...
首页> 外文期刊>Journal of computational and theoretical nanoscience >Color, Textures and Shape Descriptor Based Cervical Cancer Classification System of Pap Smear Images
【24h】

Color, Textures and Shape Descriptor Based Cervical Cancer Classification System of Pap Smear Images

机译:基于颜色,纹理和形状描述符的PAP涂片图像的宫颈癌分类系统

获取原文
获取原文并翻译 | 示例
           

摘要

Cervical cancer is the most common form of cancer in women under 35 years of age and the second most commonly occurring cancer in women of all ages, worldwide. Pap test is the most popular and effective screening test for cervical cancer. In this research article, we have developed,a cervical cancer classification system based on color, texture and shape based features with hybrid kernel based support vector machine using Pap smear images. In feature extraction, multiple features are extracted using color map, shape descriptor and Gabor filter based orientation image.This system classifies the Pap smear cells into normal and cancer classes using Hybrid-SVM. The performance of the proposed algorithm is tested and compared to other algorithms on public image database. The overall classification accuracy of the proposed CSID + HKSVM is 94%, but the existingmethods CSID + SVM, CSID + RBF and CSID + FFNN produce 90%, 84% and 72% respectively.
机译:宫颈癌是35岁以下女性中最常见的癌症形式,以及全球所有年龄段的妇女最常见的癌症。 PAP测试是宫颈癌最受欢迎和有效的筛查试验。 在本研究文章中,我们开发了一种基于颜色,纹理和形状的宫颈癌分类系统,具有使用PAP涂片图像的混合内核基于混合内核的支持向量机。 在特征提取中,使用颜色图,形状描述符和基于Gabor滤波器的取向图像提取多个特征。本系统使用杂交-SVM将PAP涂抹细胞分类为正常和癌症类别。 测试了所提出的算法的性能,并与公共图像数据库上的其他算法进行了测试。 所提出的CSID + HKSVM的总体分类准确性为94%,但现有的方法CSID + SVM,CSID + RBF和CSID + FFNN分别产生90%,84%和72%。

著录项

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