Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Journal of Information Technology (JIfoTech)
Fajar Sudana Putra
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Deteksi Otomatis Jerawat Wajah Menggunakan Metode Convolutional Neural Network (CNN) Fajar Sudana Putra; Kusrini; Mei P Kurniawan
Journal of Information Technology Vol 1 No 2 (2021): Journal of Information Technology
Publisher : Institut Shanti Bhuana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46229/jifotech.v1i2.308

Abstract

The development of cosmetology in the world lately is growing rapidly. These developments are balanced by the emergence of cosmetics and skin care from various brands, but not a few negative effects from use, one of which is acne. Acne is one of the problems on the skin, especially the face that arises physiologically because almost everyone has experienced it (Wasitaatmadja, 2010). Acne consists of various types, namely blackheads, whiteheads, papules and cysts (Bhate, K. & Williams, 2013). Not a few people who want to remove and be free from acne. The current technological developments in the field of image processing in recent years with the application of convolutional neural networks have shown significant performance by having a high level of accuracy, for example object detection which recently had image restoration. Therefore, technological developments to facilitate the treatment of acne are urgently needed by medical personnel, especially dermatologists. This research focuses on developing the accuracy of the method using the hough circle transform & Convolutional Neural Network (CNN) method. This study proves the increase in accuracy and accuracy of the object of acne detection using the Convolutional Neural Network (CNN) method. The results of the learning process obtained a CNN model with an accuracy of 99.8% to 100%, so it can be concluded that the CNN method designed in this study can classify images well.
Co-Authors Kusrini Mei P Kurniawan