Face recognition using IP, computer vision toolbox, NN toolbox and statistics toolbox

Hi, I wanted to know how i can make use of IP, computer vision, NN and statistics toolboxes to develop a face recognition system. Can anyone help me with this. I came across few methods for face recognition, but since i've the above mentioned toolboxes, i want to know how to use all of them for my project.

Answer 1

[Aruni]

Hi,

I had implemented face recognition using MATLAB by following the paper http://www4.comp.polyu.edu.hk/~cslzhang/paper/conf/iccv11/CRC_RLS_final.pdf

The ridge() function in Statistics Toolbox can be used for the L2-regularized regression mentioned in the paper. http://www.mathworks.com/help/stats/ridge.html

The other steps in that paper are straightforward matrix manipulations.

For detecting faces , I used the face detector of the Computer Vision System Toolbox. http://www.mathworks.com/help/vision/ref/vision.cascadeobjectdetector-class.html

Representing a face can be done in several ways.

The paper linked above simply vectorized the 2D array of grayvalues. This would not be robust in case of lesser number of samples per person, different posed faces etc.

One alternative is to detect facial landmarks (using the Viola-Jones Cascade Object Detector in the Computer Vision toolbox as before, but instead of faces using the provided models for – nose, lips, eyes) and extract SURF or HOG features ( extractFeatures ) at those locations. A concatenated vector of the features extracted at the landmarks can be used to represent the face.

Recognition can be done using regularized regression as in the paper. Or you can train an SVM (Stats toolbox) to recognize each person in your face database – the pictures of that person as positive samples, all other pictures as negative samples. Create an SVM for each person in the database and use that to recognize/classify a new face (one-versus-rest SVM).

[omar A.alghafoor]

Hi Mathworks team .

I am having two problems distinguishing faces using (face recognition convolutional neural network)

First: How to detect the intruder.

Second: The facial recognition overlaps between one person and another in the system.

The first test on grayscale images was good recognition, but on realtime of web camera the results are incorrect, knowing that I use a camera that has accuracy: 1024x570

note : all imge are grayscale .

Where is the defect in the code?

this my code for training dataset:

clc

clearvars

close all

%% variables

trainingNumFiles = 0.8;

rng(1)

faceData = imageDatastore('AutoCapturedFaces','IncludeSubfolders',true,'LabelSource','foldernames');

% Resize the images to the input size of the net

faceData.ReadFcn = @(loc)imresize(imread(loc),[227,227]);

% read one image to get pixel size

img = readimage(faceData,1);

% splitting the testing and training data

[trainFaceData,testFaceData] = splitEachLabel(faceData, ...

trainingNumFiles,'randomize');

%% defining CNN parameters

% defining layers

layers = [imageInputLayer([size(img,1) size(img,2) 1])

%middle layers

convolution2dLayer(5,3,'Padding', 2, 'Stride',3)

reluLayer

maxPooling2dLayer(3,'Stride',3)

%final layers

fullyConnectedLayer(8)

softmaxLayer

classificationLayer()];

% options to train the network

options = trainingOptions('sgdm', ...

'MiniBatchSize', 40, ...

'InitialLearnRate', 1e-4, ...

'MaxEpochs', 25, ...

'LearnRateSchedule', 'piecewise', ...

'LearnRateDropFactor', 0.875, ...

'LearnRateDropPeriod', 12, ...

'VerboseFrequency', 5);

% training the network

convnet = trainNetwork(trainFaceData,layers,options);

%% classifying

YTest = classify(convnet,testFaceData);

TTest = testFaceData.Labels;

%% Calculate the accuracy.

accuracy = sum(YTest == TTest)/numel(TTest)

save convnet

accuracy =

0.9375

https://www.mathworks.com/matlabcentral/answers/774947-face-recognition-convolutional-neural-network?s_tid=prof_contriblnk

Answer 2

[Namratha]

Thanks a lot for your answer, but I'm not able to view the paper you have mentioned. Could you please mail me that paper to [e-mail]. And can you please share some more info about your project if you dont mind. Thank you again.

[Aruni]

Sorry, the link is corrected now: http://www4.comp.polyu.edu.hk/~cslzhang/paper/conf/iccv11/CRC_RLS_final.pdf

Please ask any specific doubts you have?

[Namratha]

Thank you for your reply. Can you please tell me how to extract features from only eyes, lips and nose. I could create an object to detect the eyes but im unable to extract features from eyes alone. Same is the case with lips and nose.