首页> 外文OA文献 >A novel approach to nose-tip and eye corners detection using H-K Curvature Analysis in case of 3D images
【2h】

A novel approach to nose-tip and eye corners detection using H-K Curvature Analysis in case of 3D images

机译:一种使用H-K检测鼻尖和眼角的新方法   三维图像情形下的曲率分析

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。

摘要

In this paper we present a novel method that combines a HK curvature-basedapproach for three-dimensional (3D) face detection in different poses (X-axis,Y-axis and Z-axis). Salient face features, such as the eyes and nose, aredetected through an analysis of the curvature of the entire facial surface. Allthe experiments have been performed on the FRAV3D Database. After applying theproposed algorithm to the 3D facial surface we have obtained considerably goodresults i.e. on 752 3D face images our method detected the eye corners for 543face images, thus giving a 72.20% of eye corners detection and 743 face imagesfor nose-tip detection thus giving a 98.80% of good nose tip localization
机译:在本文中,我们提出了一种新颖的方法,该方法结合了基于HK曲率的方法在不同姿势(X轴,Y轴和Z轴)中进行三维(3D)人脸检测。通过分析整个面部表面的曲率,可以检测出诸如眼睛和鼻子等明显的面部特征。所有的实验都在FRAV3D数据库上进行。将建议的算法应用到3D面部表面后,我们获得了相当不错的结果,即在752个3D面部图像上,我们的方法检测到543个面部图像的眼角,从而提供了72.20%的眼角检测和743个面部图像的鼻尖检测,从而获得了良好的鼻尖定位的98.80%

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
代理获取

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