我实现在Android脸跟踪,并作为文献研究,希望找出Android的FaceDetector的基础技术。
I'm implementing a face tracker on Android, and as a literature study, would like to identify the underlying technique of Android's FaceDetector.
简单地说:我想知道如何使用 android.media.FaceDetector
分类作品
Simply put: I want to understand how the android.media.FaceDetector
classifier works.
一个简单的谷歌搜索没有取得任何资料,所以我想我会看看在code。
A brief Google search didn't yield anything informative, so I thought I'd take a look at the code.
通过查看Java源代码code,FaceDetector.java,没有太多的要学习: FaceDetector
仅仅是被提供的图像尺寸和面数的一类,然后返回面的阵列
By looking at the Java source code, FaceDetector.java
, there isn't much to be learned: FaceDetector
is simply a class that is provided the image dimensions and number of faces, then returns an array of faces.
在Android源包含JNI code该类。我跟着通过函数调用,其中,减少到最基本的要素,我学到了:
The Android source contains the JNI code for this class. I followed through the function calls, where, reduced to the bare essentials, I learned:
在FaceFinder在FaceFinder.c:75 在90行, bbs_MemSeg_alloc
返回 btk_HFaceFinder
对象(其中包含的功能,真正找到面),基本上复制它的 hsdkA-> contextE.memTblE.espArrE
中初始化初始化原 btk_HSDK
对象的数组()( FaceDetector_jni.cpp:145)通过 btk_SDK_create()
在它看来,功能迷宫相互提供 btk_HSDK
的指针和实例,但我无处可以找到 sdk-的具体实例> contextE.memTblE.espArrE [0]
,理应包含魔术
The "FaceFinder" is created in FaceFinder.c:75
On line 90, bbs_MemSeg_alloc
returns a btk_HFaceFinder
object (which contains the function to actually find faces), essentially copying it the hsdkA->contextE.memTblE.espArrE
array of the original btk_HSDK
object initialized within initialize() (FaceDetector_jni.cpp:145
) by btk_SDK_create()
It appears that a maze of functions provide each other with pointers and instances of btk_HSDK
, but nowhere can I find a concrete instantiation of sdk->contextE.memTblE.espArrE[0]
that supposedly contains the magic.
我什么的有无的发现,是一个小线索:JNI code引用FFTEm库,我无法找到源$ C $下。通过它的外观,但是,FFT是快速傅立叶变换的,这可能是一起有pre训练神经网络中使用。唯一的文学,我可以发现,对准这个理论是一纸由本 - 雅各布等人。
What I have discovered, is a little clue: the JNI code references a FFTEm library that I can't find the source code for. By the looks of it, however, FFT is Fast Fourier Transform, which is probably used together with a pre-trained neural network. The only literature I can find that aligns with this theory is a paper by Ben-Yacoub et al.
我甚至不真正了解,如果我在正确的道路上设置的,所以在所有的任何建议,无疑将有所帮助。
I don't even really know if I'm set on the right path, so any suggestions at all would undoubtedly help.
编辑:我添加了一个+100赏金任何人谁可以给任何见解
I've added a +100 bounty for anybody who can give any insight.
我在手机上,所以不能广泛响应,但谷歌的关键字内文视觉算法拉了一些有用的论文......
I'm on a phone, so can't respond extensively, but Google keywords "neven vision algorithm" pull up some useful papers...
此外,美国专利6222939涉及。
Also, US patent 6222939 is related.
可能还有些上的http://peterwilliams97.blogspot.com/2008/09/google-picasa-to-have-face-recognition.html可能是方便......
Possibly also some of the links on http://peterwilliams97.blogspot.com/2008/09/google-picasa-to-have-face-recognition.html might be handy...