Face recognition initial PR (#221)

This is the new pkg of face recognition using openface neural network
for face detection and recognition.
This is an initial PR checking.

.gitmodules

@@ -38,3 +38,7 @@
 	path = image_recognition_pose_estimation/docs
 	url = https://github.com/tue-robotics/tue_documentation_python.git
 	branch = master
+[submodule "image_recognition_face_recognition/docs"]
+	path = image_recognition_face_recognition/docs
+	url = https://github.com/tue-robotics/tue_documentation_python.git
+	branch = master

image_recognition/package.xml

@@ -15,6 +15,7 @@
   <exec_depend>image_recognition_age_gender</exec_depend>
   <exec_depend>image_recognition_analysis</exec_depend>
   <exec_depend>image_recognition_color_extractor</exec_depend>
+  <exec_depend>image_recognition_face_recognition</exec_depend>
   <exec_depend>image_recognition_footwear</exec_depend>
   <exec_depend>image_recognition_msgs</exec_depend>
   <exec_depend>image_recognition_openface</exec_depend>

image_recognition_face_recognition/CMakeLists.txt

@@ -0,0 +1,20 @@
+cmake_minimum_required(VERSION 3.0.2)
+project(image_recognition_face_recognition)
+
+
+find_package(catkin REQUIRED COMPONENTS)
+
+catkin_python_setup()
+
+catkin_package()
+
+install(PROGRAMS
+  scripts/get_face_recognition
+  scripts/face_recognition_node
+  scripts/train_from_images
+  DESTINATION ${CATKIN_PACKAGE_BIN_DESTINATION}
+)
+if(CATKIN_ENABLE_TESTING)
+  find_package(catkin_lint_cmake REQUIRED)
+  catkin_add_catkin_lint_test()
+endif()

image_recognition_face_recognition/README.md

@@ -0,0 +1,70 @@
+# image_recognition_face_recognition
+
+TO DO
+
+Face recognition with use of Facenet (https://github.com/timesler/facenet-pytorch/tree/master)
+Paper can be found: [paper](https://arxiv.org/pdf/1503.03832.pdf)
+
+## Installation
+
+See https://github.com/tue-robotics/image_recognition
+
+Make sure you have installed **CUDA8**.
+
+bash commends will be available when merged
+
+## How-to
+
+### Run Face Recognition Node
+
+Run the command why using your camera as an input (use roscamera node):
+
+    rosrun cv_camera cv_camera_node
+    rosrun image_recognition_face_recognition face_recognition_node image:=/cv_camera/image_raw 
+
+### ROS Node
+
+Run the image_recognition_face_detection node in one terminal (Specify the dlib and openface_net path as ROS parameter):
+
+    rosrun image_recognition_face_detection face_recognition_node
+
+Run the rqt annotation client (https://github.com/tue-robotics/image_recognition_rqt)
+
+    rosrun image_recognition_rqt annotation_gui
+
+Setup the service by clicking the gear wheel in the top-right corner. Select the `/annotate` services exposed by the openface ros node. Also don't forget to set-up your labels.
+
+![Configuration](doc/config.png)
+
+Now draw a rectangle around the face you would like to learn. The face recognizer will find the biggest face in the image and store a representation for this face. 
+
+![Annotate](doc/annotate.png)
+
+Now select the label and you will see that the openface ros node stores the face (console output node):
+
+    [INFO] [WallTime: 1478636380.407308] Succesfully learned face of 'rokus'
+
+Learn as many faces as you want ..
+
+Next step is starting the image_recognition_Rqt test gui (https://github.com/tue-robotics/image_recognition_rqt)
+
+    rosrun image_recognition_rqt test_gui
+
+Again configure the service you want to call with the gear-wheel in the top-right corner of the screen. If everything is set-up, draw a rectangle in the image and ask the service for detections:
+
+![Test](doc/test_face.png)
+
+You will see that the result of the detection will prompt in a dialog combo box. Also the detections will be drawn on the image.
+
+
+### Command line
+
+Command line interface to test the detection / recognition based on an image:
+
+    usage: get_face_recognition IMAGE [-k ALIGN_PATH] [-s NET_PATH] [-v]
+
+Run the command on an example image:
+
+    rosrun image_recognition_face_recognition get_face_recognition `rospack find image_recognition_face_recognition`/doc/example.png
+
+![Example](doc/example.png)

image_recognition_face_recognition/package.xml

@@ -0,0 +1,38 @@
+<?xml version="1.0"?>
+<?xml-model
+  href="http://download.ros.org/schema/package_format3.xsd"
+  schematypens="http://www.w3.org/2001/XMLSchema"?>
+<package format="3">
+  <name>image_recognition_face_recognition</name>
+  <version>0.0.1</version>
+  <description>The image_recognition_face_recognition package</description>
+
+  <maintainer email="[email protected]">iason</maintainer>
+
+  <license>MIT</license>
+
+  <buildtool_depend>catkin</buildtool_depend>
+
+  <buildtool_depend>python3-setuptools</buildtool_depend>
+
+  <exec_depend>roscpp</exec_depend>
+  <exec_depend>cv_bridge</exec_depend>
+  <exec_depend>diagnostic_updater</exec_depend>
+  <exec_depend>image_recognition_msgs</exec_depend>
+  <exec_depend>image_recognition_util</exec_depend>
+  <exec_depend>python-dlib</exec_depend> <!--pip package-->
+  <exec_depend>python3-numpy</exec_depend>
+  <exec_depend>python3-opencv</exec_depend>
+  <exec_depend>rospy</exec_depend>
+
+  <test_depend>catkin_lint_cmake</test_depend>
+
+  <doc_depend>python3-sphinx</doc_depend>
+  <doc_depend>python-sphinx-autoapi-pip</doc_depend>
+  <doc_depend>python-sphinx-rtd-theme-pip</doc_depend>
+  <doc_depend>python3-yaml</doc_depend>
+
+  <export>
+    <rosdoc config="rosdoc.yaml" />
+  </export>
+</package>

image_recognition_face_recognition/rosdoc.yaml

@@ -0,0 +1,3 @@
+- builder: sphinx
+  sphinx_root_dir: docs
+  name: Python API