請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84093完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 傅楸善(Chiou-Shann Fuh) | |
| dc.contributor.author | Chih-Kwang Li | en |
| dc.contributor.author | 李志洸 | zh_TW |
| dc.date.accessioned | 2023-03-19T22:04:41Z | - |
| dc.date.copyright | 2022-07-29 | |
| dc.date.issued | 2022 | |
| dc.date.submitted | 2022-07-18 | |
| dc.identifier.citation | Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017). Understanding of a convolutional neural network. 2017 international conference on engineering and technology (ICET), Arici, T., Dikbas, S., & Altunbasak, Y. (2009). A histogram modification framework and its application for image contrast enhancement. IEEE Transactions on image processing, 18(19):1921–1935. Chen, C., Chen, Q., Xu, J., & Koltun, V. (2018). Learning to see in the dark. Proceedings of the IEEE conference on computer vision and pattern recognition, Dong, X., Wang, G., Pang, Y., Li, W., Wen, J., Meng, W., & Lu, Y. (2011). Fast efficient algorithm for enhancement of low lighting video. IEEE International Conference on Multimedia and Expo (ICME),, pages 1–6. Dong, X., Xu, W., Miao, Z., Ma, L., Zhang, C., Yang, J., Jin, Z., Teoh, A. B. J., & Shen, J. (2022a). Abandoning the Bayer-Filter to See in the Dark. arXiv:2203.04042. Retrieved March 01, 2022, from https://ui.adsabs.harvard.edu/abs/2022arXiv220304042D Dong, X., Xu, W., Miao, Z., Ma, L., Zhang, C., Yang, J., Jin, Z., Teoh, A. B. J., & Shen, J. (2022b). Abandoning the Bayer-Filter To See in the Dark. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Fan, M., Wang, W., Yang, W., & Liu, J. (2020). Integrating semantic segmentation and retinex model for low-light image enhancement. Proceedings of the 28th ACM International Conference on Multimedia (ACMMM), Hore, A., & Ziou, D. (2010). Image quality metrics: PSNR vs. SSIM. International Conference on Pattern Recognition, Landtop. Oppo Series Comarison. https://www.landtop.com.tw/reviews/73#Reno-%E7%B3%BB%E5%88%97 Lee, C., Lee, C., & Kim, C.-S. (2013). Contrast enhancement based on layered difference representation of 2d histograms. IEEE Transactions on image processing, 22(12):5372–5384. Lehtinen, J., Munkberg, J., Hasselgren, J., Laine, S., Karras, T., Aittala, M., & Aila, T. (2018). Noise2Noise: Learning image restoration without clean data. arXiv preprint arXiv:1803.04189. Levoy, M. (2008). New Techniques in Computational photography. Retrieved 5, from https://graphics.stanford.edu/talks/compphot-publictalk-may08.pdf Li, M., Wu, X., Liu, J., & Guo, Z. (2018). Restoration of unevenly illuminated images. IEEE International Conference on Image Processing (ICIP),, 1118–1122. Liang, Z., Liu, W., & Yao, R. (2015). Contrast enhancement by nonlinear diffusion filtering. IEEE Transactions on image processing, 673–686. McCann, E. H. L. a. J. J. (1971). Lightness and Retinex Theory,. Journal of the Optical Society of America vol. 61, 1-11. Oppo. Oppo Find X5 Pro. https://www.oppo.com/tw/smartphones/series-find-x/find-x5-pro/# Oppo. (2022). About Oppo. https://www.oppo.com/tw/about/ Sony. Sony’s “All-pixel Autofocus (AF)” technology that quickly catches the target on focus under any conditions. https://www.sony-semicon.co.jp/e/products/IS/mobile/autofocus.html Sony. (2018). Sony Releases Stacked CMOS Image Sensor for Smartphones with Industry’s Highest*1 48 Effective Megapixels. https://www.sony.com/en/SonyInfo/News/Press/201807/18-060E/ Su, H., & Jung, C. (2017). Low light image enhancement based on two-step noise suppression. 2017 IEEEInternational Conference on Acoustics, Speech and Signal Processing (ICASSP), 1977–1981. Wang, R., Zhang, Q., Fu, c.-W., Shen, X., Zheng, W.-S., & Jia, J. (2019). Underexposed photo enhancement using deep illumination estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Wei, C., Wang, W., Yang, W., & Liu, J. (2018). Deep retinex decomposition for low-light enhancement. arXiv preprint arXiv:1808.04560 Wu, X., Liu, X., Hiramatsu, K., & Kashino, K. (2017). Contrast-accumulated histogram equalization for image enhancement. IEEE international conference on image processing, Zhang, Y., Zhang, J., & Guo, X. (2019). Kindling the darkness: Apractical low-light enhancer. Proceedings of the 27th ACM international conference on multimedia (ACMMM), 1632–1640. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/84093 | - |
| dc.description.abstract | 本論文提出深度學習的模型來進行低光源(月光, 0.5lux)連續影像1080p的降雜訊處理。近幾年來大眾對於手機攝影的需求以及要求有越來越大與越嚴格的趨勢。於是對於手機廠商，它們決定對於影像處理上面需要有更新穎的處理方式。除了傳統的處理方式，目前廠商的研究主要專注在深度學習對於Raw影像的生成的幫助，尤其是對於低光源目標的降雜訊以及高動態範圍成像 (HDRI: High Dynamic Range Image)。透過感光元件所獲取的最原始資訊來訓練模型。可以大幅提升深度學習的成功及成效。於是我們決定設計一套降雜訊流程，參考幾種最先進模型的優點後，提出一個新的模型，對於低光度的連續影像，提取出有影像裡面具有光照度意義的特徵點，利用其資訊對於原始影像來產生去雜訊後的擬合影像。 | zh_TW |
| dc.description.abstract | We propose a deep learning model targeted for low light 1080p video, which is under 0.5 lux of illumination, real-time video enhancement, and denoising. The cellphone photography market demand and competition become larger and harsher. Therefore, cellphone manufacturers decide to have novel processing algorithms in the image processing pipeline. Besides traditionally, the major market effort is dedicated to better generation of raw images using deep learning methods, especially for denoising and High Dynamic Range Image (HDRI) for low-light targets. Using raw information as the input of the model can increase the effectiveness and the success rate when training model. Thus, we design a model for a series of continuous low illumination raw image data, extract features with significant luminance features and output the denoised, enhanced image. | en |
| dc.description.provenance | Made available in DSpace on 2023-03-19T22:04:41Z (GMT). No. of bitstreams: 1 U0001-1507202222180600.pdf: 4942092 bytes, checksum: d2c8fd5026e268e8fa5cc504c6717a86 (MD5) Previous issue date: 2022 | en |
| dc.description.tableofcontents | Chapter 1. Introduction 1 1.1 Computational Photography 1 1.2 Video Enhancement 1 1.3 Thesis Organization 3 Chapter 2. Background 4 2.1 Case Study: Oppo Find X5 Pro 4 2.1.1 Oppo 4 2.1.2 Find X5 Pro 5 2.1.3 Features 6 2.1.4 Oppo Model Performance Evaluation 10 Chapter 3. Related Works 20 3.1 Overview 20 3.2 Traditional Method for Image Denoise 20 3.3 Machine Learning and Deep Learning 22 3.4 Convolution Neural Network 22 3.5 Neural Network Methods for Image Denoising 23 Chapter 4. Methodology 26 4.1 Overview 26 4.2 Model Introduction 26 4.3 Data Usage 27 4.4 Denoising Process 28 4.5 Evaluation 29 Chapter 5. Experiments and Results 30 5.1 Overview 30 5.2 MCR dataset testing results 30 5.3 SSIM, PSNR and Runtime Evaluation 41 5.4 Model analysis 42 Chapter 6. Conclusion and Future Works 44 6.1 Conclusions 44 6.2 Future Work 44 Chapter 7. References 46 | |
| dc.language.iso | en | |
| dc.title | 李月光: 基於機器學習之1080p月光即時視訊降雜訊 | zh_TW |
| dc.title | LiMoonLight: Noise Reduction for 1080p Real-Time Video under Moon Light with Machine Learning | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 110-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 詹志康(Chih-Kang Chan),沈裕池(Yu-Chih Shen) | |
| dc.subject.keyword | 人工智慧,影像處理,影像降雜訊,月光全彩視訊,計算攝影, | zh_TW |
| dc.subject.keyword | artificial intelligence,image processing,image denoising,moonlight color video,computational photography, | en |
| dc.relation.page | 49 | |
| dc.identifier.doi | 10.6342/NTU202201491 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2022-07-19 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 生醫電子與資訊學研究所 | zh_TW |
| dc.date.embargo-lift | 2027-07-15 | - |
| 顯示於系所單位： | 生醫電子與資訊學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-1507202222180600.pdf 目前未授權公開取用 | 4.83 MB | Adobe PDF | 檢視/開啟 |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。