| DC 欄位 |
值 |
語言 |
| DC.contributor | 生醫科學與工程學系 | zh_TW |
| DC.creator | 郭俊甫 | zh_TW |
| DC.creator | Chun-Fu Kuo | en_US |
| dc.date.accessioned | 2023-8-21T07:39:07Z | |
| dc.date.available | 2023-8-21T07:39:07Z | |
| dc.date.issued | 2023 | |
| dc.identifier.uri | http://ir.lib.ncu.edu.tw:444/thesis/view_etd.asp?URN=110827014 | |
| dc.contributor.department | 生醫科學與工程學系 | zh_TW |
| DC.description | 國立中央大學 | zh_TW |
| DC.description | National Central University | en_US |
| dc.description.abstract | 傅立葉疊層圖像與人工智慧的結合為解析度改善提供了一個強大的工具。傅立葉疊
層圖像 (Fourier Ptychography,FP)利用傅立葉變換原理，藉由不同激發光陣列，以提供不
同角度之點光源，能夠增強圖像的細節和結構。同時，人工智慧 Artificial Intelligence (AI)技術如深度學習和卷積神經網絡 (Convolution Neural Network,CNN)已在圖像處理中取得
巨大成功。
通過結合這兩種技術，我們能夠更進一步改善圖像的解析度，相比於傳統顯微影像
系統，我們擁有與高倍率相同的解析度與低倍率相同視場範圍 (Field Of View,FOV)。具
體而言，我們可 以使用傅立葉疊層圖像提取出高頻細節和低頻結構，然後利用人工智慧
算法來重建缺失的細節。這種結合可以通過深度學習模型對圖像進行超分辨率處理，以
提高圖像的解析度和品質。
人工智慧算法能夠學習從低解析度圖像到高解析度圖像之間的映射關係，從而在重
建過程中增加細節並恢復圖像的清晰度。這種結合也為圖像重建提供了更多的彈性，因
為人工智慧算法可以根據具體應用和需求進行訓練和調整。
總之，傅立葉疊層圖像搭配人工智慧技術的結合為解析度改善帶來了巨大的潛力。
這種結合能夠提高圖像的解析度，恢復細節並提供更好的視覺品質。隨著人工智慧技 術
的不斷發展和傅立葉疊層圖像的應用擴大，這一結合將在許多領域，如醫學影像、監控
系統和衛星圖像等方面帶來更多的突破和創新。 | zh_TW |
| dc.description.abstract | The combination of Fourier Ptychography (FP) and Artificial Intelligence (AI) provides a powerful tool for improving resolution. Fourier Ptychography utilizes the principles of Fourier transformation and captures images under different illuminations using an array of point sources at different angles, which enhances the details and structures in the image. On the other hand, AI techniques such as deep learning and Convolutional Neural Networks (CNN) have achieved significant success in image processing.
By combining these two techniques, we can further improve the resolution of the image. Compared to traditional microscopy systems, Fourier Ptychography with AI enables us to achieve the same resolution as high magnification, while maintaining the same field of view. Specifically, Fourier Ptychography is used to extract high-frequency details and low-frequency structures, and AI algorithms are employed to reconstruct missing details. This combination can be achieved through deep learning models for super-resolution processing, thereby enhancing the resolution and quality of the image.
AI algorithms can learn the mapping relationship between low-resolution and high-resolution images, thereby increasing the details and restoring the clarity of the image during the reconstruction process. This combination also provides more flexibility in image reconstruction, as AI algorithms can be trained and adjusted according to specific applications and requirements.
In conclusion, the combination of Fourier Ptychography and AI offers great potential for resolution improvement. This combination enhances the resolution, restores details, and provides better visual quality in the image. With the continuous development of AI technology and the expanding applications of Fourier Ptychography, this integration will bring about further breakthroughs and innovations in various fields such as medical imaging, surveillance systems, and satellite imagery. | en_US |
| DC.subject | 傅立葉疊層圖像 | zh_TW |
| DC.subject | 計算成像系統 | zh_TW |
| DC.subject | 深度學習 | zh_TW |
| DC.subject | 人工智慧 | zh_TW |
| DC.subject | Fourier Ptychography | en_US |
| DC.subject | Computational Imaging System | en_US |
| DC.subject | Deep Learning | en_US |
| DC.subject | Artificial Intelligence | en_US |
| DC.title | 計算照明高通量生物醫學成像顯微鏡系統 | zh_TW |
| dc.language.iso | zh-TW | zh-TW |
| DC.title | Computational illumination-based microscope system for high-throughput biomedical imaging | en_US |
| DC.type | 博碩士論文 | zh_TW |
| DC.type | thesis | en_US |
| DC.publisher | National Central University | en_US |