Improved accuracy of recognizing of low-quality face images using two directional matrix in 2D-PCA algorithms and euclidean distance

Abstract

Face recognition is a technique that can be used to distinguish the characteristic facial patterns of a person. A very influencing factor in the facial recognition process is image quality, so it can affect the level of accuracy. Improving the accuracy of low-quality facial recognition can be done by processing the image for its feature extraction using Two Directional Matrix on 2D-PCA. From the extraction process, the Eigenfaces value is then generated to be classified. Image classification is done by using Euclidean Distance. Furthermore, the accuracy results between image recognition with or without Two Directional Matrix will be compared. The data used were the AT&T face of database and database of Essex. Of the 18 tests carried out on the Two Directional Matrix method, it was proven to improve facial recognition accuracy by as many as 12 trials. In 5 other experiments the accuracy decreased and 1 experiment was unable to increase or decrease facial recognition accuracy. The highest accuracy result in the experiment using AT&T was 98.25%, while in Essex it was 97.27%. Suggestions for further research by conducting experiments with more diverse dataset ratios in order to get better low-quality image accuracy results.

Laser-Induced Graphene Strain Sensor for Conformable Lip-Reading Recognition and Human–Machine Interaction

“…To compare the differences between X and Y individuals, we mainly use the distance measurement. The Euclidean distance is the most common distance measurement, which measures the absolute distance between two points in multidimensional space. , The Euclidean distance between two n -dimensional vectors a⃗( x 11 , x 12 , ···, x 1 n ) and b⃗( x 21 , x 22 , ···, x 2 n ) is d = ∑ k = 1 n false( x 1 k − x 2 k false) 2 The dynamic time warping (DTW) algorithm uses a time warping function satisfying certain conditions to describe the time correspondence between the test template and the reference template and solves the warping function corresponding to the minimum cumulative distance when the two templates match. When the dimension or the number of sequences is different and cannot correspond to each other one by one, we need to use the DTW algorithm to expand or reduce to the same number of sequences, and then calculate the distance, as shown in Figure S10. − By limiting the boundary conditions, continuity, and monotonicity, the path with the least cost of regularization can be obtained DTW ( Q , C ) = min ( ∑ k = 1 K w k ) / K Here, Q and C represent the time series of lengths n and m , respectively.…”

Utilizing principal component analysis in the identification of clinically relevant changes in patient HLA single antigen bead solid phase testing patterns

“…, as has previously been established and described for the analysis of principal component-derived values [12,13]. The distance ratio of samples was calculated as the Euclidean distance of the sample of interest divided by the average Euclidean distance of the other patient samples.…”

“…Principal component analysis was performed using GraphPad Prism (version 9.4.1) and R (version 4.1.1). Euclidean distance analysis based on principal component values was performed using the equation, , as has previously been established and described for the analysis of principal component-derived values [ 12 , 13 ]. The distance ratio of samples was calculated as the Euclidean distance of the sample of interest divided by the average Euclidean distance of the other patient samples.…”