Only released in EOL distros:   indigo

The ProcRob face_recognition package can be downloaded from https://github.com/procrob/procrob_functional . For usage guide, please see below. For details of the face recognition algorithm used, please see http://www.shervinemami.info/faceRecognition.html .

How the face recognition works:

Training images are stored in the 'data' directory.
Training images are listed in the 'train.text' file.
The 'train.txt' follows a specific format which is best understood by looking at the example 'train.txt' file provided in the package. Note that person numbers start from 1, and spaces or special characters are not allowed in persons' names).
The program trains from the training examples listed in the 'train.txt' and create an Eigenfaces database which is stored in the 'facedata.xml' file.
Face detection is performed using a haarcascade classifier (haarcascade_frontalface_alt.xml).
The 'data' folder, and 'train.txt', 'face.xml' and 'haarcascade_frontalface_alt.xml' files should be placed in the program's working directory (i.e. the directory from which you execute the program).

When the face_recognition program starts:
If 'facedata.xml' exists, the Eigenfaces database is loaded from 'facedata.xml'.
If 'facedata.xml' does not exist, the program tries to train and create Eigenfaces database from the training images listed in 'train.txt', if any.
Regardless of if the Eigenfaces database is loaded/created at start up or not, you can always add training images directly from the video stream and then update the Eigenfaces database by (re)training.
Note: when the program (re)trains, the content of 'facedata.xml' is disregarded and the program trains only based on the training images listed in 'train.txt'.

Fserver

Fserver is a ROS node that provides a simple actionlib server interface for performing different face recognition functionalities in video stream.

To start the Fserver node

roscd face_recognition
rosrun face_recognition Fserver

FaceRecognitionGoal message

The FaceRecognitionGoal message has 2 fields: an 'order_id' which is an integer specifying a goal and an 'order_argument' which is a string used to specify an argument for the goal if necessary. The face recognition actionlib server (i.e. 'Fserver') accepts 5 different goals:

• 'order_id' = 0

recognise_once: Goal is to acknowledge the first face recognised in the video stream. When the first face is recognised with a confidence value higher than the desirable confidence value threshold, the name of the recognised person and its confidence value are sent back to the client as result.

• 'order_id' = 1

recognise_continuous: Goal is to continuously recognise faces in the video stream. For every face recognised with a confidence value higher than the desirable confidence value threshold, the name of the recognised person and its confidence value are sent back to the client as feedback. This goal is persuaded for infinite time until it is cancelled or preempted by another goal.

• 'order_id' = 2 and 'order_argument' = 'person_name'

add_face_images: Goal is to acquire training images for a NEW person. The video stream is processed for detecting a face which is saved and used as a training image for the new person. This process is continued until the desired number of training images for the new person is acquired. The name of the new person is provided as 'order_argument'. The acquired images are stored in the 'data' folder and are added to the list of training images in 'train.txt'

• 'order_id' = 3

train: Goal is to (re)train the Eigenfaces database from the training images listed in the 'train.txt'.

• 'order_id' = 4

exit: Goal is to exit the program.

Subscribed Topic:

• /camera/image_raw(standard ROS image transport)

A video stream

Parameters:

• confidence_value (double, default = 0.88)

A face recognised with confidence value higher than the "confidence_value" threshold is accepted as valid.

• show_screen_flag (boolean, default = true)

If output screen is shown.

• add_face_number (int, default = 25)

A parameter for the 'add_face_images' goal (order_id = 2) which determines the number of training images for a new person to be acquired from the video stream

Fclient

'Fclient' is a ROS node that implements an actionlib client example for the face_recognition simple actionlib server (i.e. 'Fserver'). 'Fclient' is provided for demonstration and testing purposes.

Subscribed topics

• fr_order(face_recognition::FRClientGoal)

Each 'FRClientGoal' message has an 'order_id' and an 'order_argument' which specify a goal to be executed by the 'Fserver'. After receiving a message, 'Fclient' sends the corresponding goal to the 'Fserver'. By registering relevant call back functions, 'Fclient' receives feedback and result information from the execution of goals in the 'Fserver' and prints such information on its terminal.

Tutorial

(You have to install gscam to do this tutorial) An exercise of using Fserver and Fclient:
1- run roscore

roscore

2- In a separate terminal publish a video stream on topic /camera/image_raw. If you have the gscam package installed and configured, you can use it to publish images from your web cam as follows:

roscd gscam/bin
rosrun gscam gscam /gscam/image_raw:=/camera/image_raw

3- In separate terminals run the face recognition server and client as follows:

rosrun face_recognition Fserver
rosrun face_recognition Fclient

4- In another terminal publish following messages on topic /fr_order to test different face recognition functionalities. After each command notice the output of Fserver and Fclient.

rostopic pub -1 /fr_order face_recognition/FRClientGoal -- 2 "your_name"

To acquire training images for your face: you should try to appear in the video stream!

rostopic pub -1 /fr_order face_recognition/FRClientGoal -- 1 "none" 

To recognise faces continuously. This would not stop until you preempt or cancel the goal. So lets preempt it by sending the next goal.

rostopic pub -1 /fr_order face_recognition/FRClientGoal -- 2 "your_friend's_name" 

To add training images for a new person

rostopic pub -1 /fr_order face_recognition/FRClientGoal -- 0 "none"

recognize_once

rostopic pub -1 /fr_order face_recognition/FRClientGoal -- 1 "none" 

recognize_continuous

rostopic pub -1 /fr_order face_recognition/FRClientGoal -- 4 "none" 

exit