51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频

設(shè)為首頁 |  加入收藏
首頁首頁 期刊簡介 消息通知 編委會 電子期刊 投稿須知 廣告合作 聯(lián)系我們
基于重建圖像信噪比特征的臉部位置檢測方法

Detection of Face Position Based on SNR of Reconstructed Images

作者: 郁洪強    劉瑾    周鵬 
單位:天津市醫(yī)療器械技術(shù)審評中心(天津300191)
關(guān)鍵詞: 人臉檢測;特征臉;信噪比;圖像重建 
分類號:
出版年·卷·期(頁碼):2011·30·4(368-372)
摘要:

目的 通過研究找到一種基于重建圖像信噪比(signal-to-noise,SNR)的人臉檢測方法,從而提高在圖片中找到人臉所在位置的準確率。方法 首先通過圖像向特征臉空間投影得到重建圖像,然后利用重建圖像的SNR進行人臉檢測。經(jīng)實驗發(fā)現(xiàn),在對一幅圖像進行掃描的過程中,人臉的位置既是信噪比值橫向的極大值點,又是縱向的極大值點,且在單幅人臉圖像中,人臉處的SNR為全局極大值,因此可以利用該動態(tài)規(guī)律準確地找到人臉位置。結(jié)果 利用上述方法對耶魯人臉庫100張人臉和自拍的50張人臉進行實驗,結(jié)果表明,通過搜索全局最大值確定出人臉的位置,準確率為98%。進一步,利用上述方法對已經(jīng)得到的人臉進行第二次搜索,找到不包含頭發(fā)等周圍圖像的中心臉部區(qū)域。最后,通過圖像銳化和模板匹配相結(jié)合的方法找到眼睛位置,旋轉(zhuǎn)圖像使雙眼在同一水平位置上,并根據(jù)比例關(guān)系可重新精確地劃出中心人臉區(qū)域,眼睛定位準確率達96%。結(jié)論 基于重建圖像SNR的人臉檢測方法可以提高尋找人臉的準確率,因此該方法是一種簡單而有效的臉部位置檢測方法。

Objective A new detection method of face position based on signal-to-noise (SNR) of reconstructed images was developed,which can improve the accuracy of finding the face position in the image.Methods The SNR of reconstructed images was acquired by projecting to eigenface space and used in the face detection.Correspondingly,the face was detected according to the dynamic change of SNR.The results of experiments showed that the SNR of faces in whole image was the maximum when the image was scanned horizontally and vertically.If the image only includes one face,then SNR of the face was global maximum.Results One hundred images from face database of Yale University and 50 images from photos acquired by camera were detected.The correct rate of the detection reached to 98%.Furthermore,we scaned the acquired faces by above method again,and then the center zone of face was marked without hair and so on.In this face,the positions of eyes were determined by sharpening and template matching.The face would be rotated in order to make eyes being horizontal,then the face were cropped again according to the proportions.The correction rata of eye position detection reached to 96%.Conclusions The detection method based on SNR of reconstructed images improves the accuracy of finding the face position in the image,and it is simple and efficient for face position detection.

參考文獻:

[1]陳愛武,夏利民,趙桂敏.基于Boosting方法的人臉檢測[J].計算機工程與應(yīng)用,2004,40(3):50-52.
[2]李剛,高政.人臉檢測技術(shù)研究與發(fā)展[J].計算機與現(xiàn)代化,2003(4):7-9.
[3]Savvides M,Kumar BVKV,Khosla PK.Eigenphases vs.eigenfaces.Pattern Recognition[C].Proceedings of the 17th International Conference,20043(23-26):810-813.
[4]Lin KH,Lam KM,Xie XD,et al.An efficient human face indexing scheme using eigenfaces[C].Neural Networks and Signal Processing,Proceedings of the 2003 International Conference,2003,2(14-17):920-923.
[5]Shakunaga T,Sakaue F,Shigenari K.Robust face recognition by combining projection-based image correction and decomposed eigenface[C].Automatic Face and Gesture Recognition,2004.Proceedings,Sixth IEEE International Conference,2004,(17-19):241-247.
[6]Yang GZ,Huang TS.Human face detection in a complex background[J].Pattern Recog,1994,27:53-63.
[7]Pentland A,Moghaddam B,Starner T.View based and modular eigenspace for face recognition[C].Proc IEEE Computer Society Conf on Computer Vision and Pattern Recognition,1994:84-91.
[8]Belhumeur PN,Hespanha JP,Kriegman DJ.Eigenfaces vs.Fisherfaces:recognition using class specific linear projection[J].Pattern Analysis and Machine Intelligence,IEEE Trans on,1997,19(7):711-720.

服務(wù)與反饋:
文章下載】【加入收藏
提示:您還未登錄,請登錄!點此登錄
 
友情鏈接  
地址:北京安定門外安貞醫(yī)院內(nèi)北京生物醫(yī)學(xué)工程編輯部
電話:010-64456508  傳真:010-64456661
電子郵箱:[email protected]