AGE & GENDER ESTIMATION WITH

FACE RECOGNITION
USING
MACHINE LEARNING

BCA RRN – 191501601014, 191501601004 & 191501601019 2nd Review

 UNDER THE GUIDANCE OF
MRS.SABARIA (ASSISTANT PROFESSOR)

DEPARTMENT OF COMPUTER APPLICATIONS

BCA MULTIMEDIA WEB DEVELOPMENT

BCA RRN – 191501601014, 191501601004 & 191501601019 2nd Review

 ABSTRACT

• Face recognition the process of identifying or veryfying the identify of a personu using
their face .This system is very essential for providing security , law enforcement , user
acces control ,visual surveillance etc .

• One of the key problems of age estimation research—absence of data— we offer a

unique data set of face images, labeled for age and gender we are addressing and adapt
network architectures and algorithmic approaches to deal with these limitations.

• The main goal of this project is to caputure a face , train the face for recognition , detect
the age and gender with Matlab

BCA RRN – 191501601014, 191501601004 & 191501601019 2nd Review

 EXISTING SYSTEM

The various types of challenges coming in the picture during face detection are
described :
Pose , Facial Expression ,Illumination .
We use violla jones algorithm , a simple model, less susceptible to over-fitting. The
shortage of data available for the study of age estimation, and the high dimensionality of
standard face representations .

BCA RRN – 191501601014, 191501601004 & 191501601019 2nd Review

 LIMITATIONS

• Proper centered face is required for training/testing.

• The algorithm is sensitive to lightining, shadows and also scale of face in the
image .
• Front view of the face is required for this algorithm to work properly
 ADVANTAGES :

• The real time datasets for age & gender used will be detection as it
demonstrated better results with 99.4% accuracy .

• Displaying specific advertisements when a particular face is recognized male

between the age of 14 to 22, the screen might show an ad about a FIFA game.

• It can restrict users for a particular sites by recognising their face with age &
gender.

BCA RRN – 191501601014, 191501601004 & 191501601019 2nd Review

 PROPOSED SYSTEM :

• This system can also handle more than one faces .

• Here we use Principal Component Analysis which is used to detect and

analyse the face with accuracy . Preprocessing the face .

• Predeicting the age and gender with the classification such as

(0 – 2), (4 – 6), (8 – 12), (15 – 20), (25 – 32), (38 – 43), (48 – 53),(60 -100)

BCA RRN – 191501601014, 191501601004 & 191501601019 2nd Review

 IMPLEMENTATION TOOLS USED

Prerequisites are:
1. Matlab version
2. GUI

BCA RRN – 191501601014, 191501601004 & 191501601019 2nd Review

 ARCHITECTURAL DIAGRAM :

Initialize protocol
buffer & model Load networks Face database

Principle
componet
analysis
Face Extraction

PCA Technique Training database

EXPECTED
Final Output OUTPUT

BCA RRN – 191501601014, 191501601004 & 191501601019 2nd Review

 LIST OF MODULES :
I. Feature selection
II. Matlab Gui installation
III. Age & Gender Prediction models
IV. Testing & Evaluation
V. Result & Comparison

BCA RRN – 191501601014, 191501601004 & 191501601019 2nd Review

 MODULE - 1
( ALGORITHM , INPUT & LIST OF PROCESS )
This real-time face detection program is developed using MATLAB version
R2012a. A graphic user interface (GUI) allows users to perform tasks
interactively through controls like switches and sliders. You can easily create a
GUI and run it in MATLAB or as a stand-alone application.

• Problem of different size face image recognition, finding the format supported
by the camera and its device ID using various command.

• Algorithm used : Viola jones Algirithm

BCA RRN:191501601014 , 191501601004 & 191501601019 2nd Review

 MODULE - 1 GRAPH

BCA RRN: 191501601014,191501601004 & 191501601019 2nd Review

 SAMPLE CODE FOR MOD - 1
def getFaceBox(net, frame, conf_threshold=0.7):
frameOpencvDnn = frame.copy()
frameHeight = frameOpencvDnn.shape[0]
frameWidth = frameOpencvDnn.shape[1]
blob = cv.dnn.blobFromImage(frameOpencvDnn, 1.0, (300, 300), [104, 117, 123], True, False)

net.setInput(blob)
detections = net.forward()
bboxes = []
for i in range(detections.shape[2]):
confidence = detections[0, 0, i, 2]
if confidence > conf_threshold:
x1 = int(detections[0, 0, i, 3] * frameWidth)
y1 = int(detections[0, 0, i, 4] * frameHeight)
x2 = int(detections[0, 0, i, 5] * frameWidth)
y2 = int(detections[0, 0, i, 6] * frameHeight)
bboxes.append([x1, y1, x2, y2])
cv.rectangle(frameOpencvDnn, (x1, y1), (x2, y2), (0, 255, 0), int(round(frameHeight/150)), 8)
return frameOpencvDnn, bboxes

BCA RRN:191501601014,191501601004 & 191501601019 2nd Review

 WORK COMPLETED :

• The main aim of this project is to detect age and gender through the given data
set. We will use matlab and GUI allows the userto perform tasks interactively.

• The first step completed is , the face is being detected usibg our webcam . And
the estimation of gender whether its male or famele is sucvesfully identified .

BCA RRN:191501601014,191501601004 &191501601019 2nd Review

 SCREEN SHOTS FOR MOD - 1

BCA RRN:191501601014,191501601004 &191501601019 2nd Review

 SCREEN SHOTS FOR MOD - 1I

Female

Male

BCA RRN:191501601014,191501601004 &191501601019 2nd Review

 THANK YOU

BCA RRN – 191501601014, 191501601004 & 191501601019 2nd Review

 WORK TO BE COMPLETED :

• The system should be able to classify a face into a set of age and gender classes;
Initialize the mean values for the model and the lists of age ranges and genders to
classify from.

• we will store in the names resultImg and faceBoxes. And if we got 0 faceBoxes, it
means there was no face to detect. Here, net is faceNet- this model is the DNN Face
Detector.

• We’ll add the gender and age texts to the resulting image and display it with
imshow().

BCA RRN:191501601014,191501601004 &191501601019 2nd Review