0% found this document useful (0 votes)
52 views17 pages

Cosmetic Suggestion System Conference Paper

The document proposes a predictive system that provides recommendations for ideal cosmetic products based on a user's skin type using deep learning techniques. It discusses how the growth of the cosmetic industry and products has made choosing the right product complex. Deep learning can be used to model this problem since it works well with large, unstructured data sources like images of skin types.

Uploaded by

ajeyanajeyan3
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
52 views17 pages

Cosmetic Suggestion System Conference Paper

The document proposes a predictive system that provides recommendations for ideal cosmetic products based on a user's skin type using deep learning techniques. It discusses how the growth of the cosmetic industry and products has made choosing the right product complex. Deep learning can be used to model this problem since it works well with large, unstructured data sources like images of skin types.

Uploaded by

ajeyanajeyan3
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 17

ADVANCED SKIN CATEGORY PREDICTION SYSTEM FOR

COSMETIC SUGGESTION USING


DEEPCONVOLUTION NEURAL NETWORK

1. Dr.B.DHIYANESH 2.Mr.R.ABISHEK 3.Mr.N.ARAVINTH

4.Mr.T.S.R.AJEYAN 5.Mr.M.GOKUL

ASSOCIATE PROFESSOR(1),STUDENT(2,3,4,5)

Dr. N.G.P. Institute of Technology, Kalapatti, Coimbatore.

ABSTRACT

Nowadays, cosmetic product s are quite important to personality look.


Customers get access to a variety of products through online shopping and e-
commerce websites. We find it challenging to choose the ideal product for our
skin. Therefore, we suggest a predictive system that provides a precise concept
of which product is ideal for our skin type. The composition is determined by
the skin types, which can be oily, dry, or neutral. The composition proposal will
be superior than the established method. We will make the difficult task for the
IT sector in cosmetic and beauty care easier by utilising deep learning
techniques. The beauty sector is expanding rapidly over time, which has a
positive knock-on effect on both the products it offers and its customers. So
based on this expansion of products and consumers,the selection of appropriate
cosmetic product becomes very important.There is a necessity to choose the
ideal cosmetic product for oneself based on personal factors because cosmetics
play a significant part in one's appearance (i.e. skin type). As every person has a
different skin texture, finding the ideal cosmetic for a user's skin type is
notoriously difficult. Even if we locate the right product for the consumer, skin
problems can still arise because of very complex issues.For solving this problem
of beauty industry we can use AI algorithms, as it works fine with unstructured
and large amount of data with promising result

Keywords – Cosmetics, Skin type, Deep learning methods, AI algorithms

1. INTRODUCTION

Over the years cosmetic industries becomes more and more vast, and so the
products offered by this industry and the customers are also increased. As a
result of this growth in both products and customers, choosing the right
cosmetic product is complex. It is necessary to choose the appropriate cosmetic
product for each and individual based on personal factors (i.e skin type),
because cosmetic products have a significant part in one's appearance. Finding
the ideal cosmetic for a user's skin type is notoriously difficult because each
person has a different skin texture. For solving the problem of choosing the best
product based on skin type we can use machine learning’s framework - deep
learning, as it works fine with unstructured and large amount of data.

1.1 Cosmetic Product Composition

Cosmetic product refers to the products that one is using for betterment of their
appearance. It can include various types of cosmetic items - Lipsticks, Kajal,
Eyeliner, Foundation, Eye shadow, Mascara, Compact, Face wash, Body lotion
etc. As everyone is not so good at choosing right product for them, so this
solution will definitely help them out.

1.2 Need for Deep Learning

Deep Learning has enabled numerous studies in fields such as computer vision,
natural language processing, machine translation, chat bots, and many others in
recent years. They provide consistent performance while removing the ability to
learn feature representation from scratch. This influence was also felt in the
recommendation area, where deep learning methods outperformed traditional
methods. Deep neural networks are composite in the sense that they are made
up of multiple neural building blocks that are combined into a single
differentiable function and trained end-to-end. In contrast to linear models, deep
neural networks can model nonlinearity in data using nonlinear activations such
as relu, sigmoid, tanh, and so on. It is now possible to capture complex and
intricate user item interaction patterns. Deep learning techniques have a high
degree of flexibility, especially since the introduction of many popular deep
learning frameworks such as TensorFlow a, Keras b, and PyTorchc. The
majority of these tools are developed in a modular manner and have active
community and professional support. Good modularization makes development
and engineering much more efficient.

1.3 Various Deep Learning Techniques:

DNN: An Artificial Neural Network (ANN) with numerous layers in between


the input and output layers is known as a Deep Neural Network (DNN).
Whether there is a linear or non-linear relationship between the input and
output, the DNN determines the proper mathematical transformation.

CNN: A particular type of feedforward neural network called a convolutional


neural network (CNN) has convolutional layers and pooling operations. The
efficiency and accuracy are much improved since it can capture both global and
local features. When processing data with a grid-like topology, it works well.

RNN: Sequential data modelling is appropriate for recurrent neural networks


(RNN). There are loops and memories for remembering the previous
computation.
DBN: A deep belief network (DBN) is a type of deep neural network used in
machine learning. It is made up of numerous layers of latent variables, or
"hidden units," with connections between the layers but not between the units
within each layer.

AE: An unsupervised model called an autoencoder (AE) tries to reconstruct its


input data in the output layer. The middle-most layer, known as the bottleneck
layer, is typically utilised to represent the input data's prominent features.
Denoising autoencoders, marginalisation denoising autoencoders, sparse
autoencoders, contractive autoencoders, and variational autoencoders (VAE) are
examples of autoencoder variations.

2.LITERATURE SURVEY

2.1 Deep learning: The MIT Press

Deep Learning provides a truly comprehensive look at the state of the art in
deep learning and some developing areas of research. The book is aimed at an
academic research audience with prior knowledge of calculus, linear algebra,
probability, and some programming capabilities.The authors are Ian
Goodfellow, along with his Ph.D. advisor Yoshua Bengio, and Aaron Courville.

Deep Learning provides a truly comprehensive look at the state of the art in
deep learning and some developing areas of research. The book is aimed at an
academic research audience with prior knowledge of calculus, linear algebra,
probability, and some programming capabilities.The authors are Ian
Goodfellow, along with his Ph.D. advisor Yoshua Bengio, and Aaron Courville.
Deep Learning provides a truly comprehensive look at the state of the art in
deep
learning and some developing areas of research. The authors are Ian
Goodfellow,
along with his Ph.D. advisor Yoshua Bengio, and Aaron Courville. All three are
widely published experts in the field of artificial intelligence (AI). In addition to
being available in both hard cover and Kindle the authors also make the
individual
chapter PDFs available for free on the Internet.
1
The book is aimed at an academic
research audience with prior knowledge of calculus, linear algebra, probability,
and
some programming capabilities. A non-mathematical reader will find this book
difficult. A comprehensive, well cited coverage of the field makes this book a
valuable reference for any researcher. The book provides a mathematical
description of a comprehensive set of deep learning algorithms, but could
benefit
from more pseudocode examples. The authors provide an adequate explanation
for
the many mathematical formulas that are used to communicate the ideas
expressed
in this book. The lack of both exercises and examples in any of the major
machine
learning software packages makes this book difficult as a primary undergraduate
textbook.
While a review of a book focused entirely on deep learning might not be the
usual topic for Genetic Programming and Evolvable Machines, there are many
areas
of interest for the genetic programming (GP) and evolutionary algorithm
research
communities. The effect of deep learning upon the field of AI has been
profound.
Deep learning’s application to diverse cases ranging from self-driving cars to
the
game of Go have been widely reported.
Deep Learning provides a truly comprehensive look at the state of the art in
deep
learning and some developing areas of research. The authors are Ian
Goodfellow,
along with his Ph.D. advisor Yoshua Bengio, and Aaron Courville. All three are
widely published experts in the field of artificial intelligence (AI). In addition to
being available in both hard cover and Kindle the authors also make the
individual
chapter PDFs available for free on the Internet.
1
The book is aimed at an academic
research audience with prior knowledge of calculus, linear algebra, probability,
and
some programming capabilities. A non-mathematical reader will find this book
difficult. A comprehensive, well cited coverage of the field makes this book a
valuable reference for any researcher. The book provides a mathematical
description of a comprehensive set of deep learning algorithms, but could
benefit
from more pseudocode examples. The authors provide an adequate explanation
for
the many mathematical formulas that are used to communicate the ideas
expressed
in this book. The lack of both exercises and examples in any of the major
machine
learning software packages makes this book difficult as a primary undergraduate
textbook.
While a review of a book focused entirely on deep learning might not be the
usual topic for Genetic Programming and Evolvable Machines, there are many
areas
of interest for the genetic programming (GP) and evolutionary algorithm
research
communities. The effect of deep learning upon the field of AI has been
profound.
Deep learning’s application to diverse cases ranging from self-driving cars to
the
game of Go have been widely reported.
Deep Learning provides a truly comprehensive look at the state of the art in
deep
learning and some developing areas of research. The authors are Ian
Goodfellow,
along with his Ph.D. advisor Yoshua Bengio, and Aaron Courville. All three are
widely published experts in the field of artificial intelligence (AI). In addition to
being available in both hard cover and Kindle the authors also make the
individual
chapter PDFs available for free on the Internet.
1
The book is aimed at an academic
research audience with prior knowledge of calculus, linear algebra, probability,
and
some programming capabilities. A non-mathematical reader will find this book
difficult. A comprehensive, well cited coverage of the field makes this book a
valuable reference for any researcher. The book provides a mathematical
description of a comprehensive set of deep learning algorithms, but could
benefit
from more pseudocode examples. The authors provide an adequate explanation
for
the many mathematical formulas that are used to communicate the ideas
expressed
in this book. The lack of both exercises and examples in any of the major
machine
learning software packages makes this book difficult as a primary undergraduate
textbook.
While a review of a book focused entirely on deep learning might not be the
usual topic for Genetic Programming and Evolvable Machines, there are many
areas
of interest for the genetic programming (GP) and evolutionary algorithm
research
communities. The effect of deep learning upon the field of AI has been
profound.
Deep learning’s application to diverse cases ranging from self-driving cars to
the
game of Go have been widely reported.
Deep Learning provides a truly comprehensive look at the state of the art in
deep
learning and some developing areas of research. The authors are Ian
Goodfellow,
along with his Ph.D. advisor Yoshua Bengio, and Aaron Courville. All three are
widely published experts in the field of artificial intelligence (AI). In addition to
being available in both hard cover and Kindle the authors also make the
individual
chapter PDFs available for free on the Internet.
1
The book is aimed at an academic
research audience with prior knowledge of calculus, linear algebra, probability,
and
some programming capabilities. A non-mathematical reader will find this book
difficult. A comprehensive, well cited coverage of the field makes this book a
valuable reference for any researcher. The book provides a mathematical
description of a comprehensive set of deep learning algorithms, but could
benefit
from more pseudocode examples. The authors provide an adequate explanation
for
the many mathematical formulas that are used to communicate the ideas
expressed
in this book. The lack of both exercises and examples in any of the major
machine
learning software packages makes this book difficult as a primary undergraduate
textbook.
While a review of a book focused entirely on deep learning might not be the
usual topic for Genetic Programming and Evolvable Machines, there are many
areas
of interest for the genetic programming (GP) and evolutionary algorithm
research
communities. The effect of deep learning upon the field of AI has been
profound.
Deep learning’s application to diverse cases ranging from self-driving cars to
the
game of Go have been widely reported.

2.2 Proposal of recommender system based on user evaluation and


cosmetic ingredients

We extracted the effective cosmetic ingredients for each user attribute and
developed a recommender system of basic cosmetics based on ingredients. We
applied the IF-IPF method which applied the concept of TF-IDF method to
extraction of effective ingredients of cosmetics - Rio Iwabuchi, Yoko Nakajima,
Hirotoshi Honma, Haruka Aoshima, Akio Kobayashi, Tomoyoshi Akiba,
Shigeru Masuyama

2.3 Visual Siamese Clustering for Cosmetic Product Recommendation

In this the authors Christopher J Holder, Boguslaw Obara, Stephen Ricketts,


were trained a Siamese convolutional neural network, using dataset of cropped
eye regions from images of 91 female subjects. They evaluate trained network
based on its ability to correctly identify existing subjects from unseen images
and then assess its capability to find visually similar matches amongst the
existing subjects.

[1] Z. Ma'or and M. Portugal-Cohen, "Injecting Innovation to Traditional,


Natural Cosmetic Ingredients: The Case of Dead Sea Minerals," in IEEE
Engineering Management Review, vol. 49, no. 2, pp. 73-80, 1 Second quarter,
june 2021.

[2] R. S, H. S, K. Jayasakthi, S. D. A, K. Latha and N. Gopinath, "Cosmetic


Product Selection Using Machine Learning," 2022 International Conference on
Communication, Computing and Internet of Things (IC3IoT), Chennai, India,
2022, pp. 1-6.

[3] M. Wang, "Empirical Study on Cosmetics Purchasing Intention of


Traditional Chinese Cosmetics Customers," 2021 5th Annual International
Conference on Data Science and Business Analytics (ICDSBA), Changsha,
China, 2021, pp. 357-361.

[4] Z. Wu et al., "Cosmetic safety risk assessment model and system


implementation based on six-dimensional classification," 2021 International
Conference on Internet, Education and Information Technology (IEIT), Suzhou,
China, 2021, pp. 31-34.

[5] S. Acharya, S. Bali and B. S. Bhatia, "Exploring Consumer Behavior


towards Sustainability of Green Cosmetics," 2021 International Conference on
Advances in Electrical, Computing, Communication and Sustainable
Technologies (ICAECT), Bhilai, India, 2021, pp. 1-6.

[6] L. Yang, "A study on optimization design of cosmetics sustainable service


system and case-based design on Xie fuchun," 2020 International Conference
on Innovation Design and Digital Technology (ICIDDT), Zhenjing, China,
2020, pp. 142-146.

[7] Y. Ishitsuka, "Possibility of Fusion: Cosmetic Research and Electronics,"


2019 International Conference on Electronics Packaging (ICEP), Niigata, Japan,
2019, pp. 1-2.

[8] R. Stam et al., "Progress report: ICNIRP Statement on non-ionizing


radiation for cosmetic purposes," 2018 EMF-Med 1st World Conference on
Biomedical Applications of Electromagnetic Fields (EMF-Med), Split, Croatia,
2018, pp. 1-2.
[9] V. Gauthier, D. Desplan, S. Serfaty, M. Michiel, E. Caplain and J. -Y. Le
Huérou, "Multi-Frequency Ultrasonic Shear Waves Rheology for Soft Materials
Monitoring in Cosmetics," 2017 Cosmetic Measurements And Testing
(COSMETIC), Cergy-Pontoise, France, 2017, pp. 1-4.

3.PROPOSED SYSTEM

In the proposed system we will implement the best composition of cosmetic


product using AI architectures (Convolution Neural Network). The suggested
approach uses input features, such as product ingredients and skin type
compatibility, which are transmitted to the input layer and subsequently to the
hidden layers for automatic feature learning. Finally we will get composition of
cosmetic products on the output layer. The suggestion for the composition will
better than the traditional system by enhancing the quality of datasets using
techniques like grayscale conversion, edge detection, median blur which will
improves the accuracy and quality of datasets as well as for the customers input.

4. PROPOSED ARCHITECTURE
4.1 CNN LAYERS
5. PROPOSED ALGORITHM

In deep learning, a convolutional neural network (CNN) is a type of deep neural


networks, which deals with the set of data to extract information about that data.
Like images, sounds or videos etc. can be used in the CNN for the data
extraction. There are mainly three things in CNN. First one is local receptive
field and then shared weight and biases and the last one is activation and
pooling. In CNN, first the neural networks are trained using a heavy set of data
so that the CNN can extract the feature of given input. When the input is given,
first image preprocessing is done then the feature extraction occurs on the basis
of set of data stored and then the classification of data is done and output is
shown as the result. The CNN can deal with those input only for what the neural
network is trained and the data is saved. They are used in image and video
recognition, recommender systems, image classification, medical image
analysis, and natural language processing

ADVANTAGES OF USING CNN

You do not need to flatten the input photos to 1D because CNNs are capable of
working with image data in 2D, which is a significant benefit over NNs. This
helps in retaining the “spatial” properties of images. So here we are using
different type of skin data set which consist of four categories

6. RESULT
7. CONCLUSION

Decision making in today’s world is more complex than the past, as for consumers
who are now confronted by various kind of choice for each type of products and
brands. This approach provides the composition based on skin types (i.e. dry, oily or
natural). Our main aim is to serve better composition of cosmetic products. By using
AI algorithm technique the proposed system will definitely help in better
composition of cosmetic products.

8. FUTURE WORK

This system can be improved by several aspects which are considered as a


future work such as extending the dataset, expanding the system to recommend
for females and males, learning the knowledge base rules directly from the
labeled data and adding more templates and colors to the makeup synthesis
library to recommend more styles.

9. REFERENCES

[1] Z. Ma'or and M. Portugal-Cohen, "Injecting Innovation to Traditional,


Natural Cosmetic Ingredients: The Case of Dead Sea Minerals," in IEEE
Engineering Management Review, vol. 49, no. 2, pp. 73-80, 1 Second quarter,
june 2021.

[2] R. S, H. S, K. Jayasakthi, S. D. A, K. Latha and N. Gopinath, "Cosmetic


Product Selection Using Machine Learning," 2022 International Conference on
Communication, Computing and Internet of Things (IC3IoT), Chennai, India,
2022, pp. 1-6.

[3] M. Wang, "Empirical Study on Cosmetics Purchasing Intention of


Traditional Chinese Cosmetics Customers," 2021 5th Annual International
Conference on Data Science and Business Analytics (ICDSBA), Changsha,
China, 2021, pp. 357-361.

[4] Z. Wu et al., "Cosmetic safety risk assessment model and system


implementation based on six-dimensional classification," 2021 International
Conference on Internet, Education and Information Technology (IEIT), Suzhou,
China, 2021, pp. 31-34.

[5] S. Acharya, S. Bali and B. S. Bhatia, "Exploring Consumer Behavior


towards Sustainability of Green Cosmetics," 2021 International Conference on
Advances in Electrical, Computing, Communication and Sustainable
Technologies (ICAECT), Bhilai, India, 2021, pp. 1-6.

[6] L. Yang, "A study on optimization design of cosmetics sustainable service


system and case-based design on Xie fuchun," 2020 International Conference
on Innovation Design and Digital Technology (ICIDDT), Zhenjing, China,
2020, pp. 142-146.

[7] Y. Ishitsuka, "Possibility of Fusion: Cosmetic Research and Electronics,"


2019 International Conference on Electronics Packaging (ICEP), Niigata, Japan,
2019, pp. 1-2.

[8] R. Stam et al., "Progress report: ICNIRP Statement on non-ionizing


radiation for cosmetic purposes," 2018 EMF-Med 1st World Conference on
Biomedical Applications of Electromagnetic Fields (EMF-Med), Split, Croatia,
2018, pp. 1-2.

[9] V. Gauthier, D. Desplan, S. Serfaty, M. Michiel, E. Caplain and J. -Y. Le


Huérou, "Multi-Frequency Ultrasonic Shear Waves Rheology for Soft Materials
Monitoring in Cosmetics," 2017 Cosmetic Measurements And Testing
(COSMETIC), Cergy-Pontoise, France, 2017, pp. 1-4.

You might also like