Article Per Year (5 Year)
p-Index From 2019 - 2024
0.562
P-Index
This Author published in this journals
All Journal Scientific Journal of Informatics
Doheir, Mohamed
Unknown Affiliation
Computer Science & IT

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

Found 3 Documents
Search

 1 
A Comparison of Non Blind Image Watermarking Using Transformation Domain Kartikadarma, Etika; Udayanti, Erika Devi; Sari, Christy Atika; Doheir, Mohamed
Scientific Journal of Informatics Vol 8, No 1 (2021): May 2021
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

In digital image processing, there is an algorithm that is most often used because it has advantages in imperceptibility and robustness. The DCT and HWT algorithms are usually used together to get better results. However in this study we wanted to know which of the algorithms had the better results for image processing by comparing these two algorithms for blind watermarking as the prevention of image plagiarism. The results of this study indicate that HWT has better results for image processing, especially blind watermarking because the results with MSE, PSNR, and NC show that HWT has advantages in every aspect. Using 512x512 pixels grayscale image as cover image, the MSE result from HWT is 0.0004156 with PSNR 81.9440 better than MSE from DCT 0.003 with PSNR 73.2949. On the other hand, robustness aspect has been tested using NC. DCT has good NC than HWT only in JPEG compression attack with value is 1, while another attack has better NC in HWT that yield close to 1.
A Comparison of Non Blind Image Watermarking Using Transformation Domain Kartikadarma, Etika; Udayanti, Erika Devi; Sari, Christy Atika; Doheir, Mohamed
Scientific Journal of Informatics Vol 8, No 1 (2021): May 2021
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v8i1.28334

Abstract

Purpose: This study aims to know which of the algorithms had the better results for image processing by comparing these two algorithms for blind watermarking as the prevention of image plagiarism. Methods: The DCT and HWT algorithms used to get better results. Result: The results of this study indicate that HWT has better results for image processing, especially blind watermarking because the results with MSE, PSNR, and NC show that HWT has advantages in every aspect.  using 512x512 pixels grayscale image as cover image, the MSE result from HWT is 0.0004156 with PSNR 81.9440 better than MSE from DCT 0.003 with PSNR 73.2949. Novelty: Robustness aspect has been tested using NC. DCT has good NC than HWT only in JPEG compression attack with value is 1, while another attack has better NC in HWT that yield close to 1.
Histogram of Gradient in K-Nearest Neighbor for Javanese Alphabet Classification Susanto, Ajib; Atika Sari, Christy; Mulyono, Ibnu Utomo Wahyu; Doheir, Mohamed
Scientific Journal of Informatics Vol 8, No 2 (2021): November 2021
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v8i2.30788

Abstract

Purpose: The Javanese script generally has a basic script or is commonly referred to as the “carakan” script. The script consists of 20 letters with different levels of difficulty. Some letters have similarities, so research is needed to make it easier to detect the image of Javanese characters. Methods: This study proposes recognizing Hiragana's writing characters using the K-Nearest Neighbor (K-NN) method. In the preprocessing stage, the segmentation process is carried out using the thresholding method to perform segmentation, followed by the Histogram of Gradient (HOG) feature extraction process and noise removal using median filtering. Histogram of Gradient (HoG) is one of the features used in computer vision and image processing in detecting an object in the form of a descriptor feature. There are 1000 data divided into 20 classes. Each class represents one letter of the basic Javanese script. Result: Based on data collection using the writings of 50 respondents where each respondent writes 20 basic Javanese characters, the highest accuracy was obtained at K = 1, namely 98.5%. Novelty: Using several preprocessing such as cropping, median filtering, otsu thresholding and HOG feature extraction before do classification, this experiment yields a good accuracy.
Co-Authors Ajib Susanto Christy Atika Sari Christy Atika Sari, Christy Erika Devi Udayanti Etika Kartikadarma Mulyono, Ibnu Utomo Wahyu