Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen)
Himamunanto, AR.
Unknown Affiliation
Computer Science & IT Control & Systems Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Pengenalan Emosi pada Citra wajah menggunakan Metode YOLO Gallu, Apliana; Himamunanto, AR.; Budiati, Haeni
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 3 (2024): Edisi Juli
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i3.444

Abstract

Human emotions can be expressed through facial expressions, and automatic recognition has a wide range of applications, from human and computer interaction to behavior analysis. Researchers developed a YOLO-based model that was trained to recognize various basic emotions such as happy, sad, angry, and surprised. The dataset used includes various facial images with corresponding emotion labels. This research produced a web to detect human faces using the YOLO algorithm in realtime. A total of 400 photos were used in the analysis; these images were separated into 4 classes: happy, sad, angry, and surprised. Of the 400 images, 70% are training images, 20% are validation images, and 10% are test images. There were 200 epochs of training data, which resulted in a new model. The validation rate of the mAP is 90%, the final score of the model shows that the object identification accuracy of the YOLOv8 model on facial expressions is at the highest point. The experimental results show that the YOLO method is able to detect and classify emotions with a high degree of accuracy. These results demonstrate its advantages in speed and efficiency compared to other more conventional methods. This implementation opens up opportunities for further development in real-time applications that allow the YOLO method to be used in a variety of applications.
Pendeteksian Level Kualitas Modifikasi Citra Manusia Dalam Eksperimen Metode Error Level Analysis (ELA) Rantiasi, R; Himamunanto, AR.; Sumihar, Yo’el Pieter
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 3 (2024): Edisi Juli
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i3.446

Abstract

Research on image processing methods has become increasingly diverse in modifying images with more attractive visuals. The results of visual modification of this image are often used to convey certain information that will often be found in various media. The method used to identify images that have been modified is the Error Level Analysis (ELA) method, which detects the quality level of a visual image compared to other images. So the method approach proposed in this research involves computing the visual components of images with shape, color and texture features. The method used in shape computing is Prewitt edge detection, while for color features using HSV color transformation and Grayscalling. The method used to identify texture is using the Gray Level Co-occurrence Matrix (GLCM). The urgency of the method proposed in this research is very important to keep up with the various image processing methods that are developing increasingly rapidly. The results of the research are the Error Level Analysis (ELA) method with an analysis approach to shape components using the edge detection method, analysis of color components using the HSV and Grayscalling color transformation methods, and analysis of texture components using the Gray-Level Co-Occurrence Matrix (GLCM) method. ) can be used to detect image authenticity based on the statistical output of processing data. The Error Level Analysis (ELA) method with identification of shape, color and texture shows the differences between the original image and the manipulated image, so that the method used in the research can be a recommendation in completing the system. It is hoped that the approach method in this research will become an instrument for identifying images that have been modified to avoid misuse of visual image information.
Deteksi Lintasan Gerak Tangan Berbasis Pengolahan Citra Menggunakan Metode K-Means Isnawati, Nurvia; Himamunanto, AR.; Budiati, Heani
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.476

Abstract

Technological developments have demanded continuous research so that it becomes more advanced in bringing benefits to computer science in particular. As is known, hand gestures are often used to convey meaning and can be used to interact with computers. Research by building software using Matlab R2020a which processes video input using a method approach based on image processing. The aim of the method approach in this research is to compute the coordinates of hand gesture objects to obtain hand movement trajectories. The research results of the K-Means method which was implemented to describe trajectory patterns can process the quality of segmented objects with exposure to dim light. The quality of segmentation that obtains the correct area of the hand gesture object influences the K-Means method in presenting trajectories in describing hand movement action patterns. The K-Means method can describe the trajectory of hand movements on the quality of segmented objects with dim light exposure. The longer the duration, the longer the processing will take, with the reality found that object detection processing based on image processing still takes longer than video viewing. With the hope that precise trajectories with hand movements can be understood as patterns in conveying meaning.
Co-Authors Budiati, Heani Gallu, Apliana Haeni Budiati Isnawati, Nurvia Rantiasi, R Sumihar, Yo’el Pieter