Akademik Veri Yönetim Sistemi
TURK-COSE 2024: VI. International Turkic World Congress on Science and Engineering, Baku, Azerbaycan, 19 - 21 Aralık 2024, cilt.6, ss.2-12, (Tam Metin Bildiri)
Limited dynamic range is a significant challenge in digital photography, as cameras often struggle to capture both bright and dark details simultaneously. This paper presents a novel multi-exposure image fusion method that addresses this limitation by effectively combining multiple images captured at different exposures. The proposed method uses the Retinex theory to decompose input images into reflection and illumination layers. A clustering algorithm is then applied to the illumination layer to identify distinct illumination segments within the images. Contrast and well-exposedness metrics are employed to compute weight maps for each segment and pixel, enabling a more accurate fusion process. The fused image is reconstructed by combining the weighted reflectance and illumination layers. Experimental results demonstrate the effectiveness of the proposed method in enhancing the dynamic range and preserving image details.