AGE AND GENDER

PREDICTION FOR
BETTER
MARKETING
STRATEGIES
Sasi Kiran Darbha (19311A1999)
Tanay Vel (19331A19B0)
Manoj Surnam (19311A19B9)

PROJECT GUIDE – P.RAMYA VANI

ABSTRACT

Because of its wide range of applications in a variety of facial

investigations, automatic age and gender prediction from face
photos has recently gained a lot of attention. We can leverage the
aforementioned technologies to determine a person's age and
gender just on a single glimpse from a camera, image, or video
using Deep learning methods. Now we use this data of age and
gender to recommend any content like clothing to the user. We use
Content-based Recommender Systems (CBRS) to recommend
clothing.

2
INTRODUCTION
Gender and age play a significant role in interpersonal interactions
among people who live in communities.
The use of smart gadgets has expanded as technology has progressed,
and social media has begun to draw everyone's attention.
For gender detection and age prediction, Image processing, feature
extraction, and classification steps are usually used.
For image processing, there are two basic and typical which we need to
follow. Image enhancement is the process of improving an image so
that the resultant image is of higher quality and can be used by other
applications.

3
INTRODUCTION
We can use the features of the image that is extracted to recommend the
user to reach their needs faster and can also be useful in online sales
systems.
We can use Content-based Recommender Systems (CBRS) unlike the
CFRS are not interested in the similarity between users. These systems
basically deal with the resemblance and closeness of the items
according to the data given to them.

4
LITERATURE REVIEW
In 2017, [2] k. Zang, et al. proposed Residual network of Residual network (ROR)
for automatic prediction of age and gender from face images of unconstrained
condition. The architecture is for high resolution facial images age and gender
classification. Two mechanisms such as pretrained by gender and training with
weighted loss layer, and used to improve the performance of age estimation. In
order to future improve the performance and alleviate overfitting problem, ROR is
pretrained on ImageNet, then it is fine-tuned on IMBD-WIKI 101dataset for
further learning the features of face images and finally tuned on Adience dataset.
High accuracy is achieved for gender classification task works well for high
resolution facial images. Age estimation accuracy of 67.37% and gender
estimation accuracy of 93.27%. Lower age estimation accuracy and ROR model is
slower than other models make this challenging. Accuracy of age estimation
sometimes affect due to minor change in alignment. Issue of dataset i.e., Adience.
Works well on some specific features only.

5
LITERATURE REVIEW
In 2018,[3] Philip smith, et al., transfer learning is employed to tackle the issue of
recognizing a person’s age and gender from an image using deep CNNs. Transfer
learning to use VGG19 and VGGFace pretrained models are used to increase the
efficiency. Training techniques such as input standardization, data augmentation,
label distribution age encoding is compared. Dataset used is MORPII.VGGFace
produce better result than VGG19. VGGFace takes far fewer epochs to fit the
training data VGGFace gender prediction accuracy of 98.68% of 4.1 years. Age
recognition produces MAE of 4.1 years due to female characteristics. Gender
prediction is largely based on the absence and presence of long hair, tilt of head.
Larger and more dataset is necessary. Mislabeled data and excessive noise can
cause model to start learning wrong things. The major problem caused by this
research is due to dataset i.e., MORP II. In this dataset few noisy variations: heads
are tilted in different direction. Most images of age ranges from 16 to 77. Most of
them are male images and black colored.

6
LITERATURE REVIEW
In 2019, [4] Ningning Yu, et al. proposed an ensemble learning used for facial age
estimation within non-ideal facial imagery in Fig[1] . The method consists of mainly
image preprocessing, feature extraction, and age predication. Separately, the input face
image is preprocessed in RGB Stream, Luminance Modified Stream, and YIQ Stream.
Three different pretrained DCNNs equipped with softmax are wont to implement
feature extraction and age estimation because the weak classifiers. Finally, the
ensemble learning module fuses the three weak classifiers to get a more accurate
estimation. Dataset used is IMBD-WIKI from Wikipedia. Three stream method
improves the performance. To generate more accurate classification, ensemble learning
to fuse the weak classifiers. To evaluate the performance of classification, some
evaluation indexes such as AEM (Exact match) and AEO (An error one age category).
With ensemble method, AEM of 45.57% and AEO of 88.20%. Need an efficient global
search method is necessary. Require an algorithm based on dataset which cover more
data. DCNN requires large time for feature extraction and training.

7
LITERATURE REVIEW
Yun-Rou Lin et al in [11] presented (appropriate) clothing with proper size
recommendation by considering factors such as gender, body height and clothing
features. Online texture modeling was implemented to produce variety in the texture
of clothing so their proposed system can create logical and diverse options for
consumers. They used CNN (Convolutional Neural Network) for gender recognition,
Dlib for face detection [12], and InceptionV3 (GoogleNet) for clothing attributes
recognition. Their attributes contain five clothing categories with eight dimensions.
Batuhan AŞIROĞLU et al in [13], developed a recommender system by taking just a
single photo of the user with their scalable embedded system. Their recommendation
is made regardless of shopping history of the user. The utilized hardware is a Linux
based system and a low-cost Raspberry Pi Zero W. They developed two inceptions
based CNN, one for the prediction part and one for feed-forward NN as a
recommender system. The prediction part exploits from Haar-Cascade of OPENCV
python library for user’s face gender detection.

8
METHODOLOGY:
DEEP LEARNING
Deep learning is an artificial intelligence (AI) technique that seeks
to learn from experience to resemble the human brain.

Through a training procedure, these representations are learned. To

teach the software how to detect an object, we must first train it
with a large number of object images that we categorise according
to different classes.

A neural network with multiple hidden layers is known as deep

learning.

9
METHODOLOGY:
DEEP LEARNING
As the layers grow larger, the network may learn more complex
features and eventually merge them to identify the image.

In the field of computer vision, deep learning has discovered a

bunch of use.

The domains that work with facial data were among the most
important computer vision applications.

10
METHODOLOGY:
CNN
A CNN (convolutional neural network) is a kind of artificial neural
network that is commonly used for image or object identification and
categorization.

Using a CNN, Deep Learning recognises items in an image. An input

layer, hidden layers, and an output layer are all part of a standard neural
network.

Multiple hidden layers may exist in CNNs, each of which performs

feature extraction from the image by performing calculations.

11
 METHODOLOGY:
CNN
The object is classified and identified in the output layer by the fully
connected layer.

12
METHODOLOGY:
CNN

20XX Pitch deck title 13

CNN MODEL

PREREQUISITE IMPLEMENTATION

• We must first extract the face from a webcam • Face detection utilising Haar feature-based
image before proceeding with the cascade classifiers, which is a machine
implementation. The OpenCV library in Python learning-based approach. There will be a large
is used to accomplish this. number of positive and negative photos, on
which the classifier will be trained.
• An effective object detection method is face
detection utilising Haar feature-based cascade • It's then utilised to find faces in other pictures.
classifiers, which is a machine learning-based
approach.

14
EXISTING SYSTEM
Today, due to the current situation caused by the Coronavirus, the majority of tasks are done online. Online
clothes shopping systems are one of them. Although they have excited before but because of the current
situation a lot more attentions have been turned towards them.
Content-Base recommender systems require product features. In a sense, due to the fact that the data volume of
these products is considerably high, entering the features of these products manually into system is extremely
time-consuming. One of the most important benefits of using deep learning is its ability to execute feature
extraction. Another benefit of it is the elimination of the need for data labeling and maximum utilization of
unstructured data.

15
EXISTING SYSTEM

20XX Pitch deck title 16

EXISTING SYSTEM
Clothing categories being high-level semantic concepts, various clues which are relevant to recognize
them, such as a person’s gender and age, uncovered skin areas, color and texture features of clothes are
used. First, face detection and tracking for each frame is performed and the detected faces are aligned.
For clothing segmentation, a light weight region growing based clothing segmentation is performed.
After that, multi-class linear SVM classifiers are employed to learn the clothing categories.

17
PROPOSED SYSTEMS
Our proposed system uses a deep convolution neural network to detect
categories, product gender, and feature extraction from an image. A
Convolutional Neural Network (CNN, or ConvNet) is a class of deep neural
networks, mostly used to analyze images and videos. CNNs are a version of
fully connected multilayer perceptron. That means each neuron in each layer
is connected to all neurons in the next layer. Each convolution layer
convolves the input by a specific filter and passes its result to the next layer
[15]. As images have high dimensions, every pixel of an image is considered
as a feature, so when we want to pass it to a multilayer perceptron the
volume of computations and parameters grows rapidly. CNNs are an efficient
solution for reducing the number of parameters without losing quality on the
models. Since our data is an image, we also use CNNs. We have
implemented our design model with Keras .

18
PROPOSED SYSTEMS

19
PROPOSED SYSTEMS
Fig. 6 depicts the Proposed System which consists of different modules. User is the
one who uses the system. Interface will be provided to the user to access the system.
User can give the following inputs. He can upload photos to insert clothes in his
digital wardrobe which will be the cache memory of his mobile phone. He needs to
provide his personal attributes like age, gender, skin tone etc. He can also give his
preference setting like favorite color, brand etc. The interface will have all the
features. By using the features as required by the user, he can get the intended results.
The system will detect clothes from the image, crop the useful part and do the needful
alignment. The system will also do the segmentation, classification and categorization
using different modules trained and tested by the dataset. The CNN and RNN models
will extract the features from the images and give output in the feature vector format.
to the interface

20
 PROPOSED SYSTEMS
This output will be used by different algorithms. The system has matching and
recommendation models which will provide the user with best case matching
combinations as well as useful recommendations. This model will work in unison with
the preference model which contains user attributes and give the user specific output.
The system will perform different functions in the back-end. These functions are
directly related to the features provided to the users. Once the user wants a particular
feature it will trigger the system to do a particular function to bring the intended result
and then this result will be sent

21
CONCLUSION

At Contoso, we believe in giving 110%. By using our next-

generation data architecture, we help organizations virtually
manage agile workflows. We thrive because of our market
knowledge and great team behind our product. As our CEO says,
"Efficiencies will come from proactively transforming how we do
business."

22
THANK YOU