電影和電視的調色（Color Grading）任務既重要又極複雜。調色涉及美學和技術，需要訓練有素技術人員、耗費大量時間，在情節中提高視覺吸引力，藉改變意象引導觀眾視覺。在這過程中 ，色彩是影像不可或缺的敘述元素，它在觀賞者中扮演著關鍵重要的角色。色彩可突顯影像主體張力，引起人們關注。場景交替、色彩變化都由調光師擔負起重要任務，校正顏色維持藝術價值以取悅人眼，隱藏著色中的不連續性，微妙調整鏡頭。調色，更是一個相當不容易操縱領域。當作業時效性成為商業製片重要考量時，使用自動方式解決是一個受歡迎且省錢選項，所以迅速取得值得參考的深度調色影像，有其高度價值。
本研究結合調光與人工智慧跨領域應用，設計以食物顏色、味覺中酸、甜、苦、辣的影像主體二級自動色彩轉換方法。此為食物味覺色調及有關凸顯主體影像二級自動色彩轉換創新嘗試，實際轉換快速且便利。轉換結果依客觀評量之峰值信噪比（PSNR）平均數據為31.29。結構相似性指標（SSIM）平均數據為0.956。從這些數字足以證明此二級自動色彩轉換應用之可實踐性。依主觀評量之（深度調色之判斷酸甜苦辣正確率）平均為61.76％，表示超過六成受測者可以精準分辨深度調色四種味覺。但在接近四項味覺目標色選擇深度調色平均為25%，只有四分之一的專業及非專業人士認為深度調色比人工調色好。綜合以上數據。充分驗證此方法的可行性及實用性。深度調色確實有效逼近人工調色，可以有效節省後期製作時間與費用。雖然深度調色仍有進步空間，但對於未具調光技能與設備的一般使用者而言，具有方便輔助性。

During the television and film post production process, color grading plays an important role. The complex procedure involves delicate technology and theory of aesthetics. Color grading definitely is a time-consuming, semi-art work and has to be practiced by highly trained technicians. Nice color grading work may enhance the visual appeal of plot texture to guide the viewing vision. Color, of course is the image indispensable narrative element that can highlight the main tension of image and attract viewers’ eyeballs. Nevertheless, while correcting the color of filming material to hide some discontinuities, the artistic purpose design must be maintained. For commercial-oriented production considerations, an near-automatic color grading method is a valuable option. Time saving means cost down as well for post production com panies.
This research project combines the cross-field application of color grading and artificial intelligence, in order to design a secondary automatic color grading method for image subjects based on good color, good flavors (sourness,sweet,bitterness,spicy hot)。The main purpose is to make the conversion accurate, fast and convenient. I found that :the averages data of the peak signal-to-noise ratio（PSNR） of the conversion result is 31.29 according to the subjective evaluation. The average data of structural similarity index（SSIM） is 0.956.Those comparative data can prove the secondary automatic color grading is effective and feasible.
Again, according to the subjective evaluation, the average correct rate of sourness, sweet, bitterness, spicy hot is 62.76%. That means more than 60% members of the 17 persons focus group can accurately differentiate the four flavors after deep color grading. The above-mentioned result was the first part of investigation. I found something interesting in the second part: only 25% of the focus group members who are broadcasting professionals and non-professionals as well considered the deep color grading was better than manual color grading. This data indicated that a lot of users are still approach to manual color grading because of the working mode and sense of unfamiliarity. I wrap up the result: the deep color grading method has the effects close enough to manual color grading. It does save time and cost of post production. Its feasibility and practicability have been verified.
Although there are plenty of room for improvement in deep color grading, I can not deny it had a great potential to be polished and be accepted by users in broadcasting industry in the near future.

英文文獻
Armenteros Gallardo, M., Benítez Iglesias, A. J., & Utray Delgado, F. (2015). Post producción digital: una perspectiva contemporánea. Madrid:Dykinson.
Artusi, A., Richter, T., Ebrahimi, T., & Mantiuk, R. K. (2017). High dynamic range imaging technology. IEEE Signal processing magazine, 34(5), 165-172.
Ariani, D. R., & Neta, F. (2021). Penerapan teknik color grading dan musik scoring pada tahap paska produksi film horor Waktu Terlarang. Journal of applied multimedia and networking, 5(1), 29-41.
Adams, F. M., & Osgood, C. E. (1973). A cross-cultural study of the affective meanings of color. Journal of cross-cultural psychology, 4(2), 135-156.
Bonneel, N., Sunkavalli, K., Paris, S., Pfister, H.（2013）. Example based video color grading. Harvard university, Massachusetts.
Brands, C. M.（2014）. Color Grading on set and in post .Doctoral dissertation rochester institute of technology, New York .
Barron, C., Aylsworth, W., Gluck, T. E., Hummel, R., Tronick, M., & Maltz, A. (2019). Report from the academy of motion picture arts and sciences' science and technology council. SMPTE Motion Imaging Journal, 128(8), 52-61.
Chinnock, C. (2016). White paper：The status of wide color gamut UHD TV. Insight Media. 53.
Da Silva, I. N., Spatti, D. H., Flauzino, R. A., Liboni, L. H. B., & dos Reis Alves, S. F.(2017). Artificial neural network architectures and training processes. Artificial neural networks (pp. 21-28). Springer, Cham.
Fischer, W. (2008). Digital video and audio broadcasting technology: a practical engineering guide. Springer Science & Business Media.
Frigo, O., Sabater, N., Demoulin, V., & Hellier, P. (2014). Optimal transportation for example-guided color transfer. Asian Conference on Computer Vision (pp. 655-670). Springer, Cham.
Fautier, T. (2016). UHD for broadcast and the DVB ultra HD-1 phase 2 standard.
Gatys, L. A., Ecker, A. S. & Bethge, M. （2016） Image Style Transfer Using Convolutional Neural Networks, Conference on Computer Vision and Pattern Recognition （pp. 2414-2423）. Las Vegas. IEEE.
Guionnet, T., Raulet, M., & Burnichon, T. (2020). Forward-looking content aware encoding for next generation UHD, HDR, WCG, and HFR. SMPTE Motion Imaging Journal, 129(7), 26-32.
Gibbs, J. L. (2018). Video color grading via deep neural networks. Iadis-internation journal on computer science add information system,13(2), 1-15
Huang, H., Wang, H., Luo, W., Ma, L., Jiang, W., Zhu, X., & Liu, W. (2017). Real-time neural style transfer for videos. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 783-791). Honolulu.
Haine, C. (2019). Color grading 101: Getting started color grading for editors, cinematographers, directors, and aspiring colorists. Routledge.
Ion, L., & Hunphery, N. (2017). White paper :4K digital capture and post-production workflow. Canada:Dalsa digital cinema.
International telecommunication union (2012). Parameter values for ultra-high definition television systems for production and international programme exchange.
International telecommunication union (2012). The present state of ultra-high definition television.
Johnson, G. M. (2005). The quality of appearance. In proceedings of 10th congress of the international colour association (pp. 303-308). Granada, Spain.
Leirpoll, J., Osborn, D., Murphy, P., & Edwards, A. (2017). Compositing in premiere pro. The cool stuff in premiere pro (pp. 677-756). Apress, Berkeley, CA.
Luštica, A. (2018). Live HDR workflow. 2018 international symposium ELMAR (pp. 87-90) , Zadar, Croatia. IEEE.
Li, Y., Liu, M. Y., Li, X., Yang, M. H., & Kautz, J. (2018). A closed-form solution to photorealistic image stylization. Proceedings of the european conference on computer vision,453-468.
Nielsen, M. A. (2015). Neural networks and deep learning . San Francisco, CA: Determination press.
Reinhard, E., Adhikhmin, M., Gooch, B., & Shirley, P. (2001). Color transfer between images. Computer Graphics and Applications, 21(5), 34-41. IEEE.
Pitié, F. (2020). Advances in colour transfer. IET computer vision, 14(6), 304-322.
Sara, U., Akter, M., & Uddin, M. S. (2019). Image quality assessment through FSIM, SSIM, MSE and PSNR - a comparative study. Journal of computer and communications, 7(3), 8-18.
Sugito, Y., & Bertalmío, M. (2020). Non-experts or experts ? statistical analyses of MOS using DSIS method. International Conference on Acoustics, Speech and Signal Processing, 2732-2736. IEEE.
Sengupta, S., Jayaram, V., Curless, B., Seitz, S. M., & Shlizerman, I. K. (2020). Background matting: the world is your green screen. In proceedings of the IEEE/CVF conference on computer vision and pattern ecognition , 2291-2300. IEEE.
Gerrits, H. J. M., Vendrik, A. J. H. (1970). Simultaneous contrast, fillingin process and information processing in man's visual system. Experimental Brain Research, 11, 411–430.
Soranzo, A. (2015). Simultaneous contrast, simultaneous brightness contrast, simultaneous color contrast. Encyclopedia of color science and technology. Springer, Berlin, Heidelberg, 1149-1152.
Taniguchi, M., & Tezuka, T. (2021). Automatic trimap generation by a multimodal neural network. International conference on image processing, 2768-2772. IEEE.
Ultra HD Forum. (2020). Ultra HD Forum Guidelines.106-137.
Van Hurkman, A. (2014). Color correction handbook: professional techniques for video and cinema. pearson education.
Weber, D., & Kostek, B. (2019). Subjective tests for gathering knowledge for applying color grading to video clips automatically. signal processing: algorithms, architectures, arrangements, and applications, 87-92. IEEE.
Winkler, S., & Mohandas, P. (2008). The evolution of video quality measurement: from PSNR to hybrid metrics. IEEE Transactions on Broadcasting, 54(3), 660-668.
Wang, J., & Li, S. (2020). Investigation and design of 4K ultra high definition television production and broadcasting system.Information technology and mechatronics engineering conference, 579-582. IEEE.
Wichmann, F. A., Sharpe, L. T., & Gegenfurtner, K. R. (2002). The contributions of color to recognition memory for natural scenes. Journal of Experimental Psychology: Learning, Memory, and Cognition, 28(3), 509.
Zhao, H. H., Rosin, P. L., Lai, Y. K., Lin, M. G., & Liu, Q. Y. (2019). Image neural style transfer with global and local optimization fusion. IEEE Access, 7, 85573-85580.
Zabaleta, I., & Bertalmío, M. (2021). Photorealistic style transfer for video. Signal Processing: Image Communication, 95, 116-240.
Series, B. T. 500-14. (2019). The present state of ultra-high definition television.
Series, B. T. 2246-6. (2016). The present state of ultra-high definition television.
Soranzo, A. (2015). Simultaneous contrast, simultaneous brightness contrast, simultaneous color contrast. Encyclopedia of color science and technology. Springer, Berlin, Heidelberg, 1149-1152.
中文文獻
行政院文化部（2016）。2016-2020年推動超高畫質電視內容升級前瞻計畫，台北：行政院。
中國電影電視製作協會（2019）。節目製播用高清晰度電視圖像監視器色彩 校準指南，北京：CSMPTE。
王旭正、翁麒耀、林家禎（2012)。數位影像處理與應用，北京：博碩文化
王建堯、王家慶、吳信輝、李宏毅、高虹安、張智星、曾新穆、陳信希、蔡炎龍、鄭文皇、蘇尚育（2019）。人工智慧導論，台北：全華。
古大治、傅師申、楊仁鳴（2000）。色彩與圖形視覺原理關於看的藝術與科學，北京：科學出版社。
方程（2016）。DaVinci Resolve12數字電影調色典型實例精講，北京：人民郵電出版社。
文淵閣工作室、鄧文淵（2021）。Python機器學習與深度學習特訓班，南投：碁華。
林書堯（1977）。色彩認識論，台北：三民。
曲思義（2019）。調光／影像的工藝，電影感的煉成，台北：電影協會 。
曾志剛（2007) 。數字中間片校色過程中的色彩管理概述。北京電影學院學報，69-74。
湯曉鷗、陳玉琨（2018）。人工智能基礎（高中版），北京：華東師範。
陳昇瑋、溫怡玲（2019）。人工智慧在台灣：產業轉型的契機與挑戰，台北：天下雜誌。
陳俊才（2017）。色彩調和美度與色彩味覺之關聯性研究。未出版碩士論文，國立高雄第一科技大學，高雄市。
張揚（2015）。影視調色學，北京：人民郵電。
張宇、何潞申（2015）數字調色的藝術圖解DaVinci Resolve，北京：電子工業出版社。
鄭柏左（2004）。色彩理論與數位影像。臺北市：新文京出版。
吳嘉芳（譯）（2021）。Deep learning：用Python進行深度學習的基礎理論實作。台北：碁峰資訊。（斎藤康毅，2017）
財團法人公共電視文化事業基金會（2016）。公共電視超高畫質電視製作中 心使用手冊，台北 ：公共電視。
網路資料
Mathworks (2021). Image quality metrics.
https://www.mathworks.com/help/images/image-quality-metrics.html
Studio binder (2020).Color grading vs. Color correction process for video: a complete guide.
https://www.studiobinder.com/blog/color-grading-vs-color-correction- process/
Video maker (2021). Color grading in post production.
https://www.videomaker.com/article/c3/15710-color-grading-in-post-production
Morton J. (2010), Why color matters. Available from:
http://www.colormatters.com/color-and-design/why-color-matters/
台北金馬影展 (2021). Digital Cinema Report.
https://www.goldenhorse.org.tw/academy/filmacademyplus/class/history/1354
Chuang, Yung-Yu. (2016). Matting and Compositing .
https://www.csie.ntu.edu.tw/~cyy/courses/vfx/20spring/lectures/handouts/lec11_matting_4up.pdf
https://en.wikipedia.org/wiki/Peak_signal-to-noise_ratio
https://en.wikipedia.org/wiki/ Structural_similarity
https:// www.getit01.com/2018013124281841/
https://ultrahdforum.org/