Feature synthesis and analysis by evolutionary computation for object detection and recognition

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@PhdThesis{Yingqiang_Lin:thesis,
  author =       "Yingqiang Lin",
  title =        "Feature synthesis and analysis by evolutionary
                 computation for object detection and recognition",
  school =       "University of California, Riverside",
  year =         "2003",
  address =      "USA",
  month =        jun,
  keywords =     "genetic algorithms, genetic programming, coevolution,
                 Applied sciences, Object detection, Minimum description
                 length, Computer science",
  URL =          "http://phdtree.org/pdf/25708813-feature-synthesis-and-analysis-by-evolutionary-computation-for-object-detection-and-recognition/",
  URL =          "http://dl.acm.org/citation.cfm?id=979049",
  URL =          "http://search.proquest.com/docview/305342764",
  size =         "168 pages",
  abstract =     "This dissertation investigates evolutionary
                 computational techniques such as genetic programming
                 (GP), coevolutionary genetic programming (CGP) and
                 genetic algorithm (GA) to automate the synthesis and
                 analysis of object detection and recognition
                 systems.

                 First, this dissertation shows the efficacy of GP and
                 CGP in synthesizing effective composite operators and
                 composite features from domain-independent primitive
                 image processing operations and primitive features for
                 object detection and recognition. Based on GP and CGP's
                 ability of synthesizing effective features from simple
                 features not specifically designed for a particular
                 kind of imagery, the cost of building object detection
                 and recognition systems is lowered and the flexibility
                 of the systems is increased. More importantly, it shows
                 that a large amount of unconventional features are
                 explored by GP and CGP and these unconventional
                 features yield exceptionally good detection and
                 recognition performances in some cases, overcoming the
                 human experts' limitation of considering only a small
                 number of conventional features.

                 Second, smart crossover, smart mutation and a new
                 fitness function based on minimum description length
                 (MDL) principle are designed to improve the efficiency
                 of genetic programming. Smart crossover and smart
                 mutation are designed to identify and keep the
                 effective components of composite operators from being
                 disrupted and a MDL-based fitness function is proposed
                 to address the well-known code bloat problem of GP
                 without imposing severe restriction on the GP search.
                 Compared to normal GP, smart GP algorithm with smart
                 crossover, smart mutation and a MDL-based fitness
                 function finds effective composite operators more
                 quickly and the composite operators learned by smart GP
                 algorithm have smaller size, greatly reducing both the
                 computational expense during testing and the
                 possibility of overfitting during training.

                 Finally, a new MDL-based fitness function is proposed
                 to improve the genetic algorithm's performance on
                 feature selection for object detection and recognition.
                 The MDL-based fitness function incorporates the number
                 of features selected into the fitness evaluation
                 process and prevents GA from selecting a large number
                 of features to overfit the training data. The goal is
                 to select a small set of features with good
                 discrimination performances on both training and unseen
                 testing data to reduce the possibility of overfitting
                 the training data during training and the computational
                 burden during testing.",
  notes =        "SAR image, region of interest. Paved road, lake, tank
                 t72, river, grass, brdm2, d7, t62, zil, zsu

                 Supervisor Bir Bhanu

                 Senior Research Engineer, Trend Micro Inc UMI Number:
                 3096772 ProQuest Order No. 3096772 OCLC: 53984756",
}

Genetic Programming entries for Yingqiang Lin

Citations