About & Pics

Description

Face Recognition can be used as a test framework for several face recognition methods including the Neural Networks with TensorFlow and Caffe.

It includes following preprocessing algorithms:
- Grayscale
- Crop
- Eye Alignment
- Gamma Correction
- Difference of Gaussians
- Canny-Filter
- Local Binary Pattern
- Histogramm Equalization (can only be used if grayscale is used too)
- Resize

You can choose from the following feature extraction and classification methods:
- Eigenfaces with Nearest Neighbour
- Image Reshaping with Support Vector Machine
- TensorFlow with SVM or KNN
- Caffe with SVM or KNN

The manual can be found here https://github.com/Qualeams/Android-Face-Recognition-with-Deep-Learning/blob/master/USER%20MANUAL.md

At the moment only armeabi-v7a devices and upwards are supported.

For best experience in recognition mode rotate the device to left.
_______________________________________________________________

TensorFlow:

If you want to use the Tensorflow Inception5h model, download it from here:
https://storage.googleapis.com/download.tensorflow.org/models/inception5h.zip

Then copy the file "tensorflow_inception_graph.pb" to "/sdcard/Pictures/facerecognition/data/TensorFlow"

Use these default settings for a start:
Number of classes: 1001 (not relevant as we don't use the last layer)
Input Size: 224
Image mean: 128
Output size: 1024
Input layer: input
Output layer: avgpool0
Model file: tensorflow_inception_graph.pb
---------------------------------------------------------------------------------------------------------
If you want to use the VGG Face Descriptor model, download it from here:
https://www.dropbox.com/s/51wi2la5e034wfv/vgg_faces.pb?dl=0

Caution: This model runs only on devices with at least 3 GB or RAM.

Then copy the file "vgg_faces.pb" to "/sdcard/Pictures/facerecognition/data/TensorFlow"

Use these default settings for a start:
Number of classes: 1000 (not relevant as we don't use the last layer)
Input Size: 224
Image mean: 128
Output size: 4096
Input layer: Placeholder
Output layer: fc7/fc7
Model file: vgg_faces.pb
_______________________________________________________________

Caffe:

If you want to use the VGG Face Descriptor model, download it from here:
http://www.robots.ox.ac.uk/~vgg/software/vgg_face/src/vgg_face_caffe.tar.gz

Caution: This model runs only on devices with at least 3 GB or RAM.

Then copy the files "VGG_FACE_deploy.prototxt" and "VGG_FACE.caffemodel" to "/sdcard/Pictures/facerecognition/data/caffe"

Use these default settings for a start:
Mean values: 104, 117, 123
Output layer: fc7
Model file: VGG_FACE_deploy.prototxt
Weights file: VGG_FACE.caffemodel

_______________________________________________________________

The license files can be found here https://github.com/Qualeams/Android-Face-Recognition-with-Deep-Learning/blob/master/LICENSE.txt and here https://github.com/Qualeams/Android-Face-Recognition-with-Deep-Learning/blob/master/NOTICE.txt

 Free in Google Play

Screenshots

Face Recognition screenshot 1Face Recognition screenshot 2Face Recognition screenshot 3Face Recognition screenshot 4Face Recognition screenshot 5Face Recognition screenshot 6Face Recognition screenshot 7Face Recognition screenshot 8

Version History

Launched May 24, 2016 (almost 3 years ago).

Releasing new versions every about 1 month, on average.

May 26
2017
(Current)
Version 1.5.1

- Switch from building Tensorflow from source to using the Jcenter library
- Included optimized_facenet model and changed default settings to use TensorFlow by default

Apr 23
2017
Version 1.4.1

- fixes crash in Crop method, if the camera view is not used in the default landscape mode

Apr 01
2017
Version 1.4.0

- Upgrade to TensorFlow r1.0
- Upgrade to OpenCV 3.2.0
- Add function to set the Camera View size (default 320 x 240)
- Fixed detection (removed Crop from settings, instead always crop the image before applying additional preprocessings)

Feb 10
2017
Version 1.3.2

Version 1.3.2:
- Added link to the Privacy Policy (About button) due to the Play Store policy
- Fixed crashing if Night Portrait Mode is not supported for the device

Jan 06
2017
Version 1.3.1

Version 1.3.1:
- Fixed SupportVectorMachine (again)
- Added DetectionView
- Disabled DetectionTest (no time to finish it at the moment but it's unusable in the current state)

Dec 11
2016
Version 1.2.7

Version 1.2.7:
- Fixed SupportVectorMachine

Dec 03
2016
Version 1.2.4

Version 1.2.4:
- Added additional settings (face detection preprocessing)
- Added DetectionTest function
- Added Night Portrait Mode and Exposure Compensation Settings
- Added new face detector (choose between OpenCV and Android API)
- Fixed Eye Detection

Oct 14
2016
Version 1.2

Version 1.2:
- Update to TensorFlow r.0.11
- "Add Person" only saves an image if exactly one face has been detected
- Support for arm64-v8a (TensorFlow and SVM libs)

Jun 21
2016
Version 1.1.1

Version 1.1 includes:
- Reset settings to default
- "Add Person" only saves an image if a face has been detected
Version 1.1.1:
- Fixed camera mirroring in Recognition mode
- Fixed default settings
Sorry for the last few updates. There were several bugs which needed to be fixed.

Jun 20
2016
Version 1.0

Previous 3 versions
5

Total Ratings

5
3
4
1
3
0
2
0
1
1
150

Total Ratings

5
65
4
14
3
10
2
5
1
58