An evolutionary approach to feature function generation in application to biomedical image patterns

ABSTRACT

A mechanism involving evolutionary genetic programming (GP) and the expectation maximization algorithm (EM) is proposed to generate feature functions, based on the primitive features, for an image pattern recognition system on the diagnosis of the disease OPMD. Experiments show that the propose algorithm achieves an average performance of 90.20% recognition rate on diagnosis, while reducing the number of feature dimensions from 11 primitive features to the space of a single generated feature.

REFERENCES

• 1: Rafael, R.C. Digital Image Processing. Addison-Wesley, Reading, MA, 2002.
• 2: Thomas M. Mitchell, Machine Learning, McGraw-Hill, Inc., New York, NY, 1997
• 3: John R. Koza, Genetic programming II: automatic discovery of reusable programs, MIT Press, Cambridge, MA, 1994
• 4: Mike James, Classification algorithms, Wiley-Interscience, New York, NY, 1985

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.2 Design Methodology
          Subjects: Feature evaluation and selection

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.8 Problem Solving, Control Methods, and Search
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.7 Feature Measurement
          Subjects: Texture; Moments

General Terms:
Algorithms, Design, Experimentation

Keywords:
artificial intelligence, feature generation, gaussian mixture estimation, genetic programming, hybrid evolutionary algorithm, texture analysis, the expectation maximization algorithm