https://scholar.dgist.ac.kr/handle/20.500.11750/6308 2026-04-04T15:35:38Z https://scholar.dgist.ac.kr/handle/20.500.11750/58615 Title: Double Random Phase-Encoded Image Reconstruction based on Denoising Diffusion Models Author(s): Zahar, Loaa El; Park, Seonghwan; Moon, Inkyu Abstract: Optical cryptosystems based on double random phase encoding (DRPE) offers a robust method for image encryption, effectively safeguarding images against unauthorized access. However, the inherent randomness of DRPE introduces significant challenges for image processing tasks, including reconstruction and classification. To address these challenges, this study proposes a new approach utilizing diffusion models. Our framework utilizes diffusion models to learn and mitigate the complex noise patterns introduced by DRPE, aiming to reconstruct the original images with high fidelity. Additionally, we explore the efficacy of diffusion models in image reconstruction tasks by evaluating their performance on both encrypted and original datasets, providing insights into their capacity for learning and transferring knowledge across different image versions. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only. 2025-04-13T15:00:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/58614 Title: Photon-counting imaging with denoising diffusion models Author(s): Park, Seonghwan; Moon, Inkyu Abstract: In this paper, we present a multispectral photon-counting imaging (PCI) method based on denoising diffusion models for multispectral visualization of virtually photon limited scenes. We measure the accuracy as well as the speed of denoising diffusion algorithms to estimate multispectral scenes at low light levels. Experimental results demonstrate that the proposed deep learning model achieves better performance in terms of peak-to-SNR (PSNR) and faster computation than variational autoencoders. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only. 2025-04-13T15:00:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/58613 Title: An Overview of Label-Free Quantitative Holographic Live Cell Imaging for Drug Toxicity Assessment Author(s): Moon, Inkyu Abstract: Quantitative phase imaging with digital holographic microscopy (QP-DHM) can be employed to quantify the movement of cardiomyocytes. In this paper, we review the application of QP-DHM in studying cardiomyocytes derived from induced pluripotent stem cells (iPSCs), in control and drug-treated conditions. This allowed us to extract a set of several parameters that can characterize the cardiomyocytes beating patterns from the recorded quantitative phase signal. We monitored the effects of E-4031 and isoprenaline on the cardiomyocyte beating patterns. Our results show that some effects specific to the mode of action of the drugs used can be identified. This stresses that QP-DHM can represent a promising label-free approach to identify new drug candidates by measuring their effects on iPSC-derived cardiomyocytes. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only. 2025-04-13T15:00:00Z https://scholar.dgist.ac.kr/handle/20.500.11750/57927 Title: Privacy-Preserving Classification of Photon-Limited Images Using Deep Learning Author(s): Jeong, Ongee; Moon, Inkyu Abstract: This paper presents a privacy-preserving image classification scheme based on deep learning and photon counting imaging. The vision transformer-based deep learning model can classify the photon-limited color images, which represents the images sparsely by using a few photons. As a result, over 90 % of photon-limited images can be classified when at least 50,000 photons are used. Since some information from the original images is lost in the photon-limited images, it is challenging to recognize the personal information in the photon-limited images. Therefore, the proposed scheme can classify the images while concealing the portion of the information in the images. © 2024 IEEE. 2024-10-15T15:00:00Z