Claim Missing Document
Check
Articles

Found 4 Documents
Search

Surveying the Landscape: A Comprehensive Review of Object Detection Algorithms and Advancements Majeed Zangana, Hewa; Mustafa, Firas Mahmood
Jurnal Ilmiah Computer Science Vol. 3 No. 1 (2024): Volume 3 Number 1 July 2024
Publisher : PT. SNN MEDIA TECH PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58602/jics.v3i1.29

Abstract

This review paper gives a comprehensive investigation of the energetic scene of object detection, an essential field inside computer vision. Leveraging experiences from an assorted cluster of thinks about, the paper navigates through the chronicled advancement, techniques, challenges, later headways, applications, and future bearings in object detection. The comparative examination dives into the complexities of conventional strategies versus profound learning approaches, the trade-offs between exactness and speed, and the vigor of models against ill-disposed assaults. Highlighting key measurements such as cross-modal location, ceaseless learning, and moral contemplations, the paper divulges the multifaceted nature of object detection techniques. Applications of question discovery over spaces, counting independent vehicles, healthcare imaging, and keen cities, emphasize its transformative effect on different businesses. The talk amplifies to long term, envisioning challenges and openings in ranges such as ill-disposed vigor, cross-modal discovery, and moral contemplations. As a comprehensive direct for analysts, professionals, and devotees, this paper not as it were capturing the current state of object detection but too serves as a compass for exploring the strange domains that lie ahead. The survey typifies the essence of protest detection's advancement and its significant suggestions, empowering proceeded investigation and advancement within the domain of computer vision.
Advancements and Applications of Convolutional Neural Networks in Image Analysis: A Comprehensive Review Majeed Zangana, Hewa; Mohammed, Ayaz Khalid; Mustafa, Firas Mahmood
Jurnal Ilmiah Computer Science Vol. 3 No. 1 (2024): Volume 3 Number 1 July 2024
Publisher : PT. SNN MEDIA TECH PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58602/jics.v3i1.30

Abstract

Convolutional Neural Networks (CNNs) have revolutionized image analysis, extracting meaningful features from raw pixel data for accurate predictions. This paper reviews CNN fundamentals, architectures, training methods, applications, challenges, and future directions. It introduces CNN basics, including convolutional and pooling layers, and discusses diverse architectures like LeNet, AlexNet, ResNet, and DenseNet. Training strategies such as data preprocessing, initialization, optimization, and regularization are explored for improved performance and stability. CNN applications span healthcare, agriculture, ecology, remote sensing, and security, enabling tasks like object detection, classification, and segmentation. However, challenges like interpretability, data bias, and adversarial attacks persist. Future research aims to enhance CNN robustness, scalability, and ethical deployment. In conclusion, CNNs drive transformative advancements in image analysis, with ongoing efforts to address challenges and shape the future of AI-enabled technologies.
From Classical to Deep Learning: A Systematic Review of Image Denoising Techniques Majeed Zangana, Hewa; Mustafa, Firas Mahmood
Jurnal Ilmiah Computer Science Vol. 3 No. 1 (2024): Volume 3 Number 1 July 2024
Publisher : PT. SNN MEDIA TECH PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58602/jics.v3i1.36

Abstract

Image denoising is essential in image processing and computer vision, aimed at removing noise while preserving critical features. This review compares classical methods like Gaussian filtering and wavelet transforms with modern deep learning techniques such as convolutional neural networks (CNNs) and generative adversarial networks (GANs). We conducted a systematic literature review from [start year] to [end year], analyzing studies from IEEE Xplore, PubMed, and Google Scholar. Classical methods are effective for simple noise models but struggle with fine detail preservation. In contrast, deep learning excels in both noise reduction and detail retention, supported by metrics like PSNR and SSIM. Hybrid approaches combining classical and deep learning show promise for balancing performance and computational efficiency. Overall, deep learning leads in handling complex noise patterns and preserving high-detail images. Future research should focus on optimizing deep learning models, exploring unsupervised learning, and extending denoising applications to real-time and large-scale image processing.
Enhancing Image Quality With Deep Learning: Techniques And Applications Zangana, Hewa Majeed; Mustafa, Firas Mahmood; Mohammed, Ayaz Khalid; Omar, Naaman
Jurnal ELTIKOM : Jurnal Teknik Elektro, Teknologi Informasi dan Komputer Vol. 8 No. 2 (2024)
Publisher : P3M Politeknik Negeri Banjarmasin

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31961/eltikom.v8i2.1242

Abstract

The emergence of deep learning has transformed numerous fields, particularly image processing, where it has substantially enhanced image quality. This paper provides a structured overview of the objectives, methods, results, and conclusions of deep learning techniques for image enhancement. It examines deep learning methodologies and their applications in improving image quality across diverse domains. The discussion includes state-of-the-art algorithms such as Convolutional Neural Networks (CNNs), Generative Adversarial Networks (GANs), and Autoencoders, highlighting their applications in medical imaging, photography, and remote sensing. These methods have demonstrated notable impacts, including noise reduction, resolution enhancement, and contrast improvement. Despite its significant promise, deep learning faces challenges such as computational complexity and the need for large annotated datasets. outlines future research directions to overcome these limitations and further advance deep learning's potential in image enhancement.