Facial expression using Histogram of Oriented Gradients and Ensemble Classifier
DOI:
https://doi.org/10.25130/tjps.v27i2.67Abstract
In this research, two methods were proposed to design a new system to recognize facial expressions. The first method relies on extracting features from the face area, and the second method relies on the process of extracting features on the parts of the face (eyes, nose, and mouth) where the histogram of oriented gradients (HOG) algorithm was used in the feature extraction process in addition to the principal component analysis algorithm to reduce feature dimensions in both methods. We have proposed a group classifier consisting of three basic classifiers: support vector machines, knn-algorithm closest to neighbors, and Naive Bayes in the classification stage. Our proposed algorithm was tested on japanese female facial expression (JAFFE) Dataset and Cohn-Kanade (CK) dataset. It was found that higher overall accuracy is achieved for F1-Score when using the second method of 93.82 % and 94.12% for CK and JAFFA, respectively.
Downloads
Published
How to Cite
License
Copyright (c) 2022 Tikrit Journal of Pure Science
This work is licensed under a Creative Commons Attribution 4.0 International License.
Tikrit Journal of Pure Science is licensed under the Creative Commons Attribution 4.0 International License, which allows users to copy, create extracts, abstracts, and new works from the article, alter and revise the article, and make commercial use of the article (including reuse and/or resale of the article by commercial entities), provided the user gives appropriate credit (with a link to the formal publication through the relevant DOI), provides a link to the license, indicates if changes were made, and the licensor is not represented as endorsing the use made of the work. The authors hold the copyright for their published work on the Tikrit J. Pure Sci. website, while Tikrit J. Pure Sci. is responsible for appreciate citation of their work, which is released under CC-BY-4.0, enabling the unrestricted use, distribution, and reproduction of an article in any medium, provided that the original work is properly cited.