Project CellNet: Evolving An Autonomous Pattern Recognizer

@article{Kharma2004ProjectCE,
  title={Project CellNet: Evolving An Autonomous Pattern Recognizer},
  author={Nawwaf N. Kharma and Taras Kowaliw and E. Clement and Christopher Jensen and Azdoud Youssef and Jie Yao},
  journal={Int. J. Pattern Recognit. Artif. Intell.},
  year={2004},
  volume={18},
  pages={1039-1056}
}
We describe the desire for a black box approach to pattern classification: a generic Autonomous Pattern Recognizer, which is capable of self-adapting to specific alphabets without human intervention. The CellNet software system is introduced, an evolutionary system that optimizes a set of pattern-recognizing agents relative to a provided set of features and a given pattern database. CellNet utilizes a new genetic operator designed to facilitate a canalization of development: Merger. CellNet… 

CellNet CoEv : Co-Evolving Robust Pattern Recognizers

An evolutionary model of classifier synthesis is presented. The CellNet system for generating binary pattern classifiers is used as a base for experimentation [5]. CellNet is extended to include a

CellNet Co-Ev: Evolving Better Pattern Recognizers Using Competitive Co-evolution

The CellNet system for generating binary classifiers is extended to include a competitive co- evolutionary Genetic Algorithm, where patterns evolve as well as classifiers; This is facilitated by the addition of a set of topologically-invariant camouflage functions, through which images may disguise themselves.

Using Competitive Co-evolution to Evolve Better Pattern Recognisers

Application to the CEDAR database of handwritten characters shows an increase in the reliability of the evolution of recognisers, as well as in the elimination of over-fitting, relative to the original CellNet software.

Networks of transform-based evolvable features for object recognition

This work is concerned with the addition of algorithmic depth to a genetic programming (GP) system, hypothesizing that it will improve the capacity for solving problems that require high-level, hierarchical reasoning.

The unconstrained automated generation of cell image features for medical diagnosis

An extension to a non-linear offline method for generating features for image recognition that shows good promise for the creation of novel image features in situations where pixel-level features are complex or unknown, such as medical images is introduced.

On the Role of Genetic Algorithms in the Pattern Recognition Task of Classification

A genetic algorithm is developed which optimizes MATLAB classifiers and a variable length genetic algorithm which does classification based entirely on boolean logic is developed.

Evolving novel image features using Genetic Programming-based image transforms

The notion of a Transform-based Evolvable Feature (TEF), a moment value extracted from a GP-transformed image, used in a classification task, and it is shown that the inclusion of a single TEF allows for significantly superior classification relative to predefined features alone.

A Coevolution Algorithm in the Image Recognition System

This result shows that competitive co evolution and camouflage are expected to aid in the problem of over fitting and reliability without expert tuning, and also in the generation of a larger and more diverse data set.

Recognizing Handwriting Indian Numbers using Neural Network

The goal was achieved by designing a neural network that can recognize digits with an average generalization ratio of recognizing 92.31 for digit that the neural never been trained on.

Image Classification with Genetic Programming: Building a Stage 1 Computer Aided Detector for Breast Cancer

An automated work-flow that begins with image processing and culminates in the evolution of classification models which identify suspicious segments of mammograms, which is to evolve classifiers which detect as many cancers as possible but which are not overly conservative.

References

SHOWING 1-10 OF 33 REFERENCES

Neocognitron based handwriting recognition system performance tuning using genetic algorithm

  • D. YeungY. T. ChengH. FongK. Chung
  • Computer Science
    SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218)
  • 1998
A parameter tuning methodology based on a sensitivity analysis of the neocognitron model is presented, and the off-line handwritten numeral recognition with supervised learning is chosen to be the demonstrated application problem and genetic algorithm is used to select parameters leading to improved recognition results.

Fast generic selection of features for neural network classifiers

The authors describe experiments using a genetic algorithm for feature selection in the context of neural network classifiers, specifically, counterpropagation networks, and propose a method called the training set sampling, which selects feature sets that are as good as and occasionally better for counterPropagation than those chosen by an evaluation that uses the entire training set.

Feature selection for handwritten Chinese character recognition based on genetic algorithms

  • D. ShiW. ShuHaitao Liu
  • Computer Science
    SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218)
  • 1998
It is concluded that the GA-based method proposed in this paper is promising to solve the feature selection problems in a multidimensional space.

Automatic Feature Design for Optical Character Recognition Using an Evolutionary Search Procedure

  • F. Stentiford
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 1985
An automatic evolutionary search is applied to the problem of feature extraction in an OCR application. A performance measure based on feature independence is used to generate features which do not

Robust feature selection algorithms

  • H. VafaieK. A. Jong
  • Computer Science
    Proceedings of 1993 IEEE Conference on Tools with Al (TAI-93)
  • 1993
Results are presented which suggested that genetic algorithms can be used to increase the robustness of feature selection algorithms without a significant decrease in compuational efficiency.

Feature Selection for Classification

Recognition of Handwritten Digits Using Deformable

Deformable models are used to recognize handwritten characters which have a great variety of handwriting styles. The overall character shape is modeled by a B-spline and individual pixels are modeled

Investigation of image feature extraction by a genetic algorithm

The implementation and performance of a genetic algorithm which generates image feature extraction algorithms for remote sensing applications and the basis set of primitive image operators and chromosomal representation of a complete algorithm are described.