Image Processing for Improvement of Facial Keypoints Detector

Q2 Social Sciences

Webology Pub Date : 2022-01-20 DOI:10.14704/web/v19i1/web19048

A. Kusnadi, Leondy ., Lianna Nathania, I. Z. Pane, Marlinda Vasty Overbeek, Syarief Gerald Prasetya

{"title":"Image Processing for Improvement of Facial Keypoints Detector","authors":"A. Kusnadi, Leondy ., Lianna Nathania, I. Z. Pane, Marlinda Vasty Overbeek, Syarief Gerald Prasetya","doi":"10.14704/web/v19i1/web19048","DOIUrl":null,"url":null,"abstract":"This paper discusses the improvement of facial detection algorithms using the DCT algorithm and image processing. Face key point is very needed in the face recognition system. Some important factors that have effects to detect its result are noise and illuminations. These two factors can be overcome by eliminating some DCT coefficients, both high and low. However, after handling the problem, most likely the image quality will become decrease, which will adversely influence the performance of the feature detector algorithm. Therefore, it is very important to test the performance of the feature detector algorithm on images that are implemented noise and illumination handling and how to improve the quality again. This research implemented Discrete Cosine Transform (DCT), by eliminating the high and low coefficient because there is noise and illumination. However, it is not known at what coefficient level is the most effective, so testing in this study was carried out. Four deblurring algorithms are tested in this research, Blind Deconvolution, Wiener Filter Deconvolution, Lucy-Richardson Deconvolution, and Regularization Deconvolution. And tested the CLAHE algorithm to overcome the effect of removing low coefficient DCT. The best coefficient value to be removed at the DCT frequency is 0.75 with the best SURF algorithm, without the use of other algorithms. Also, the highest F-score is produced by the SURF detector at removing DCT low frequency in combination with the CLAHE algorithm. With the most ideal coefficient of 0.25.","PeriodicalId":35441,"journal":{"name":"Webology","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2022-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Webology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.14704/web/v19i1/web19048","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Social Sciences","Score":null,"Total":0}

引用次数: 0

Abstract

This paper discusses the improvement of facial detection algorithms using the DCT algorithm and image processing. Face key point is very needed in the face recognition system. Some important factors that have effects to detect its result are noise and illuminations. These two factors can be overcome by eliminating some DCT coefficients, both high and low. However, after handling the problem, most likely the image quality will become decrease, which will adversely influence the performance of the feature detector algorithm. Therefore, it is very important to test the performance of the feature detector algorithm on images that are implemented noise and illumination handling and how to improve the quality again. This research implemented Discrete Cosine Transform (DCT), by eliminating the high and low coefficient because there is noise and illumination. However, it is not known at what coefficient level is the most effective, so testing in this study was carried out. Four deblurring algorithms are tested in this research, Blind Deconvolution, Wiener Filter Deconvolution, Lucy-Richardson Deconvolution, and Regularization Deconvolution. And tested the CLAHE algorithm to overcome the effect of removing low coefficient DCT. The best coefficient value to be removed at the DCT frequency is 0.75 with the best SURF algorithm, without the use of other algorithms. Also, the highest F-score is produced by the SURF detector at removing DCT low frequency in combination with the CLAHE algorithm. With the most ideal coefficient of 0.25.

查看原文本刊更多论文

改进面部关键点检测器的图像处理

本文讨论了利用DCT算法和图像处理对人脸检测算法的改进。人脸识别系统中非常需要人脸关键点。影响检测结果的一些重要因素是噪声和照明。这两个因素可以通过消除一些DCT系数来克服，包括高系数和低系数。然而，在处理该问题之后，图像质量很可能会降低，这将对特征检测器算法的性能产生不利影响。因此，测试特征检测器算法在实现噪声和光照处理的图像上的性能以及如何再次提高质量是非常重要的。本研究实现了离散余弦变换（DCT），通过消除高系数和低系数，因为有噪声和光照。然而，目前还不知道在什么系数水平下最有效，因此在本研究中进行了测试。本研究测试了四种去模糊算法，即盲反卷积、维纳滤波器反卷积、Lucy-Richardson反卷积和正则化反卷积。并对CLAHE算法进行了测试，克服了去除低系数DCT的效果。在不使用其他算法的情况下，使用最佳SURF算法，在DCT频率下要去除的最佳系数值是0.75。此外，SURF检测器结合CLAHE算法在去除DCT低频时产生最高的F分数。最理想的系数为0.25。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Webology Social Sciences-Library and Information Sciences

自引率

0.00%

发文量

374

审稿时长

10 weeks

期刊介绍： Webology is an international peer-reviewed journal in English devoted to the field of the World Wide Web and serves as a forum for discussion and experimentation. It serves as a forum for new research in information dissemination and communication processes in general, and in the context of the World Wide Web in particular. Concerns include the production, gathering, recording, processing, storing, representing, sharing, transmitting, retrieving, distribution, and dissemination of information, as well as its social and cultural impacts. There is a strong emphasis on the Web and new information technologies. Special topic issues are also often seen.