Outline CP467 Image Processing and Pattern Recognition Fall 2012
Instructor: Hongbing Fan  Email: h f a n @ w l u . c a  Office: N2081 Phone: (519)884-0710 ext.2823

Lectures:

TR 2:30 -3:50   Room: Science Building N1059
Office Hours: TR 16:00 - 17:00 p.m. or by appointment
Textbook: Textbook: Digital Image Processing 3/e by Gonzalez and Woods
Optional textbook: Pattern Recognition, Fourth Edition Authors: Sergios Theodoridis and Konstantinos Koutroumbas 

Web page:

 http://bohr.wlu.ca/hfan/cp467
Prerequisite: CP213, MA240 (or equivalent), MA255 recommended


 
Objectives

To learn and practice the principles, methods and algorithms in image processing and pattern recognition, to gain the fundamental skills in image acquistion, processing and pattern recognition for related hardware and software development.

Topics

  1. Digital images fundamentals

    • Image acquisition

    • Image sampling and digitization

    • Image representation, compressing and storage

  2. Image Enhancement

    • Intensity transformations in spatial domain

      • Histogram processing

      • Spatial filtering: convolution, smoothing, sharpening

    • Transformations in frequency domain

      • Discrete Fourier Transformation (DFT) and Fast Fourier Transformation (FFT)
      • Frequency domain filtering: smoothing with lowpass filters, sharpening with highpass filters

    • Image restoration: spatial noise reduction, periodic noise reduction

    • Wavelet transformation for multiresolution processing

  3. Image processing for pattern recognition

    • Image segmentation:

    • Image representation and description

  4. Pattern Recognition

    • Feature extraction, feature selection

    • Linear and non-linear classifiers
       
    • Clustering

Grading Scheme

  • Assignments 40%,  project 15%, final 40%, class participation and contribution 5%. 

Assignments are to be done individually and to be submitted before the due time. Project can be done by a team of at most three members. Late submission will not be marked except approved by the instructor in advance. Class participation is mandatory. Class contributions (ask/answer questions, discussions, and demos) are encouraged.

 Final letter grades are obtained by converting the numerical percentage grades according to the following table:

A+

A

A-

B+

B

B-

C+

C

C-

D+

D

D-

F

90-100

85-89

80-84

77-79

73-77

70-72

67-69

63-66

60-62

57-59

53-56

50-52

0-49

The instructor reserves a right to adjust the cut-off for final letter grade up or down by 1.0%.

Additional information