EKSTRAKSI CIRI CITRA WAJAH MENGGUNAKAN GEOMETRIC MOMENT INVARIANTS UNTUK KLASIFIKASI EKSPRESI WAJAH PADA CITRA MULTIPLE FACE
Total View This Week0
Total View This Week0
Institusion
Universitas Sriwijaya
Author
AYU LESTARI (STUDENT ID : 09021181520021)
Muhammad Fachrurrozi (LECTURER ID : 0222058001)
Osvari Arsalan (LECTURER ID : 0028068806)
Muhammad Fachrurrozi (LECTURER ID : 0222058001)
Osvari Arsalan (LECTURER ID : 0028068806)
Subject
R858-859.7 Computer applications to medicine. Medical informatics
Datestamp
2019-10-02 07:52:49
Abstract :
Research on human facial expression recognition has become a growing field. One important step in the recognition of facial expressions is feature extraction. This research uses Geometric Moment Invariants (GMI) as a feature extraction method. Research on facial expression recognition using either the GMI method or another method use single face image as the dataset. Therefore, in this study uses GMI feature extraction to classify facial expressions on multiple face images. Feature extraction from the results of self-codes will be compared with the results of GMI with OpenCV. Face detection process uses Viola-Jones method on OpenCV and classification process uses Multi Class SVM method. The results are features for each expression and a small average accuracy of 5 times except sad expressions. Sad expression with its self-code features get accuracy 77,26% and from features of OpenCV get accuracy of 78,10%. Therefore, the classification is also done with the k-fold cross validation technique with another classification method. The average accuracy results are still small. It is tested from k value 2 to10, and produce Multi Class SVM 10,2%, Decision Tree Classifier 14,73%, Random Forest Classifier 14,78%, Gaussian Naive Bayes 14,73%, Nearest Centroid 14,66%, MLP Classifier 11,09%, and Stochastic Gradient Descent Classifier 14,19%. The highest accuracy result is Random Forest Classifier method 14,78%. In Random Forest method, the best k value obtained is 4 with an average accuracy 16,18%.
Research on human facial expression recognition has become a growing field. One important step in the recognition of facial expressions is feature extraction. This research uses Geometric Moment Invariants (GMI) as a feature extraction method. Research on facial expression recognition using either the GMI method or another method use single face image as the dataset. Therefore, in this study uses GMI feature extraction to classify facial expressions on multiple face images. Feature extraction from the results of self-codes will be compared with the results of GMI with OpenCV. Face detection process uses Viola-Jones method on OpenCV and classification process uses Multi Class SVM method. The results are features for each expression and a small average accuracy of 5 times except sad expressions. Sad expression with its self-code features get accuracy 77,26% and from features of OpenCV get accuracy of 78,10%. Therefore, the classification is also done with the k-fold cross validation technique with another classification method. The average accuracy results are still small. It is tested from k value 2 to10, and produce Multi Class SVM 10,2%, Decision Tree Classifier 14,73%, Random Forest Classifier 14,78%, Gaussian Naive Bayes 14,73%, Nearest Centroid 14,66%, MLP Classifier 11,09%, and Stochastic Gradient Descent Classifier 14,19%. The highest accuracy result is Random Forest Classifier method 14,78%. In Random Forest method, the best k value obtained is 4 with an average accuracy 16,18%.
File :
RAMA_55201_09021181520021_0222058001_0028068806_01_front_ref.pdf
RAMA_55201_09021181520021_0222058001_0028068806_02.pdf
RAMA_55201_09021181520021_0222058001_0028068806_03.pdf
RAMA_55201_09021181520021_0222058001_0028068806_04.pdf
RAMA_55201_09021181520021_0222058001_0028068806_05.pdf
RAMA_55201_09021181520021_0222058001_0028068806_06.pdf
RAMA_55201_09021181520021_0222058001_0028068806_07_ref.pdf
RAMA_55201_09021181520021_0222058001_0028068806_08_lamp.pdf
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
