×
Namespaces

Variants
Actions
(Difference between revisions)

Face Recognition using 2D Fast Fourier Transform

From Nokia Developer Wiki
Jump to: navigation, search
galazzo (Talk | contribs)
(Galazzo - - Working with 2D FFT in Windows Phone)
galazzo (Talk | contribs)
m (Galazzo - - Working with 2D FFT in Windows Phone 8)
Line 94: Line 94:
 
</Extensions>
 
</Extensions>
 
</code>
 
</code>
# Each {{Icode|Extention}} element describes an App Connect extension and the {{Icode|Extention}} tag must be allocated after {{Icode|Tokens}} tag.  
+
# Each {{Icode|Extention}} element describes an App Connect extension and the {{Icode|Extention}} tag must be allocated after {{Icode|Tokens}} tag.
 +
# {{Icode|ExtensionName}} Is the identifier for the type of extension support. The value is {{Icode|Camera_Capture_App}}
 
# {{Icode|ConsumerID}} Restricts access to the extension to the consumer with the specified ProductID. All search extensions require the same value, '''5B04B775-356B-4AA0-AAF8-6491FFEA5661'''.
 
# {{Icode|ConsumerID}} Restricts access to the extension to the consumer with the specified ProductID. All search extensions require the same value, '''5B04B775-356B-4AA0-AAF8-6491FFEA5661'''.
  

Revision as of 01:51, 30 November 2012

This article explains how to implement a simple face recognition system based on analysis through their Fourier spectrum. Recognition is done by finding the closest match between feature vectors containing the Fourier coefficients at selected frequencies. The introduced method well compares to other competing approaches.
Despite the argument is certainly complex, the approach used and the tools already implemented make the process easy to implement by all users. The call is therefore not to be frightened by appearances.

WP Metro Icon Multimedia.png
WP Metro Icon WP8.png
Article Metadata
Tested with
Devices(s): Nokia Lumia
Compatibility
Platform(s): Windows Phone
Windows Phone 8
Article
Keywords: Face Recognition, Image Processing
Created: galazzo (12 Nov 2012)
Last edited: galazzo (30 Nov 2012)

Contents

Introduction

The face is one of several features witch can be used to uniquely identify a person. It's the characteristic that we most commonly use to recognize others. Not two human faces are identical which makes them well suited for use in identification.
Besides being a challenging problem in itself the importance of face recognition systems lies in their potential applications such as access control, passport, etc...
The obvious advantage of a face recognition system compared to competing methods is its low level of intrusion. It only requires looking into camera.
Automated face recognition systems generally evolved along two main routes, either the analysis of grey level information ( often called template based ) or the extraction of mainly geometrical features such as shape, profile or hair color.
The work presented here comprises a novel template based approach that considering it's simple algorithm compares very well to other more complex methods that are used commonly such Hidden Markov Models or back propagation Neural Network.

According to humans are thought to view faces primary in a holistic manner and experiments suggest that holistic approaches are superior to geometrical recognition systems.
The technique presented is based on the Fourier spectrum of facial images, thus it relies on a global transformation, every pixel in the image contributes to each value in the spectrum.
The Fourier spectrum is a plot of the energy against spacial frequencies, where spatial frequencies relate to the spatial relations of intensities in the image . In our case this translate to distances between areas of particular brightness such as the overall area of the head or the distance of the eyes.
Higher frequencies describe finer details and contrary to what you might think we found them less useful for identification, just as humans can recognize a face from a brief look without focusing on small details.
The recognition of faces is done by finding the closet match ( the difference or distance ) between the newly presented face and all those faces known to the system. The distances are calculated between the feature vectors with entries that are the Fourier transform values at specially chosen frequencies. As few as 30 frequencies yield excellent results.

Fast Fourier Transform

The Fourier Transform is an important image processing tool which is used to decompose an image into its sine and cosine components. The output of the transformation represents the image in the Fourier or frequency domain, while the input image is the spatial domain equivalent. In the Fourier domain image, each point represents a particular frequency contained in the spatial domain image.

The Fourier Transform is used in a wide range of applications, such as image analysis, image filtering, image reconstruction and image compression, text orientation finding that will be covered ( hopefully ) in further articles.

The Fast Fourier Transform (FFT) is an efficient algorithm to compute the discrete Fourier transform (DFT) and its inverse. The discrete Fourier transform (DFT) transforms one function into another, which is called the frequency domain representation of the original function. The DFT requires an input function that is discrete. Such inputs are often created by sampling a continuous function, such as a person's voice. The discrete input function must also have a limited (finite) duration, such as one period of a periodic sequence or a windowed segment of a longer sequence.

The DFT is the sampled Fourier Transform and therefore does not contain all frequencies forming an image, but only a set of samples which is large enough to fully describe the spatial domain image. The number of frequencies corresponds to the number of pixels in the spatial domain image, i.e. the image in the spatial and Fourier domain are of the same size.

For a square image of size N×N, the two-dimensional DFT is given by:

DFT2D.gif

where f(a,b) is the image in the spatial domain and the exponential term is the basis function corresponding to each point F(k,l) in the Fourier space. The equation can be interpreted as: the value of each point F(k,l) is obtained by multiplying the spatial image with the corresponding base function and summing the result.
The Fourier Transform produces a complex number valued output image which can be displayed with two images, either with the real and imaginary part or with magnitude and phase. In image processing, often only the magnitude of the Fourier Transform is displayed, as it contains most of the information of the geometric structure of the spatial domain image. However, if we want to re-transform the Fourier image into the correct spatial domain after some processing in the frequency domain, we must make sure to preserve both magnitude and phase of the Fourier image.

The Fourier domain image has a much greater range than the image in the spatial domain. Hence, to be sufficiently accurate, its values are usually calculated and stored in float values.
The Fourier Transform is used if we want to access the geometric characteristics of a spatial domain image. Because the image in the Fourier domain is decomposed into its sinusoidal components, it is easy to examine or process certain frequencies of the image, thus influencing the geometric structure in the spatial domain.

In most implementations the Fourier image is shifted in such a way that the DC-value (i.e. the image mean) F(0,0) is displayed in the center of the image. The further away from the center an image point is, the higher is its corresponding frequency.

For a slightly deeper view, see Sound pattern matching using Fast Fourier Transform in Windows Phone.

Selecting Frequencies

From the spectrum it can be seen that almost all the information is contained near the center, within the low frequencies. Thus it seems reasonable that these frequencies will also provide the best ground for the recognition process. Valuable frequencies don't lie in a circle around the origin but more in a rhombus shaped region.
We know that the second half of FFT carry no useful and duplicated information, so we can half the data to treat. As the 2D FFT is built as two pass of 1D FFT it means that we can focus just to one quadrant reducing further the data to treat.


Working with 2D FFT in Windows Phone 8

A new great Windows Phone's feature is Camera Lenses that enables you to build apps into the camera app. Users can launch “Lenses” apps directly from the camera app making the facial recognition process a perfect solution for Lenses application.

  • Download DSP.cs and add it into your project. DSP.cs provides a namespace called DSP and a class FourierTransform containing a set of functions to compute the FFT.

Don't forget to include the namespace DSP

using DSP;

Inside th WMAppManifest.xml file add the following capabilities:

<Capabilities>
<Capability Name="ID_CAP_ISV_CAMERA" />
<Capability Name="ID_CAP_MEDIALIB_PHOTO" />
</Capabilities>
 
<Extensions>
<Extension ExtensionName="Camera_Capture_App" ConsumerID="{5B04B775-356B-4AA0-AAF8-6491FFEA5631}" TaskID="_default" />
</Extensions>
  1. Each Extention element describes an App Connect extension and the Extention tag must be allocated after Tokens tag.
  2. ExtensionName Is the identifier for the type of extension support. The value is Camera_Capture_App
  3. ConsumerID Restricts access to the extension to the consumer with the specified ProductID. All search extensions require the same value, 5B04B775-356B-4AA0-AAF8-6491FFEA5661.

Now your application is registered as Lenses app and can be found and called from the main Camera app.

To display the Camera flow int oyour application let's add the following code:

<Button Content="Snap Picture" Click="SaveImage" />
<Grid x:Name="ContentPanel" Grid.Row="1" >
<Grid.Background>
<VideoBrush x:Name="viewfinderBrush" />
</Grid.Background>
</Grid>

Now lt's begin to buoild the app.

using Microsoft.Devices; // Needed for PhotoCamera
using Microsoft.Xna.Framework.Media;
using System.Windows.Media.Imaging;
using Microsoft.Phone; // Needed for PictureDecoder
 
namespace Face_Recognition
{
public partial class MainPage : PhoneApplicationPage
{
PhotoCamera cam;
MediaLibrary library = new MediaLibrary();
 
public static WriteableBitmap CapturedImage;
private static int W = 256;
private static int H = 256;
private static int matchSamples = 25;
 
private double[] compareSignal = new Double[matchSamples];
 
private Double[] pRealIn = new Double[W * H];
private Double[] pImagIn = new Double[W * H];
private Double[] pRealOut = new Double[W * H];
private Double[] pImagOut = new Double[W * H];
private Double[] pRealOut2 = new Double[W * H];
private Double[] pImagOut2 = new Double[W * H];
 
public MainPage()
{
InitializeComponent();
 
this.Loaded += Lense_Loaded;
}
 
void Lense_Loaded(object sender, RoutedEventArgs e)
{
if (PhotoCamera.IsCameraTypeSupported(CameraType.Primary))
{
cam = new Microsoft.Devices.PhotoCamera(CameraType.Primary);
 
cam.CaptureImageAvailable += cam_CaptureImageAvailable;
viewfinderBrush.SetSource(cam);
}
}
 
}

Convertint a pixel to Grayscale

Here a useful function to convert a colored pixel into gray-scale. That operation allow us to save more computation,

         internal int ColorToGray(int color)
{
int gray = 0;
 
int a = color >> 24;
int r = (color & 0x00ff0000) >> 16;
int g = (color & 0x0000ff00) >> 8;
int b = (color & 0x000000ff);
 
if ((r == g) && (g == b))
{
gray = color;
}
else
{
// Calculate for the illumination.
// I =(int)(0.109375*R + 0.59375*G + 0.296875*B + 0.5)
int i = (7 * r + 38 * g + 19 * b + 32) >> 6;
 
gray = ((0x1) << 24) | ((i & 0xFF) << 16) | ((i & 0xFF) << 8) | (i & 0xFF);
}
return gray;
}

FFT 2D

Tip.pngTip: Don't create a BitmapImage or WriteableBitmap on the UI thread because they are DependencyObjects otherwise you get the ObjectDisposedException error because the stream for the image is closed already when the dispatcher handles your request. Move into your Dispatcher invocation.

void cam_CaptureImageAvailable(object sender, ContentReadyEventArgs e)
{
Deployment.Current.Dispatcher.BeginInvoke(delegate()
{
//Take JPEG stream and decode into a WriteableBitmap object
MainPage.CapturedImage = PictureDecoder.DecodeJpeg(e.ImageStream,W,H);
 
//Collapse visibility on the progress bar once writeable bitmap is visible.
progressBar.Visibility = Visibility.Collapsed;
 
int[] pixel = MainPage.CapturedImage.Pixels;
 
int color = 0;
for (int y = 0; y < MainPage.CapturedImage.PixelHeight; y++)
{
for (int x = 0; x < MainPage.CapturedImage.PixelWidth; x++)
{
color = MainPage.CapturedImage.Pixels[x + (y * MainPage.CapturedImage.PixelWidth)];
pRealIn[x + (y * MainPage.CapturedImage.PixelWidth)] = ColorToGray(color) & 0xFF;
}
}
 
Double[] match;
double mse = 0;
 
System.Diagnostics.Debug.WriteLine("Using Fourier");
DSP.FourierTransform.Compute2D((uint)W, (uint)H, ref pRealIn, null, ref pRealOut, ref pImagOut, false);
match = DSP.Utilities.triangularExtraction(ref pRealOut, (uint)W, (uint)H, (uint)matchSamples, 0);
mse = DSP.Utilities.MSE(ref compareSignal, ref match, (int)matchSamples);
 
// normalize
mse /= 1000000000;
 
mseResult.Text = "" + Math.Round(mse);
System.Diagnostics.Debug.WriteLine("MSE:" + mseResult.Text);
Array.Copy(match, 0, compareSignal, 0, matchSamples);
 
color = 0;
for (int y = 0; y < MainPage.CapturedImage.PixelHeight; y++)
{
for (int x = 0; x < MainPage.CapturedImage.PixelWidth; x++)
{
color = (int)Math.Floor(pRealIn[x + (y * MainPage.CapturedImage.PixelWidth)]);
color = (color > 0) ? ((color > 255) ? 255 : color) : 0;
MainPage.CapturedImage.Pixels[x + (y * MainPage.CapturedImage.PixelWidth)] = (1 << 24) | (color << 16) | (color << 8) | color;
}
}
});
}

Results

Assuming the threshold is 50

Image A Image B Result
Giuseppe
Giuseppe
37
Giuseppe
Gianluca
61
Elena
Elena
36
Elena
Gianluca
618
Gianluca
Elk
386
Elk
Elk
34

Interesting to note how the algorithm is enough tolerant to rotated faces. Also notice the difference between my two brothers Giuseppe and Gianluca compared to Elena with Gianluca. Funny the result my brother Gianluca is nearest to Elk than Elena :-)
Important to understand that results are strongly influenced by the background, how the face is rotated or light conditions when compared to the sample image. The best case is when we manage photos with flat background as for the Elena's case.

Summary

This article as shown a possible approach to Face recognition problem. Of course is not the ultimate solution as other more complex methods are available for example for military or national security use. Anyway the proposed approach is very powerful, relatively easy to implement on mobile devices.

A lot of improvements will come for better results :

  • Skin detection
  • Skin quantization
  • Hair detection
  • Hair quantization
729 page views in the last 30 days.