Authentication System Using 3D Face With Algorithm DLT and Neural Network

Alexander, Leonardus; Kusnadi, Adhi; Wella, Wella; Winantyo, Rangga; Pane, Ivransa Zuhdi

doi:10.1109/scis-isis.2018.00039

“…The study conducted by [11] only increased the performance of the SIFT algorithm for illumination generally, [12] studied the repeatability of keypoints using the epipolar geometry method on five feature detectors algorithm and the result was affected by noise and illumination. In the research carried out by [13], the accuracy rate of 3D face recognition was affected by the success rate of its reconstruction model, where it needed the accuracy of detecting facial keypoints. [14] researched the effect of illumination on the performance of face recognition and the result was using Histogram Equalization can yield a better result without no preprocessing and [15] studied that Discrete Cosine Transform (DCT) can be used to remove the illumination variation on the low-frequency component.…”

Section: Introductionmentioning

confidence: 99%

“…From the research, the applied methods on the two data sets show an improvement in the detection of facial keypoints from testing two different datasets. Furthermore, it is important to detect keypoints in 3D face reconstruction [23]. This is because the higher the F-score achieved from detecting the facial keypoints, it will yield a better result.…”

Section: Introductionmentioning

confidence: 99%

The Effect of Using Histogram Equalization and Discrete Cosine Transform on Facial Keypoint Detection

Kusnadi

¹

,

Darmawan

²

,

Pane

³

et al. 2020

EECSI

Self Cite

0

View full text Add to dashboard Cite

This study aims to figure out the effect of using Histogram Equalization and Discrete Cosine Transform (DCT) in detecting facial keypoints, which can be applied for 3D facial reconstruction in face recognition. Four combinations of methods comprising of Histogram Equalization, removing lowfrequency coefficients using Discrete Cosine Transform (DCT) and using five feature detectors, namely: SURF, Minimum Eigenvalue, Harris-Stephens, FAST, and BRISK were used for test. Data that were used for test were obtained from Head Pose Image and ORL Databases. The result from the test were evaluated using F-score. The highest F-score for Head Pose Image Dataset is 0.140 and achieved through the combination of DCT & Histogram Equalization with feature detector SURF. The highest F-score for ORL Database is 0.33 and achieved through the combination of DCT & Histogram Equalization with feature detector BRISK.

show abstract

“…The feature detectors used are Harris-Stephens, Speeded Up Robust Features (SURF), Features from Accelerated Segment Test (FAST), Binary Robust Invariant Scalable Keypoints (BRISK), and Minimum Eigenvalue. Detecting facial keypoints is meant to reconstructing 3D models of face [16].…”

Section: Introductionmentioning

confidence: 99%

Image Restoration Effect on DCT High Frequency Removal and Wiener Algorithm for Detecting Facial Key Points

Kusnadi

¹

,

Ngadiman

²

,

Pane

³

et al. 2020

EECSI

Self Cite

2

0

View full text Add to dashboard Cite

This study aims to figure out the effect of using Histogram Equalization and Discrete Cosine Transform (DCT) in detecting facial keypoints, which can be applied for 3D facial reconstruction in face recognition. Four combinations of methods comprising of Histogram Equalization, removing lowfrequency coefficients using Discrete Cosine Transform (DCT) and using five feature detectors, namely: SURF, Minimum Eigenvalue, Harris-Stephens, FAST, and BRISK were used for test. Data that were used for test were obtained from Head Pose Image and ORL Databases. The result from the test were evaluated using F-score. The highest F-score for Head Pose Image Dataset is 0.140 and achieved through the combination of DCT & Histogram Equalization with feature detector SURF. The highest F-score for ORL Database is 0.33 and achieved through the combination of DCT & Histogram Equalization with feature detector BRISK.

show abstract

PCA effect on the 3D face recognition system speed

Kusnadi

¹

,

Wella

²

,

Winantyo

³

et al. 2021

IOP Conf. Ser.: Mater. Sci. Eng.

View full text Add to dashboard Cite

In this paper, a system of three-dimensional (3D) face recognition is not done through 3D face reconstruction method but directly uses the data retrieved from Kinect Xbox camera system. From a previous study, there exists a possibility to increase the speed and accuracy of the system. In order to accelerate the recognition speed, a single step in the said study is eliminated, which is the reconstruction of 3D face data. The algorithms used in this research are Backpropagation Neural Network and PCA. Testing is done in two ways. The first test uses a combination of Backpropagation and PCA, while the second test uses Backpropagation only. PCA has the function of simplifying the amount of data, thereby reducing the amount of computing that can increase speed system. The results show that the system that uses a combination of Backpropagation and PCA achieved an increase in speed up to 34.2 times, but a reduced accuracy of 8.5%.

show abstract

Authentication System Using 3D Face With Algorithm DLT and Neural Network

Cited by 3 publications

References 6 publications

The Effect of Using Histogram Equalization and Discrete Cosine Transform on Facial Keypoint Detection

The Effect of Using Histogram Equalization and Discrete Cosine Transform on Facial Keypoint Detection

Image Restoration Effect on DCT High Frequency Removal and Wiener Algorithm for Detecting Facial Key Points

PCA effect on the 3D face recognition system speed

Contact Info

Product

Resources

About