利用Matlab实现人脸检测与人脸马赛克
|
摘要
人脸检测是基于人的脸部特征信息进行身份检测的一种生物检测技术。马赛克,即用模糊的连续四方片状阴影对图片处理。本文利用Matlab软件,通过图像分割、腐蚀膨胀、图片放缩等基本方式对给定图片进行人脸检测,如确认为人脸则将其用矩形框出,并将框内的人脸自动打码,实现人脸检测和人脸马赛克。实验表明,本方法能成功检测出人脸,检测准确率高达96.05%;借助Matlab软件进行计时,每张600×400的照片完成人脸检测并马赛克过程不超过24 s。
Face detection is a biological detection technology based on human facial feature information for identity detection. Mosaic, that is, the image is processed with fuzzy continuous square-shaped shadows. This article use Matlab software to perform face detection on a given picture at first. If it is confirmed that the face will be out of a rectangular frame, the face inside the frame will be automatically coded to achieve face detection and face mosaic. This experiment can successfully detect human face, and the accuracy is as high as 96.05%. Timing with matlab software, the face detection and Mosaic for each600×400 photos are completed in 24 seconds.
Face detection is a biological detection technology based on human facial feature information for identity detection. Mosaic, that is, the image is processed with fuzzy continuous square-shaped shadows. This article use Matlab software to perform face detection on a given picture at first. If it is confirmed that the face will be out of a rectangular frame, the face inside the frame will be automatically coded to achieve face detection and face mosaic. This experiment can successfully detect human face, and the accuracy is as high as 96.05%. Timing with matlab software, the face detection and Mosaic for each600×400 photos are completed in 24 seconds.
引文
[1]韩贵金,杨嘉宁.基于改进卷积神经网络的人脸检测测算法探析[J].陕西教育,2017(25):64-65.
[2]ZHAO W,CHELLAPA R,PHILIPS P J,et al.Face recognition:a literature survey[J].ACM Computing Surveys,2003,35(4):399-458.
[3]马艳.基于颜色与模板匹配的人脸检测方法[D].大连:大连理工大学,2006.
[4]EL-BAKRY H M,MASTORAKIS N.A novel model of neural networks for fast data detection[J].WSEAS Transactions on Computers,2006,5(8):1773-1780.
[5]HAUSNER A.Simulating decorative mosaics[M].New York:ACM Press,2001:207-214.
[6]DOBASHI Y,HAGA T,JOHAN H,et al.A method for creating mosaic images using voronoi diagram[C].Proceeding of Eurographics(Short Presentations),2002:341-348.
[7]ORCHARD J,KAPLAN C S.Cut-out image mosaics[C].Proceedings of the 6th International Symposium on Non-photorealistic Animation and Rendering,2008:79-87.
[8]LIU Y,VEKSLER O,JUAN O.Generating classic mosaics with graph cuts[J].Computer Graphics Forum,2010,29(8):2387-2399.
[9]姚东明,马川,于溪,等.一种高效的人脸马赛克方法[J].软件导刊,2017,16(3):167-169.
[10]张懿,刘旭,李海峰,等.数字RGB与YCbCr颜色空间转换的精度[J].江南大学学报(自然科学版),2007(2):200-202.
[11]王曦.基于高斯肤色模型的图像皮肤区域分割算法研究[J].工程技术研究,2010(8):238-239.
[2]ZHAO W,CHELLAPA R,PHILIPS P J,et al.Face recognition:a literature survey[J].ACM Computing Surveys,2003,35(4):399-458.
[3]马艳.基于颜色与模板匹配的人脸检测方法[D].大连:大连理工大学,2006.
[4]EL-BAKRY H M,MASTORAKIS N.A novel model of neural networks for fast data detection[J].WSEAS Transactions on Computers,2006,5(8):1773-1780.
[5]HAUSNER A.Simulating decorative mosaics[M].New York:ACM Press,2001:207-214.
[6]DOBASHI Y,HAGA T,JOHAN H,et al.A method for creating mosaic images using voronoi diagram[C].Proceeding of Eurographics(Short Presentations),2002:341-348.
[7]ORCHARD J,KAPLAN C S.Cut-out image mosaics[C].Proceedings of the 6th International Symposium on Non-photorealistic Animation and Rendering,2008:79-87.
[8]LIU Y,VEKSLER O,JUAN O.Generating classic mosaics with graph cuts[J].Computer Graphics Forum,2010,29(8):2387-2399.
[9]姚东明,马川,于溪,等.一种高效的人脸马赛克方法[J].软件导刊,2017,16(3):167-169.
[10]张懿,刘旭,李海峰,等.数字RGB与YCbCr颜色空间转换的精度[J].江南大学学报(自然科学版),2007(2):200-202.
[11]王曦.基于高斯肤色模型的图像皮肤区域分割算法研究[J].工程技术研究,2010(8):238-239.