Program Size and Pixel Statistics in Genetic Programming for Object Detection

Abstract

AbstractThis paper describes an approach to the use of genetic programming for object detection problems. In this approach, local region pixel statistics are used to form three terminal sets. The function set is constructed by the four standard arithmetic operators and a conditional operator. A multi-objective fitness function is constructed based on detection rate, false alarm rate, false alarm area and program size. This approach is applied to three object detection problems of increasing difficulty. The results suggest that the concentric circular pixel statistics are more effective than the square features for the coin detection problems. The fitness function with program size is more effective and more efficient for these object detection problems and the evolved genetic programs using this fitness function are much shorter and easier to interpret.KeywordsFalse AlarmGenetic ProgramFalse Alarm RateObject DetectionDetection ProblemThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.