scholarly journals Face Recognition based Feature Extraction using Principal Component Analysis (PCA)

2020 ◽  
Vol 3 (2) ◽  
pp. 182-191
Author(s):  
Muhammad Zulfahmi Nasution
Keyword(s):  
Principal Component Analysis ◽  
Feature Extraction ◽  
Face Recognition ◽  
Digital Image ◽  
Principal Component ◽  
Image Database ◽  
Component Analysis ◽  
Facial Features ◽  
Semantic Features ◽  
Pca Method

The human face is an entity that has semantic features. Face detection is the first step before face recognition. Face recognition technique is an identification process based on facial features. One feature extraction approach for facial recognition techniques is the Principal Component Analysis (PCA) method. The PCA method is used to simplify facial features and characteristics in order to obtain proportions that are able to represent the characteristics of the original face. The purpose of this research is to construct facial patterns stored in a digital image database. The process of pattern construction and face recognition starts from objects in the form of face images, side detection, pattern construction until it can determine the similarity of face patterns to proceed as face recognition. In this research, a program has been designed to test some samples of face data stored in a digital image database so that it can provide a similarity in the face patterns being observed and its introduction using PCA

scholarly journals Patch-Based Principal Component Analysis for Face Recognition

2017 ◽  
Vol 2017 ◽  
pp. 1-9 ◽  
Author(s):  
Tai-Xiang Jiang ◽  
Ting-Zhu Huang ◽  
Xi-Le Zhao ◽  
Tian-Hui Ma
Keyword(s):  
Principal Component Analysis ◽  
Face Recognition ◽  
Nearest Neighbor ◽  
Spatial Information ◽  
Principal Component ◽  
Component Analysis ◽  
Two Dimensional ◽  
Face Images ◽  
Pca Method ◽  
Local Spatial Information

We have proposed a patch-based principal component analysis (PCA) method to deal with face recognition. Many PCA-based methods for face recognition utilize the correlation between pixels, columns, or rows. But the local spatial information is not utilized or not fully utilized in these methods. We believe that patches are more meaningful basic units for face recognition than pixels, columns, or rows, since faces are discerned by patches containing eyes and noses. To calculate the correlation between patches, face images are divided into patches and then these patches are converted to column vectors which would be combined into a new “image matrix.” By replacing the images with the new “image matrix” in the two-dimensional PCA framework, we directly calculate the correlation of the divided patches by computing the total scatter. By optimizing the total scatter of the projected samples, we obtain the projection matrix for feature extraction. Finally, we use the nearest neighbor classifier. Extensive experiments on the ORL and FERET face database are reported to illustrate the performance of the patch-based PCA. Our method promotes the accuracy compared to one-dimensional PCA, two-dimensional PCA, and two-directional two-dimensional PCA.

Matrix Based Feature Measurement and Extraction for Face Recognition

2015 ◽  
Vol 738-739 ◽  
pp. 643-647
Author(s):  
Qi Zhu ◽  
Jin Rong Cui ◽  
Zi Zhu Fan
Keyword(s):  
Principal Component Analysis ◽  
Feature Extraction ◽  
Face Recognition ◽  
Measurement Method ◽  
Principal Component ◽  
Component Analysis ◽  
High Accuracy ◽  
Face Image ◽  
Two Dimensional ◽  
The Matrix

In this paper, a matrix based feature extraction and measurement method, i.e.: multi-column principle component analysis (MCPCA) is used to directly and effectively extract features from the matrix. We analyze the advantages of MCPCA over the conventional principal component analysis (PCA) and two-dimensional PCA (2DPCA), and we have successfully applied it into face image recognition. Extensive face recognition experiments illustrate that the proposed method obtains high accuracy, and it is more robust than previous conventional face recognition methods.

scholarly journals Ekstraksi Ciri Orde Pertama dan Metode Principal Component Analysis untuk Mengidentifikasi Jenis Telur Ayam Kampung dan Ayam Arab

2019 ◽  
Vol 9 (2) ◽  
pp. 133
Author(s):  
Oky Dwi Nurhayati ◽  
Dania Eridani ◽  
Ajik Ulinuha
Keyword(s):  
Principal Component Analysis ◽  
Feature Extraction ◽  
Color Space ◽  
Principal Component ◽  
Component Analysis ◽  
Domestic Chicken ◽  
Image Size ◽  
First Order ◽  
Pca Method ◽  
Chicken Eggs

Chicken eggs become one of the animal proteins commonly used by people, especially in Indonesia. Eggs have high economic value and have diverse benefits and a high nutritional content. Visually to distinguish between domestic chicken eggs and arabic chicken eggs has many difficulties because physically the shape and color of eggs have similarities. This research was conducted to develop applications that were able to identify the types of domestic chicken eggs and Arab chicken eggs using the Principal Componenet Analysis (PCA) method and first order feature extraction. The application applies digital image processing stages, namely resizing image size, RGB color space conversion to HSV, contrast enhancement, image segmentation using the thresholding method, opening and region filling morphology operations, first order feature extraction and classification using the PCA method. The results of identification of types of native domestic chicken eggs and Arabic chicken eggs using the Principal Component Analysis method showed the results of 95% system accuracy percentage, consisting of 90% accuracy of success in the type of domestic chicken eggs and 100% accuracy of success in the type of Arabic chicken eggs.

scholarly journals Diagnosis of Esophagitis Based on Face Recognition Techniques

2010 ◽  
Vol 4 (1) ◽  
pp. 58-62
Author(s):  
Santosh S Saraf ◽  
Gururaj R Udupi ◽  
Santosh D Hajare
Keyword(s):  
Principal Component Analysis ◽  
Face Recognition ◽  
Principal Component ◽  
Component Analysis ◽  
Analysis Techniques ◽  
The Face ◽  
Pca Method ◽  
Recognition Efficiency ◽  
Motivating Factor

Face recognition technology has evolved over years with the Principal Component Analysis (PCA) method being the benchmark for recognition efficiency. The face recognition techniques take care of variation of illumination, pose and other features of the face in the image. We envisage an application of these face recognition techniques for classification of medical images. The motivating factor being, given a condition of an organ it is represented by some typical features. In this paper we report the use of the face recognition techniques to classify the type of Esophagitis, a condition of inflammation of the esophagus. The image of the esophagus is captured in the process of endoscopy. We test PCA, Fisher Face method and Independent Component Analysis techniques to classify the images of the esophagus. Esophagitis is classified into four categories. The results of classification for each method are reported and the results are compared.

scholarly journals Comparative Analysis of Illumination Normalizations on Principal Component Analysis Based Feature Extraction for Face Recognition

2019 ◽  
Vol 4 (1) ◽  
Author(s):  
Oluwakemi C Abikoye ◽  
Iyabo F Shoyemi ◽  
Taye O Aro
Keyword(s):  
Principal Component Analysis ◽  
Feature Extraction ◽  
Face Recognition ◽  
Discrete Cosine Transform ◽  
Principal Component ◽  
Histogram Equalization ◽  
Component Analysis ◽  
Recognition System ◽  
Adaptive Histogram Equalization ◽  
Face Images

Principle Component Analysis (PCA) is an appearance-based technique for extraction of feature extraction that is commonly used in computer vision and image processing. This technique suffers from illumination variations, thus knowing which illumination control method to be used in PCA-based face recognition system is very important. This paper applies three selected normalization techniques; Discrete Cosine Transform (DCT), Adaptive Histogram Equalization (AHE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) to normalize face images. PCA was further used to extract features from the normalized face images. Euclidean distance was used to classify extracted features. The best recognition accuracy of 91.84% was obtained in DCT for ORL Database, while the best accuracy of 76% was achieved in DCT for FERET Database. The highest FAR of 0.9 was achieved in DCT for ORL Database, while the highest FAR of 0.5 was obtained in DCT and AHE for FERET Database. The highest FRR of 0.2821 was achieved in CLAHE for ORL Database, while 0.3000 was obtained in AHE for FERET Database. It was concluded that illumination control approaches have predominant effect on PCA–based facial recognition system. Keywords— Adaptive Histogram Equalization, Contrast Adaptive Histogram Equalization, Discrete Cosine Transform Illumination Normalization, Principal Component Analysis

Sign in / Sign up

Export Citation Format

Share Document