Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen)
Gede Putra Kusuma
Bina Nusantara University, Jakarta, Indonesia
Computer Science & IT Control & Systems Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Image Enhancement using Convolutional Neural Network for Low Light Face Detection Antonius Filian Beato Istianto; Gede Putra Kusuma
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 1 (2024): Edisi Januari
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i1.318

Abstract

This research aims to combine the study of face detection with improvement of image quality in low-light conditions. In this research, we introduce a method that combines Convolutional Neural Networks for image processing to enhance face detection performance in low-light conditions. The proposed method involves pre-processing the images using three image enhancement methods: Deep Lightening Network, Deep Retinex Net, and Signal-to-Noise Ratio Aware. Each of these methods is combined with the face detection method, RetinaFace. The experiment is evaluated using the DARKFACE Dataset, and the performance of each combination is assessed using Average Precision (AP). The combination that yields the best AP value will be determined as the best approach for low-light face detection. The best combination, which utilizes Signal to Noise Ratio Aware for image enhancement and RetinaFace for face detection, achieves an AP score of 52.92%. This result surpasses the face detection performance using the original images from the DARKFACE Dataset, which scored 7.12% in AP. Thus, this experiment demonstrates that image enhancement using Convolutional Neural Networks can significantly improve face detection in low-light conditions
Improving Image Quality to Assist Brand Logo Detection in Blurred Images Jibril Hartri Putra; Gede Putra Kusuma
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 1 (2024): Edisi Januari
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i1.346

Abstract

Logo detection is a challenging task in computer vision, especially when the logos are blurred or distorted in the images. Image deblurring is a technique that can improve the quality and clarity of the logos, which can enhance the logo detection performance. In this paper, we propose a novel method for logo detection that combines image deblurring and robust logo detection techniques. We create synthetic blurred images from the Flickr Logos 27 Dataset using Motion Blur data to improve deblurring methods. Then, we use three different image deblurring methods, namely Restormer, DeblurGAN-v2, and DeepRFT, to preprocess the images and remove the blur effects to improve the sharpness of images. We then use two different logo detection methods, namely Yolov7 and Robust Logo Detection, to detect and recognise the logos in the images. We evaluate our method on the Flickr Logos 27 dataset, which is a well-known and widely used dataset for logo detection. It contains 810 annotated images of 27 logo classes, as well as 4207 distractor images and 270 query images. We show that combining the method of Robust Logo Detection with Restormer achieves the highest mean average precision (mAP) at 0,754 among all the methods, and significantly improves the logo detection accuracy on blurred images. We conclude that image deblurring can effectively enhance logo detection performance and that our method is the best combination of image deblurring and logo detection techniques.
Co-Authors Antonius Filian Beato Istianto Jibril Hartri Putra