Comparison of Different Classifiers for Drowsiness Detection Based on Facial Expression Recognition
Abstract
Traffic accidents often occur due to the negligence of sleepy drivers. This study proposed a method to classify the normal expression and drowsiness expression as the first step in a driving safety system. In this study, a driver's facial expression recognition system was designed using Principal Component Analysis (PCA) as a feature extraction method and classifier comparison using K-Nearest Neighbor (K-NN) and Linear Discriminant Analysis (LDA) methods. PCA worked to reduce the data without eliminating important information in the image, and this process also caused system performance to be faster. The developed facial expression recognition systems can detect facial expressions and classify them into two types using data from the Yawning Detection Dataset (YawDD). They are normal expression and drowsiness expression using K-NN and LDA. The K-NN classification method has the advantage of being more effective and simpler computing with an accuracy rate of 97% from 200 test images using eigenface parameters on PCA and K value, equal to 1 using city block distance by 256 x 256 pixels. This paper proved that LDA has the same performance as the KNN classifier with an accuracy rate of 97 % using Bayes prior in size 128x82 pixels with the advantage that LDA is more compressible than KNN.
Keywords: Eigenface, Facial expression, PCA, K-NN, LDA, Drowsiness detection.
Full Text:
PDFReferences
LENI S., JACHRIZAL S., KUSUMA A., BULAN S., & RUDROKASWORO S. Analyzing driving environment factors in pedestrian crashes injury levels in Jakarta and the surrounding cities [J]. Journal of Applied Engineering Science, 2019, 17(4): 482–489, 2019. DOI: 10.5937/jaes17-22121.
SPASOJEVIĆ-BRKIĆ V., VELJKOVIĆ Z, ESSDAI A, & BRKIĆ A. Differences in anthropometric measurements between Libyan and Serbian passenger car drivers and crane operators [J]. Journal of Applied Engineering Science, 2019, 17(1): 1–7. DOI: 10.5937/jaes17-19969.
JAVID A. and AL-NEAMA Y. Identification of factors causing driver's distraction in Oman [J]. Journal of Applied Engineering Science, 2016, 16(2): 153–160. DOI: 10.5937/jaes16-16669.
KAMENCHUKOV A. Application of grapho-analytical method for assessing the change in the speed of movement of vehicles means after repair of highways [J]. Journal of Applied Engineering Science, 2019, 17(4): 473–481. DOI: 10.5937/jaes17-20088.
FARDANI E. Y., ARIFIANTO A., and RAMADHANI K. N. Pengenalan Ekspresi Wajah Menggunakan LGBP (Local Gabor Binary Pattern) dan SVM (Support Vector Machine) [C]. EProceedings of Engineering, 2018, 5(3): 1–8. https://libraryeproceeding.telkomuniversity.ac.id/index.php/engineering/article/view/7501
SUBASI A. and ISMAIL GURSOY M. EEG signal classification using PCA, ICA, LDA and support vector machines [J]. Expert Systems With Application, 2010, 37(12): 8659–8666, http://dx.doi.org/10.1016/j.eswa.2010.06.065
HONGZHE B. and GONGZHANG S. Recognition and Applications of Emotion Detection in Driving Fatigue [J]. Open Automation and Control Systems Journal, 2015, 7(1): 655–660. http://dx.doi.org/10.2174/1874444320150617E010.
ANITHA C., VENKATESHA M. K., and ADIGA B. S. A Two-Fold Expert System for Yawning Detection [J]. Procedia Computer Science, 2016, 92: 63–71. DOI: 10.1016/j.procs.2016.07.324.
ALIOUA N., AMINE A., and RZIZA M. Driver's Fatigue Detection Based on Yawning Extraction. International Journal of Vehicular Technology, 2014: 1–7. DOI: 10.1155/2014/678786.
FAN X., YIN B.-C., & SUN Y.-F. Yawning Detection for Monitoring Driver Fatigue [C]. IEEE International Conference on Machine Learning and Cybernetics, 2007, pp. 664 - 668. DOI: 10.1109/ICMLC.2007.4370228
HEMADRI V.B. and KULKARNI U.P. Detection of Drowsiness Using Fusion of Yawning and Eyelid Movements [J]. Advances in Computing, Communication, and Control, 2013, 361: 583–594. DOI: 10.1007/978-3-642-36321-4_55
CHANCHAL A. K. and ELECTRONICS H. Recognition of Emotions from Facial Expressions and its Application in Car Driving System [J]. International Journal of Advanced Research in Electronics and Communication Engineering 2016, 5(10): 2398–2406.
JABON M., BAILENSON J., PONTIKAKIS E., TAKAYAMA L., and NASS C. Facial-expression analysis for predicting unsafe driving behavior [C]. IEEE Pervasive Computing, 2011, 10(4): 84–95. http://dx.doi.org/10.1109/MPRV.2010.46
KATSIS C. D., RIGAS G., GOLETSIS Y., and FOTIADIS D. I. Emotion Recognition in Car Industry [J]. Emotion Recognition: A Pattern Analysis Approach, 2015, 515–544, http://dx.doi.org/10.1002/9781118910566.ch20
DHOKE P. and PARSAI M. P. A MATLAB based Face Recognition using PCA with Back Propagation Neural network [J]. International Journal of Innovative Research in Computer and Communication Engineering, 2014, 2(8): 5291–5297.
GAO H., YÜCE A. and THIRAN J.-P. Detecting Emotional Stress From Facial Expressions For Driving Safety [J] IEEE International Conference on Image Processing (ICIP), Paris, France, 2014, pp. 5961-5965. https://doi.org/10.1109/ICIP.2014.7026203.
PERSADA R.P., AULIA S., BURHANUDDIN D., and SUGONDO H. Automatic Face and VLP's Recognition for Smart Parking System [J]. TELKOMNIKA Telecommunication Computing Electronics and Control, 2019, 17(4): 1698–1705. https://doi.org/10.12928/telkomnika.v17i4.11746
AHMAD R.A.R, AHMAD M. I., ISA M.N. and ANWAR S. A. Face recognition using assemble of low frequency of DCT features [J]. Bulletin of Electrical Engineering and Informatics, 2019, 8(2): 541–550. https://doi.org/10.11591/eei.v8i2.1417.
GUAN F., SHI J., MA X., CUI W., and WU J. A method of false alarm recognition based on k-nearest neighbor [C]. Proceedings of the 4th International Conference on Dependable Systems and Their Application (DSA), 2017, 2018: 8–12. https://doi.org/10.1109/DSA.2017.11.
THARWAT A., GABER T., IBRAHIM A., and HASSANIEN A. E. Linear discriminant analysis: A detailed tutorial [J]. AI Communications, 2017, 30(2): 169–190, https://doi.org/10.3233/AIC-170729.
CHEN L.-F., LIAO H.-Y.M., KO M.-T., LIN J.-C., and YU G.-J. A new LDA-based face recognition system which can solve the small sample size problem [J]. Pattern Recognition, 2000, 33(10): 1713–1726.
MUSTAFA A.S. Face Recognition Systems Using Different Algorithms: A Literature Review [J]. Australian Journal of Basic and Applied Sciences 2017, 11(May): 9–17.
THARWAT A., MAHDI H., EL HENNAWY A., and HASSANIEN A.E. Face sketch synthesis and recognition based on linear regression transformation and multi-classifier technique [J]. Advances in Intelligent Systems and Computing, 2016, 407: 183–193. https://doi.org/10.1007/978-3-319-26690 9_17.
WANG X. and TANG X. Random sampling LDA for face recognition [C]. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004, 2. https://doi.org/10.1109/CVPR.2004.1315172.
KUSTIA N. Principal Component Analysis untuk Sistem Pengenalan Wajah dengan Menggunakan Metode Eigenface [J]. Satuan Tulisan Riset dan Inovasi Teknologi, 2016, 1(2): 193–202. http://dx.doi.org/10.30998/string.v1i2.1042.
EBRAHIMPOUR H. and KOUZANI A. Face recognition using bagging KNN [C]. Proceedings of the International Conference on Signal Processing and Communication Systems, 1996: 209–216.
GELER Z., KURBALIJA V., RADOVANOVIĆ M., and IVANOVIĆ M. Comparison of different weighting schemes for the kNN classifier on time-series data [J]. Knowledge and Information Systems, 2016, 48(2): 331–378. https://doi.org/10.1007/s10115-015-0881-0.
AULIA S., HADIYOSO S., and RAMADAN D.N. Analisis Perbandingan KNN dengan SVM untuk Klasifikasi Penyakit Diabetes Retinopati berdasarkan Citra Eksudat dan Mikroaneurisma [J]. Elkomika, 2018, 3(1): 75–90. https://doi.org/10.26760/elkomika.v3i1.75.
JOHNSON J. M. and YADAV A. Fault Detection and Classification Technique for HVDC Transmission Lines Using KNN [J]. Lecture Notes in Networks and Systems, 2018, 10, Springer: 245–253. https://doi.org/10.1007/978-981-10-3920-1_25.
ZHANG S., LI X., ZONG M., ZHU X., and CHENG D. Learning k for kNN Classification [J]. ACM Transactions on Intelligent Systems and Technology, 2017, 8(3): 1–19. https://doi.org/10.1145/2990508.
GOPI, E. S. Multi-Disciplinary Digital Signal Processing [M]. Cham: Springer International Publishing. 2018. http://link.springer.com/10.1007/978-3-319-57430-1.
GOPI E. S. Digital Speech Processing Using Matlab [M]. Cham: Springer International Publishing. 2014. http://link.springer.com/ 10.1007/978-81-322-1677-3.
Refbacks
- There are currently no refbacks.
