کنفرانس مهندسی برق ایران

صفحه اصلی / سی و سومین کنفرانس بین المللی مهندسی برق

Underwater Image Quality Assessment via Color and Contrast Analysis

نویسندگان :

Meysam Ghalyani¹ Maryam Karimi²

1- دانشگاه شهرکرد 2- دانشگاه شهرکرد

کلمات کلیدی :

Underwater Image،No-reference Image Quality Assessment،Natural Scene Statistics،Color Image Quality Assessment

چکیده :

Underwater images suffer from light absorption, scattering, and color distortion, impacting their quality and usability. This paper proposes an underwater image quality assessment (IQA) framework, integrating statistical features such as distribution characteristics of Generalized Gaussian Distribution (GGD) and Asymmetric Generalized Gaussian Distribution (AGGD) fitted on Mean Subtracted Contrast Normalized (MSCN) coefficients, and the descriptive statistics of HSV and LAB color spaces to address chromatic distortions. Comprehensive evaluations on the standard UID2021 dataset demonstrate the proposed framework's superior performance over existing techniques, providing a more robust measure of underwater image quality and paving the way for improved image enhancement and analysis.