DON BOSCO INSTITUTE OF TECHNOLOGY

MYSORE ROAD, KUMBALAGODU, BANGALORE - 560074

COMPUTER SCIENCE AND ENGINEERING

DURING ACADEMIC YEAR 2019-2020

INTERNSHIP PRESENTATION ON:

MACHINE LEARNING USING PYTHON

Submitted By: Under The Guidance Of:

Omansh Srivastava 1DB16CS097 Professor Thaseen Taj

Asst. Professor
Dept. Of Computer Science And Engineering
INTRODUCTION TO VERZEO EDUTECH
 PROBLEM DEFINITION

• Over the recent years, a great deal of effort has been made to age estimation & gender
recognization from face images.
• It has been reported that age can be accurately estimated under controlled environment such as
frontal faces, no expression, and static lighting conditions.
• However, it is not straightforward to achieve the same accuracy level in real-world environment
because of considerable variations in camera settings, facial poses, and illumination conditions.
• In this paper, we apply a recently-proposed machine learning technique called covariate shift
adaptation to alleviating lighting condition change between laboratory and practical environment.
• Through real-world age estimation experiments, we demonstrate the usefulness of our proposed
method
 LITERATURE SURVEY
S.NO TITLE OF PAPER AUTHOUR PUBLICATION TECHNIQUE USED

1 Age and Gender Estimation of Eran Eidinger, Roee IEEE TRANSACTIONDEC. Robust face alignment
Unfiltered Faces 2014 technique, SVM
2 Automated Estimation of Human Yaoyu Tao Stanford, CA 94305, USA LBP & Gabor filter LDA
Age, Gender and Expression [email protected] algorithm

3 Comparison of Recent Machine Joseph Lemley Central Washington Feature extraction

Learning Techniques for Gender Sami Abdul-Wahid University Ellensburg, techniques: PCA & HOG.
Recognition Dipayan WA, USA MAICS 2016 Gender classification
methods
4 Age Group Estimation using Face Ranjan Jana, (IJEIT) Volume 3, Issue 2, K-means clustering
Features Debaleena Datta, August 2013 algorithm. PCA, LDA
Rituparna
5 Partial Face Recognition: Shengcai Liao, Anil IEEE transactions on PCA + LDA & LBP Canny
Alignment-Free Approach K. Jain, Fellow, IEEE pattern analysis edge detector
and Stan Z. Li
 OBJECTIVES
• The main objective of this project is to recognize and predict gender and age from face.

• Using various machine learning techniques for increasing accuracy and precision of both
recognition and prediction processes.

• To reduce the delay of entire process using techniques like SVM(Support Vector Machine)
 METHODOLOGIES
WEEK 1
Machine Learning

• Data analysis is a process of inspecting, cleansing, transforming, and modeling data with the goal of
discovering useful information ,informing conclusions and supporting decision-making.

• Machine learning is an application of artificial intelligence (AI) that provides systems the ability to
automatically learn and improve from experience without being explicitly programmed.

Introduction To Python

• Python is widely used general purpose high level programming language.

• Python programming language lets you work quickly and integrate system more efficiently.

• Python can be used to handle BigData and used to perform complex math.
 WEEK 2
Gender Recognization
1. Input an Image
2. Detect skin area in Input Image.
3. Detect Features like eyes and mouth in skin region.
4. If Features detected then go to step 5 else step 1.
5. Crop Face.
6. Load Database Male Females features.
7. Locate Features in a face area.
8. Count Male & female Features.
9. Filter Counted features into strong & weak features.
10. Form Fuzzy Conclusion from features & Display gender
result.
 WEEK 3
Age Prediction(Training)
1. Select an Input Image.
2. Detect skin area in Input Image.
3. Detect Features like eyes and mouth in skin
region.
4. If Features detected then go to step 5 else
step
5. Crop Face.
6. Save Face into Database with its age.
7. Repeat step 1 to 6 for 100 images (Training
Images)
 WEEK 4
Age Prediction (Testing)
1. Select an Input Image.
2. Detect skin area in Input Image.
3. Detect Features like eyes and mouth in skin
region.
4. If Features detected then go to step 5 else step
5. Crop Face.
6. Load faces Images from training directory &
Match With input face image.
7. Retrieve Match image age from database.
8. Display Result.
9. Stop
ARCHITECTURE
 OUTCOME
• The main outcome of this project is that it is recognizing and predicting
gender and age from faces as input.

• The accuracy and precision of both the processes ,gender recognition and
age prediction has been increased to 85%.

• Delay of entire process has been reduced using techniques like SVM.
 CONCLUSION
• Age, gender and other facial traits represent information important to a wide range of tasks.

• Our work leads us to the conclusion that wrinkle geography analysis has been the best procedure
to estimate human age range of an individual.

• Image should be of a straight frontal face ,Image could contain multiple human face.

• This project works with 85% accuracy for age group clusters, and 85% accuracy for gender
recognition.

• SVM(Support Vector Machine) classifier is used for age group estimation and we finalize LBP(Local
Binary Pattern) technique for gender identification
 REFERENCES
[1]. H. Ai and Z. Yang. Demographic classi_cation with local binary patterns. Advances in Biometrics,
4642:464{473, August 2007.

[2]. A.N.Akansu and R.A. Haddad. Multiresolution Signal Decomposition: Transforms, Subbands, and
Wavelets. Telecommunications Series. Academic Press, 2001.

[3]. A. Alahi, R. Ortiz, and P. Vandergheynst. Freak: Fast retina keypoint. In Proceedings of the 2012
IEEE Conference on Computer Vision and Pattern Recognition(CVPR)June 2012.

[4]. F.A. Alomar, G. Muhammad, H. Aboalsamh, M. Hussain, A.M. Mirza, and G. Bebis. Gender recognition
from faces using bandlet and local binary patterns. In 20th International Conference on Systems,
Signals and Image Processing (IWSSIP), pages 59{62, July 2013.

[5]. P.N. Belhumeur, J.P. Hespanha, and D. Kriegman. Eigenfaces vs. sherfaces: recognition using class
specific linear projection. volume 19, pages 711{720, Jul 1997.
THANKS
Do you have any
questions?

[email protected]