Java 样本人脸识别
声明:本页面是StackOverFlow热门问题的中英对照翻译,遵循CC BY-SA 4.0协议,如果您需要使用它,必须同样遵循CC BY-SA许可,注明原文地址和作者信息,同时你必须将它归于原作者(不是我):StackOverFlow
原文地址: http://stackoverflow.com/questions/20407934/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
Java Sample Face Recognition
提问by Matt Brown
I'm trying to develop a system whereby somebody can take a picture of somebody's face and, after the image has been sent to a remote server, the client will be able to read information about the person.
我正在尝试开发一个系统,使某人可以拍摄某人的脸部照片,并且在将图像发送到远程服务器后,客户端将能够读取有关此人的信息。
I have, previously, experimented with JavaCV, however, I have found it too inaccurate for my purpose. I have tried these JavaCV algorithms so far:
我之前曾尝试过 JavaCV,但是,我发现它对我的目的来说太不准确了。到目前为止,我已经尝试过这些 JavaCV 算法:
- Fisher Face Recognition
- Eigen Face Recognition
- LBPH Face Recognition
- 费雪人脸识别
- 特征人脸识别
- LBPH人脸识别
However, I need to build a facial recognition system. This will be 'standalone' and will not be run on Android (for example). I need some help in choosing the correct java sdk/library (and also whether commercial solutions, such as 'Cybula', 'NeuroTechnology' and 'Sensible Vision' can be avoided).
但是,我需要建立一个面部识别系统。这将是“独立的”并且不会在 Android 上运行(例如)。我需要一些帮助来选择正确的 java sdk/库(以及是否可以避免商业解决方案,例如“Cybula”、“NeuroTechnology”和“Sensible Vision”)。
Any help would be much appreciated!
任何帮助将非常感激!
Thanks,
谢谢,
Matt
马特
采纳答案by mwhs
Face recognitionis only the last step in the process. To solve this problem, you first have to find the face in the picture (face detection) and then in the detected face you will have to extract the characteristics of the face depending on the quality of the picture, light/flash used, facial/sideways, ... (feature extraction).
人脸识别只是这个过程的最后一步。要解决这个问题,您首先必须在图片中找到人脸(人脸检测),然后在检测到的人脸中,您必须根据图片质量、使用的光线/闪光灯、面部/侧身,...(特征提取)。
Process chain:
流程链:
face detection-> feature extraction-> face recognition
人脸检测->特征提取->人脸识别
There are probably a hundred publications for each of these topics. It's up to you to assemble something.
这些主题中的每一个都可能有一百种出版物。由你来组装一些东西。
Also notable: this is not the kind of problem that has one global best solution. The chosen approach is at most optimal for the one special problem that you are trying to solve.
同样值得注意的是:这不是那种只有一个全局最佳解决方案的问题。所选择的方法至多是您要解决的一个特殊问题的最佳选择。
Other keywords that you might want to consider:
您可能要考虑的其他关键字:
- face tracking
- pose estimation
- facial feature tracking
- emotion recognition
- holistic templates
- feature geometry
- 人脸追踪
- 姿态估计
- 面部特征跟踪
- 情绪识别
- 整体模板
- 特征几何
Also noteable: most SDKs that say they do face recognition in reality only do face detection (and sometimes (rarely) feature extraction). To do face recognition you need a huge database of known faces (face features), which of course most "vendors" don't have (not talking about all those agencies though... LOL).
同样值得注意的是:大多数声称他们在现实中进行人脸识别的 SDK 只进行人脸检测(有时(很少)进行特征提取)。要进行人脸识别,您需要一个巨大的已知人脸(人脸特征)数据库,当然大多数“供应商”没有(尽管不是在谈论所有这些机构......哈哈)。
回答by Danae Wong
Try Face++ API for Java,see here.Face++ SDK for Java, can be used in Android project.
尝试面向 Java 的 Face++ API,请参见此处。Face++ SDK for Java,可用于Android项目。
It is recommended that Face++ free APIs are easy to use.Enjoy it :)
推荐Face++ free APIs 好用。享受吧:)