### 摘要

Polygonal approximation is an important issue in pattern recognition and image processing. A new polygonal approximation method using genetic algorithm is proposed. Genetic algorithms are search algorithms based on the mechanisms of natural selection and natural genetics. The chromosome is used to represent an approximated polygon and is represented by a binary string. Each bit, called gene, represents a curve point. A gene with value 1 indicates that the corresponding curve point is a breakpoint of the approximated polygon. The objective function is defined as the total arc-to-chord deviation between the curve and the polygon. The proposed method is compared to two existing methods proposed by Teh-Chin [5] and Ansari-Huang [6]. Some experimental results depict the superiority of the proposed approach.

原文 | English |
---|---|

頁面 | 469-474 |

頁數 | 6 |

出版狀態 | Published - 1996 一月 1 |

事件 | Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96 - Nagoya, Jpn 持續時間: 1996 五月 20 → 1996 五月 22 |

### Other

Other | Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96 |
---|---|

城市 | Nagoya, Jpn |

期間 | 96-05-20 → 96-05-22 |

### 指紋

### All Science Journal Classification (ASJC) codes

- Engineering(all)

### 引用此文

*Polygonal approximation using genetic algorithm*. 469-474. 論文發表於 Proceedings of the 1996 IEEE International Conference on Evolutionary Computation, ICEC'96, Nagoya, Jpn, .

}

**Polygonal approximation using genetic algorithm.** / Huang, Shu Chien; Sun, Yung Nien.

研究成果: Paper

TY - CONF

T1 - Polygonal approximation using genetic algorithm

AU - Huang, Shu Chien

AU - Sun, Yung Nien

PY - 1996/1/1

Y1 - 1996/1/1

N2 - Polygonal approximation is an important issue in pattern recognition and image processing. A new polygonal approximation method using genetic algorithm is proposed. Genetic algorithms are search algorithms based on the mechanisms of natural selection and natural genetics. The chromosome is used to represent an approximated polygon and is represented by a binary string. Each bit, called gene, represents a curve point. A gene with value 1 indicates that the corresponding curve point is a breakpoint of the approximated polygon. The objective function is defined as the total arc-to-chord deviation between the curve and the polygon. The proposed method is compared to two existing methods proposed by Teh-Chin [5] and Ansari-Huang [6]. Some experimental results depict the superiority of the proposed approach.

AB - Polygonal approximation is an important issue in pattern recognition and image processing. A new polygonal approximation method using genetic algorithm is proposed. Genetic algorithms are search algorithms based on the mechanisms of natural selection and natural genetics. The chromosome is used to represent an approximated polygon and is represented by a binary string. Each bit, called gene, represents a curve point. A gene with value 1 indicates that the corresponding curve point is a breakpoint of the approximated polygon. The objective function is defined as the total arc-to-chord deviation between the curve and the polygon. The proposed method is compared to two existing methods proposed by Teh-Chin [5] and Ansari-Huang [6]. Some experimental results depict the superiority of the proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=0029710028&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029710028&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029710028

SP - 469

EP - 474

ER -