Article
Engineering, Biomedical
Olubunmi O. Sule, Absalom E. Ezugwu
Summary: Early detection of ophthalmologic complications in retinal fundus images is crucial for accurate analysis and diagnosis. This paper proposes a method that adjusts uneven illumination and color balance using histogram matching and enhances local contrast with CLAHE in the luminance component of the HSV color space. Experimental results show that the proposed method can significantly enhance color retinal fundus images and outperform state-of-the-art techniques in both visual and quantitative comparisons.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Computer Science, Information Systems
Najmul Hassan, Sami Ullah, Naeem Bhatti, Hasan Mahmood, Muhammad Zia
Summary: In this paper, a Retinex-based underwater image enhancement approach is proposed, which enhances contrast with CLAHE, restores colors, edges, and smooths blurred parts using Retinex and bilateral filtering, achieving better enhancement of underwater images through comprehensive utilization of individual strengths of different algorithms.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Interdisciplinary Applications
Erjian Guo, Huazhu Fu, Luping Zhou, Dong Xu
Summary: Deep learning models for image enhancement have greatly improved the readability of fundus images and reduced the risk of misdiagnosis. However, the discrepancy between synthetic and real images hinders the generalization of these models. In this work, we propose an optimized teacher-student framework that simultaneously enhances images and adapts to domain shift. Our framework outperforms baseline approaches and benefits downstream clinical tasks.
IEEE TRANSACTIONS ON MEDICAL IMAGING
(2023)
Article
Remote Sensing
Wisdom Simataa Moola, Wietske Bijker, Mariana Belgiu, Mengmeng Li
Summary: This study developed a fuzzy classifier based on TWDTW distances to map vegetable types from Sentinel-1A SAR image time series. By calculating fuzzy memberships for each pixel, assessing classification uncertainty, and applying thresholds during defuzzification, the classification accuracy of the image was improved.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2021)
Article
Environmental Sciences
Aswathy K. Cherian, Eswaran Poovammal, Ninan Sajeeth Philip, Kadiyala Ramana, Saurabh Singh, In-Ho Ra
Summary: This paper presents a method to address the issues of light absorption and scattering in underwater imaging using a trained model network. The method includes denoising, contrast enhancement, and resolution improvement techniques. Experimental results demonstrate that this method can effectively produce enhanced underwater images from degraded ones.
Article
Computer Science, Information Systems
Sinan S. Mohammed Sheet, Tian-Swee Tan, M. A. As'ari, Wan Hazabbah Wan Hitam, Joyce S. Y. Sia
Summary: The identification of retinal diseases plays a critical role in preserving vision. This study introduces an enhanced design of a fully automatic multi-class retina diseases prediction system, which utilizes upgraded image processing techniques and transfer learning methods, demonstrating high accuracy and superior performance.
Article
Chemistry, Analytical
Khalaf Alshamrani, Hassan A. Alshamrani, Fawaz F. Alqahtani, Bander S. Almutairi
Summary: Breast cancer is a common and life-threatening disease that can spread in the body. Early detection is crucial for successful treatment. By improving the contrast in mammograms, the accuracy of diagnosis can be enhanced.
Article
Chemistry, Multidisciplinary
Mofleh Hannuf AlRowaily, Hamzah Arof, Imanurfatiehah Ibrahim
Summary: This paper presents an automatic correction method for luminosity and contrast variation in fundus images. The method includes five stages: image input, filtering, luminosity correction, histogram stretching, and post-processing. It achieves a 30% reduction in luminosity variation and a 90% increment in contrast on average for the tested images.
APPLIED SCIENCES-BASEL
(2023)
Article
Optics
Mohineet Kaur, Ram Krishna Sarkar, Manoj Kumar Dutta
Summary: This study discusses how to improve the quality of traditional cultural artwork using modern image processing techniques, such as filtering, histogram equalization, and the implementation of a combination of different techniques in MATLAB. Quality assessment metrics are used to evaluate the processed image.
Article
Chemistry, Multidisciplinary
Dayana Ribas, Antonio Miguel, Alfonso Ortega, Eduardo Lleida
Summary: This paper proposes a Deep Learning (DL) based Wiener filter estimator for speech enhancement in the framework of the classical spectral-domain speech estimator algorithm. By using data-driven learning, the proposed method improves the robustness and performance of the speech enhancement algorithm, which is validated by objective quality metrics and practical examples.
APPLIED SCIENCES-BASEL
(2022)
Article
Environmental Sciences
Andrzej Stateczny, Sujatha Canavoy Narahari, Padmavathi Vurubindi, Nirmala S. Guptha, Kalyanapu Srinivas
Summary: A new framework is implemented in this study for predicting underground water levels using remote sensing images. By preprocessing and extracting features, the features are combined as a novel hydro index, which is then used to predict the water levels. The efficacy of the proposed framework is proven through different performance measures.
Article
Engineering, Biomedical
Deepak Kumar Maharana, Pranati Das, Ranjeet Kumar Rout
Summary: This paper proposes an unsupervised approach for automatically extracting blood vessels from fundus photographs using logarithmic transformation, contrast limited adaptive histogram equalization, and matched filtering technique. Different thresholding techniques were evaluated to find the best segmentation scheme, and the final vessel segmented image was compared to the ground truth image using statistical measures. The proposed method achieved high accuracy on multiple datasets.
COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION
(2023)
Article
Engineering, Electrical & Electronic
Wen Xu, Chun Huang, Hui Jiang
Summary: This article mainly analyzes the steady state of the Linear Kalman-filter-based phase-locked loop (LKF-PLL) and its adaptive process, introduces a design guideline, and proposes a dynamic tracking algorithm under phase jump condition. Comparative tests show that the proposed algorithm can greatly improve dynamic response while maintaining steady-state performance.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Olubunmi Sule, Serestina Viriri
Summary: This paper proposes an improved method for optimal segmentation of blood vessels in retinal fundus images using convolutional neural networks (CNNs). By enhancing the contrast of the RGB and green channel, the improved images are evaluated for quality using various measures. The results show that the improved RGB quality outperforms the improved green channel, indicating that using RGB for contrast enhancement effectively improves the image quality. The proposed method achieves an accuracy of 94.47%, sensitivity of 70.92%, specificity of 98.20%, and AUC (ROC) of 97.56% on the DRIVE dataset.
JOURNAL OF DIGITAL IMAGING
(2023)
Article
Computer Science, Artificial Intelligence
Erwin, Heranti Reza Damayanti
Summary: This study proposed a new method for segmenting blood vessels in retinal images using various image processing techniques and data analysis methods. The experimental results showed high accuracy and specificity on two datasets.
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE AND APPLICATIONS
(2021)