首页> 外文会议>International Progress on Wavelet Analysis and Active Media Technology(IPWAAMT) vol.1; ; >FACE DETECTION IN COLOR IMAGES BASED ON MULTI-RESOLUTION SUB-IMAGE FUSION
【24h】

FACE DETECTION IN COLOR IMAGES BASED ON MULTI-RESOLUTION SUB-IMAGE FUSION

机译:基于多分辨率子图像融合的彩色图像人脸检测

获取原文
获取原文并翻译 | 示例

摘要

A face detection method in color Images, using multi-resolution sub-images Fusion and face modes, is proposed. Firstly the skin image is obtained by two different color modes (HSI and YCbCr). Secondly, Multi-Resolution Sub-image is gained by wavelet analysis of skin area image. Thirdly Fusion image can be obtained by sub-image LH and HL according to pixel fusion criterion. Candidate face area can be detected in fusion image. Finally face images can be validated through template matching method. Experiment result shows that, detection rate of faces in a complex background is high, but several faces in a group photo would be detected as one face if they are too close.
机译:提出了一种利用多分辨率子图像融合和人脸模式的彩色图像人脸检测方法。首先,通过两种不同的颜色模式(HSI和YCbCr)获得皮肤图像。其次,通过对皮肤区域图像进行小波分析得到多分辨率子图像。第三,可以根据像素融合标准,通过子图像LH和HL获得融合图像。可以在融合图像中检测出候选面部区域。最后,可以通过模板匹配方法对人脸图像进行验证。实验结果表明,复杂背景下的人脸检测率较高,但如果过于靠近,则将集体照片中的多个人脸检测为一个人脸。

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