• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Computational Science and Its Applications(ICCSA 2004) pt.4; 20040514-20040517; Assisi; IT >On Extraction of Facial Features from Color Images
【24h】

On Extraction of Facial Features from Color Images

机译：从彩色图像中提取人脸特征

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

Human face detection is one of the most important processes in applications such as video surveillance, human computer interface, face recognition, and image database management. Algorithms have been discussed in lots of papers about face detection and face recognition. But it is well known that their implementation is not easy. Due to variations in illumination, background, visual angle and facial expressions, the problem of machine face detection is complex. Face detection algorithms have primary factors that decrease a detection ratio: variation by lighting effect, location and rotation, distance of object and complex background. We propose a face detection algorithm for color images in the presence of varying lighting conditions as well as complex background. We use the YC_bC_r color space since it is widely used in video compression standards and multimedia streaming services. Our method detects skin regions over the entire image, and then generates face candidate based on the spatial arrangement of the skin patches. The algorithm constructs eyes, mouth, nose, and boundary maps for verifying each face candidate.
机译：人脸检测是视频监控，人机界面，人脸识别和图像数据库管理等应用程序中最重要的过程之一。许多关于面部检测和面部识别的论文都讨论了算法。但是众所周知，实现起来并不容易。由于照明，背景，视角和面部表情的变化，机器面部检测的问题很复杂。人脸检测算法具有降低检测率的主要因素：光照效果，位置和旋转，物体的距离和复杂背景的变化。我们提出了在光照条件不同以及背景复杂的情况下用于彩色图像的面部检测算法。我们使用YC_bC_r颜色空间，因为它已广泛用于视频压缩标准和多媒体流服务中。我们的方法检测整个图像上的皮肤区域，然后根据皮肤斑块的空间排列生成面部候选对象。该算法构造眼睛，嘴巴，鼻子和边界图，以验证每个候选脸部。

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