• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International Journal of Innovative Computing Information and Control >EFFICIENT GENDER CLASSIFICATION USING OPTIMIZATION OF HYBRID CLASSIFIERS USING GENETIC ALGORITHM
【24h】

EFFICIENT GENDER CLASSIFICATION USING OPTIMIZATION OF HYBRID CLASSIFIERS USING GENETIC ALGORITHM

机译：利用遗传算法优化混合分类器的高效性别分类

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Classification is an important area of research which presents an immense potential in the form of its applicability and usefulness. Gender classification is one such application of classification which has gained a great deal of attention recently. However, the techniques presented so far in literature dealing with gender classification present a significant room for improvement. The paper presents an efficient feature based gender classification technique. In this technique, a face detection mechanism has been used, which excludes unwanted area from the image. This significantly reduces image size, thus enabling to classify more efficiently. Classifier ensemble has been proven to be an effective technique which considerably enhances the performance of classifiers. The proposed technique uses Genetic algorithm based optimized ensemble classification which provides a more accurate classification as compare to the state-of-the-art techniques in terms of various quantitative measures. The proposed method is tested on the standard facial images database and results have been compiled. The experimental results on this database have been compared with results achieved by using existing methods. The comparison indicates that the proposed technique gives superior performance to the other competitive methods based on well known quantitative measures.
机译：分类是一个重要的研究领域，以其适用性和实用性的形式展现出巨大的潜力。性别分类就是这种分类的一种应用，近来引起了极大的关注。但是，到目前为止，有关性别分类的文献中提出的技术仍存在很大的改进空间。本文提出了一种基于特征的有效性别分类技术。在这种技术中，已经使用了面部检测机制，该机制从图像中排除了不需要的区域。这显着减小了图像尺寸，从而使分类更加有效。分类器集成已被证明是一种有效的技术，可以大大提高分类器的性能。所提出的技术使用了基于遗传算法的优化集成分类，与各种定量度量相比，该分类与最新技术相比提供了更准确的分类。该方法在标准的人脸图像数据库上进行了测试，结果进行了汇编。该数据库上的实验结果已与使用现有方法获得的结果进行了比较。比较表明，基于众所周知的定量方法，所提出的技术比其他竞争方法具有更好的性能。

著录项

  • 来源
  • 作者

    Muhammad Nazir; M. Arfan Jaffar; Ayaz Hussain; Anwar M. Mirza;

  • 作者单位

    Department of Computer Science National University of Computer and Emerging Sciences A.K Brohi Road, Islamabad 44000, Pakistan;

    Department of Computer Science National University of Computer and Emerging Sciences A.K Brohi Road, Islamabad 44000, Pakistan,Department of Mechatronics Gwangju Institute of Science and Technology 1 Oryong-dong, Buk-gu, Gwangju 500-712, South Korea;

    Department of Computer Science International Islamic University Islamabad, Pakistan;

    Department of Computer Science National University of Computer and Emerging Sciences A.K Brohi Road, Islamabad 44000, Pakistan,Department of Computer Engineering College of Computer and Information Sciences King Saud University P.O.Box: 2454, Riyadh 11451, Saudi Arabia;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    gender classification; feature extraction; genetic algorithms; ensemble classification;

    机译：性别分类;特征提取;遗传算法;整体分类;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号