A KNN Classifier for Face

Recognition

Submitted By,
Ayswaryalakshmi M G
Contents
• Abstract
• Introduction
• Methods
 Training Phase
 Testing Phase
• Data Source
• Image Enhancement
• Feature Extraction
• KNN Classification
• Results & Discussion
• Conclusion
• Reference
Abstract
• Face identification has been widely applied for security on gadgets, smart home security, and others.

• Face recognition utilizes facial features for security purposes.

• The classification method in this paper is K-nearest Neighbor (KNN).

• The KNearest Neighbor algorithm uses neighborhood classification as the predictive value of a good
instance value.

• This paper developed face identification using Principal Component Analysis (PCA).

• Method that used in this paper is contrast stretching, grayscale and haar cascade segmentation.
Introduction
• Face is one of the most popular types of biometrics at the moment.

• Facial biometrics is a personal identification system that is very different from one
person to another.

• This difference makes face as a biometric that is widely applied besides is easily
acquired.

• The study entitled Real-Time Face Detection and Recognition in Complex Back-ground
has researched facial biometrics.
Introduction Conti...
• Ada Boost, cascade classifier, Local Binary Patent (LBP), Haar-like features, face image
pre-processing and Principal Component Analysis (PCA) are a series of signal processing
methods.

• Three stages carried out in this study to identify face,

 Face detection

 Feature extraction

 Classification

• This paper develops face identification using the K-Nearest Neighbor (KNN) method and
using feature extraction Principal Component Analysis (PCA).

• Classification method used is K-nearest Neighbor (KNN)

Methods
 Training Phase of Face identification
Methods Conti...
 Testing Phase of Face Identification
Data Source
• It used comes from manual shoots.

• This dataset research contains 790 faces from 158 people taken from several angles.

• The dataset has not gone through the segmentation process so that there is still a background that is
quite significant outside the face object.

Dataset has been separated

into each folder containing the
name of the individual owner
of the face.
Image Enhancement
• It is an accentuation or sharpening of the elements of an image such as edge and boundaries.

• Stages consists of ROI (Region of Image), image conversion to grayscale and contrast stretching.

• Image enhancement technique increase contrast in the image by stretching called Contrast stretching.

• Its concept is to maintain the range of values of intensity it contains to reach the desired range of values.
Feature Extraction
• It is a process which is extracted features to encourage
the classifier to make decisions when classifying.

• PCA method reduces the dimensions of data with the

least amount of information loss.

• In the PCA method, faces are described as linear

combinations of eigenvector weights called Eigenfaces.
This eigenvector is a covariance matrix from the image
database.

• The number of images in the database will be the same

as the number of Eigenfaces received.
KNN Classification
• KNN is one of the simple algorithms that can be used for
classification.

• Face classification is a stage for the process of matching

testing data and training data from face datasets.

• The classification stages in face identification systems

use the K-Nearest Neighbor (KNN) method where the
eigen image of the feature extraction process used as
input is as follows.
Result & Discussion
Result & Discussion Conti...

Table 1 is a testing process used the K-Nearest Neighbor (KNN) method with

parameters k=1 using face training data with 30 classes consist of 2 testing data and 3

training data, which obtained an accuracy or F1-score of 81%.

Result & Discussion Conti...
Result & Discussion Conti...

Table 2 a testing process used the K-Nearest Neighbor (KNN) method

with parameters k=2 using face training data with 30 classes, which

obtained accuracy or F1-score of 53%.

Result & Discussion Conti....

Table 3 a testing process used the K-Nearest Neighbor

(KNN) method with parameters k=3, using face training

data with 30 classes where accuracy or F1- score is 47%.

Result & Discussion Conti...

• Testing scenario in this research by using parameter k=1, k=2, and k=3, give the best

accuracy is on k=1 with 81%, while k=2 give 53%, and k=3 is 47%. It shows the value of k

affected to the accuracy.

• From this paper we can tell that the higher k value is the smaller accuracy that we get for

face identification using KNN.

Conclusion
• In this paper we have presented an experiment for face identification using the KNN method.

• The face identification using the KNN method consists of two stages, such as the training phase and the
testing phase.

• Based on the results by changing the parameter k value obtained results are different for each
parameter.

• The parameter k value and accuracy are inversely proportional, the greater k value gives the smaller
accuracy of the identification system.

• From this paper can be concluded that the higher k value is the smaller accuracy that we get for face
identification using KNN.
References
[1] Biometrics Institute. (2017). Kairos- Protect your business and create frictionless customer experiences with face recognition.
Retrieved from https://www.kairos.com/face-recognition-for-security.

[2] Ding, C., Xu, C., & Tao, D. (2015). Multi-Task Pose-Invariant Face Recognition. IEEE Transactions on Image Processing, 24(3), 980 -
993.

[3] Zhang, X., Gonnot, T., & Saniie, J. (2017). Real-Time Face Detection and Recognition in Complex Background. Journal of Signal and
Information Processing, 8(2), 99-112.

[4] Ranjan , R., Bansal, A., Zheng, J., Xu, H., Gleason, J., Lu, B., et al. (2015). A Fast and Accurate System for Face Detection,. JOURNAL OF
LATEX CLASS, 14(8).

[5] Mantoro, T., Ayu, M. A., & Suhendi. (2018). Multi-Faces Recognition Process Using Haar Cascades and Eigenface Methods. 2018 6th
International Conference on Multimedia Computing and Systems (ICMCS).
References Conti....
[6] Rachmawanto, E. H., Anarqi, R. G., Setiadi, D. I., & Sari, A. (2018). Handwriting Recognition Using Eccentricity and Metric
Feature Extraction Based on K-Nearest Neighbors. 2018 International Seminar on Application for Technology of Information
and Communication (iSemantic).
[7] Fransiska, R. (2016). Voice Recognition Using k Nearest Neighbor and Double Distance Method. 2016 International
Conference on Industrial Engineering, Management Science and Application (ICIMSA).
[8] Asana, I., Widyantara, I., Wirastuti, N., & Adnyana, I. (2017). Metode Contrast Stretching untuk Perbaikan Kualitas Citra
pada Proses Segmentasi Video. OJS Unud, 16(2).
[9] Natesan, M., & Bhuvaneshwaran, K. (2014). Image Enhancement Using Multilevel Contrast Stretching and Noise
Smoothening Technique for CT Images. International Journal of Scientific and Engineering Research, 5(5), 713-718.
[10] Mahmud , F., Khatun, T., Zuhori, S., Afroge, S., Aktar, M., & Pal, B. (2015). Face recognition using Principle Component
Analysis and Linear Discriminant Analysis. International Conference on Electrical Engineering and Information
Communication Technology (ICEEICT).
THANKYOU