14b1ae350b
This commit introduces chinese_whispers method without any "helpers" on PHP side. Users needs to take care of everything (building edges from 128D face chip vector, for example), but this is exposed for people that need low-level call and want to calculate distances and build edges in PHP directly. |
||
---|---|---|
src | ||
tests | ||
.gitignore | ||
CMakeLists.txt | ||
config.m4 | ||
config.w32 | ||
CREDITS | ||
EXPERIMENTAL | ||
pdlib.cc | ||
pdlib.php | ||
php_pdlib.h | ||
README.md |
PDlib - A PHP extension for Dlib
A PHP extension
Requirements
- Dlib 19.13+
- PHP 7.0+
- C++ 11
Dependence
Dlib
Install Dlib as share library
git clone git@github.com:davisking/dlib.git
cd dlib/dlib
mkdir build
cd build
cmake -DBUILD_SHARED_LIBS=ON ..
make
sudo make install
Installation
git clone https://github.com/goodspb/pdlib.git
cd pdlib
phpize
./configure --enable-debug
make
sudo make install
Configure
vim youpath/php.ini
Write the below content into php.ini
[pdlib]
extension="pdlib.so"
Usage
face detection
<?php
// face detection
$faceCount = dlib_face_detection("~/a.jpg");
// how mary face in the picture.
var_dump($faceCount);
face landmark detection
<?php
// face landmark detection
$landmarks = dlib_face_landmark_detection("~/a.jpg");
var_dump($landmarks);
chinese whisers
Provides raw access to dlib's chinese_whispers
function.
Client need to build and provide edges. Edges are provided
as numeric array. Each element of this array should also be
numeric array with 2 elements of long type.
Returned value is also numeric array, containing obtained labels.
<?php
// This example will cluster nodes 0 and 1, but would leave 2 out.
// $labels will look like [0,0,1].
$edges = [[0,0], [0,1], [1,1], [2,2]];
$labels = dlib_chinese_whispers($edges);
Features
- 1.Face Detection
- 2.Face Landmark Detection
- 3.Deep Face Recognition
- 4.Deep Learning Face Detection
- 5. Raw chinese_whispers