Removing DCT High Frequency on Feature Detector Repeatability Quality

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

doi:10.1109/conmedia46929.2019.8981817

Cited by 2 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the high-frequency component was removed by conducting feature extraction [10,11,18,20] the image was transformed back to the spatial domain using the inverse DCT as shown in Equation 2:…”

Section: A Discrete Cosine Transform (Dct)mentioning

confidence: 99%

See 1 more Smart Citation

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

Kusnadi

Ngadiman

Pane

et al. 2020

EECSI

Self Cite

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

Section: A Discrete Cosine Transform (Dct)mentioning

confidence: 99%

“…Various studies have been conducted on the removal of noise by taking out the high-frequency band using the DCT method [10], [8], [11], [12], [13]. However, in these studies, eliminating the high frequency made the images blur because high frequency storages edges information [14].…”

Section: Introductionmentioning

confidence: 99%

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

Kusnadi

Ngadiman

Pane

et al. 2020

EECSI

Self Cite

View full text Add to dashboard Cite

show abstract

“…The research carried out by [10] utilized local features and LD-SIFT algorithm for feature selection, without considering illumination. 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.…”

Section: Introductionmentioning

confidence: 99%