Implementation of K-Nearest Neightbors Face Recognition on Low-power Processor

Eko Setiawan, Adharul Muttaqin

Abstract


Face recognition is one of early detection in security system. Automation encourages implementation of face recognition in robot with low-power processor. Most of face recognition research focused on recognition accuration only and performed on high-speed computer. Face recognition that is implemented on low-cost processor, such as ARM processor, needs proper algorithm. Our research proposed K-Nearest Neighbor (KNN) algorithm to recognize face by ARM processor, which was common processor in robot system. This research sought best k-value to create proper face recognition with low-power processor. The proposed algorithm was tested on AT&T face dataset from Computer Laboratory, Cambridge University. The 15 images were set as testing image and 315 images were used as reference data set. OpenCV was choosen as main core image processing library, due to its high-speed. Proposed algorithm was implemented on ARM11 700MHz. Experiment result showed that KNN face recognition detected 93.3% face with k=1. Another proposed Histogram KNN face recognition gave 100% true detection with k=3. Overall experiment showed that proposed algorithm detected face on 2.657 s by ARM processor.

Full Text:

PDF

References


Rabia J, Hamid R A. A Survey of Face Recognition Techniques. Journal of Information Processing. 2009. Vol 5 No 2 June.

Yong X, Xiaozhao F, Xuelong L, Jian Y, Jane Y, Hong L, Shaohua T. Data Uncertainty in Face Recognition. IEEE Transaction on Cybernetics. 2014.

Hala M E. 2012. Feature Extraction using PCA and Kernel-PCA for Face Recognition. The 8th International Conference on INFOrmatics and System. Mei 2012.

Zhang H, Chen G. The Research of Face Recognition Based on PCA and K-Nearest Neighbor. 2012.

Ganesh A J. The Novel Nearest Neighbor Algorithm. International Conference on Computer Communication and Informatics - India. 2013.

Peter N B, Joao P H, David J K. Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection. 2014.

Cambridge University, ATT Face Dataset, accessed on 17 September 17th 2014, http://www.cl.cam.ac.uk/research/dtg/attarchive/facesataglance.html,

OpenCV Dev Team. 2014. The OpenCV Reference Manual Release 2.4.9.0. accessed on September 10th 2014. http://docs.opencv.org




DOI: http://dx.doi.org/10.12928/telkomnika.v13i3.713

Article Metrics

Abstract view : 254 times
PDF - 215 times

Refbacks



Copyright (c) 2015 Universitas Ahmad Dahlan

TELKOMNIKA Telecommunication, Computing, Electronics and Control
ISSN: 1693-6930, e-ISSN: 2302-9293
Universitas Ahmad Dahlan, 4th Campus, 9th Floor, LPPI Room
Jl. Ringroad Selatan, Kragilan, Tamanan, Banguntapan, Bantul, Yogyakarta, Indonesia 55191
Phone: +62 (274) 563515, 511830, 379418, 371120 ext. 4902, Fax: +62 274 564604

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

View TELKOMNIKA Stats