016). Beyond pixels: A comprehensive survey from bottom-up to semantic image segmentation and cosegmentation. Journal of Visual Communication and Image Representation, 34, 12-27.

·         Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning (Adaptive Computation and Machine Learning series).