cv::face::MACE クラス

Minimum Average Correlation Energy Filter useful for authentication with (cancellable) biometrical features. (does not need many positives to train (10-50), and no negatives at all, also robust to noise/salting) [詳解]

#include <mace.hpp>

cv::Algorithmを継承しています。

公開メンバ関数
virtual CV_WRAP void	salt (const cv::String &passphrase)=0
	optionally encrypt images with random convolution [詳解]
virtual CV_WRAP void	train (cv::InputArrayOfArrays images)=0
	train it on positive features compute the mace filter: h = D(-1) * X * (X(+) * D(-1) * X)(-1) * C also calculate a minimal threshold for this class, the smallest self-similarity from the train images [詳解]
virtual CV_WRAP bool	same (cv::InputArray query) const =0
	correlate query img and threshold to min class value [詳解]
基底クラス cv::Algorithm に属する継承公開メンバ関数
virtual CV_WRAP void	clear ()
	Clears the algorithm state [詳解]
virtual void	write (FileStorage &fs) const
	Stores algorithm parameters in a file storage [詳解]
CV_WRAP void	write (const Ptr< FileStorage > &fs, const String &name=String()) const
	simplified API for language bindings これはオーバーロードされたメンバ関数です。利便性のために用意されています。元の関数との違いは引き数のみです。
virtual CV_WRAP void	read (const FileNode &fn)
	Reads algorithm parameters from a file storage [詳解]
virtual CV_WRAP bool	empty () const
	Returns true if the Algorithm is empty (e.g. in the very beginning or after unsuccessful read [詳解]
virtual CV_WRAP void	save (const String &filename) const
virtual CV_WRAP String	getDefaultName () const

静的公開メンバ関数
static CV_WRAP cv::Ptr< MACE >	load (const String &filename, const String &objname=String())
	constructor [詳解]
static CV_WRAP cv::Ptr< MACE >	create (int IMGSIZE=64)
	constructor [詳解]
基底クラス cv::Algorithm に属する継承静的公開メンバ関数
template<typename _Tp >
static Ptr< _Tp >	read (const FileNode &fn)
	Reads algorithm from the file node [詳解]
template<typename _Tp >
static Ptr< _Tp >	load (const String &filename, const String &objname=String())
	Loads algorithm from the file [詳解]
template<typename _Tp >
static Ptr< _Tp >	loadFromString (const String &strModel, const String &objname=String())
	Loads algorithm from a String [詳解]

その他の継承メンバ
基底クラス cv::Algorithm に属する継承限定公開メンバ関数
void	writeFormat (FileStorage &fs) const

詳解

Minimum Average Correlation Energy Filter useful for authentication with (cancellable) biometrical features. (does not need many positives to train (10-50), and no negatives at all, also robust to noise/salting)

see also: [Savvides04]

this implementation is largely based on: https://code.google.com/archive/p/pam-face-authentication (GSOC 2009)

use it like:

Ptr<face::MACE> mace = face::MACE::create(64);
 
vector<Mat> pos_images = ...
mace->train(pos_images);
 
Mat query = ...
bool same = mace->same(query);

you can also use two-factor authentication, with an additional passphrase:

String owners_passphrase = "ilikehotdogs";
Ptr<face::MACE> mace = face::MACE::create(64);
mace->salt(owners_passphrase);
vector<Mat> pos_images = ...
mace->train(pos_images);
 
// now, users have to give a valid passphrase, along with the image:
Mat query = ...
cout << "enter passphrase: ";
string pass;
getline(cin, pass);
mace->salt(pass);
bool same = mace->same(query);

save/load your model:

Ptr<face::MACE> mace = face::MACE::create(64);
mace->train(pos_images);
mace->save("my_mace.xml");
 
// later:
Ptr<MACE> reloaded = MACE::load("my_mace.xml");
reloaded->same(some_image);

関数詳解

create()

static CV_WRAP cv::Ptr< MACE > cv::face::MACE::create ( int  IMGSIZE = 64 )

static

constructor

引数

IMGSIZE

images will get resized to this (should be an even number)

load()

static CV_WRAP cv::Ptr< MACE > cv::face::MACE::load ( const String &  filename, const String &  objname = String()  )

static

constructor

引数

filename	build a new MACE instance from a pre-serialized FileStorage
objname	(optional) top-level node in the FileStorage

salt()

virtual CV_WRAP void cv::face::MACE::salt ( const cv::String &  passphrase )

pure virtual

optionally encrypt images with random convolution

引数

passphrase

a crc64 random seed will get generated from this

same()

virtual CV_WRAP bool cv::face::MACE::same ( cv::InputArray  query ) const

pure virtual

correlate query img and threshold to min class value

引数

query

a Mat with query image

train()

virtual CV_WRAP void cv::face::MACE::train ( cv::InputArrayOfArrays  images )

pure virtual

train it on positive features compute the mace filter: h = D(-1) * X * (X(+) * D(-1) * X)(-1) * C also calculate a minimal threshold for this class, the smallest self-similarity from the train images

引数

images

a vector<Mat> with the train images

---

このクラス詳解は次のファイルから抽出されました:

• mace.hpp