跳到主要內容

臺灣博碩士論文加值系統

(100.28.0.143) 您好!臺灣時間:2024/07/18 07:08
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:楊怡群
研究生(外文):Yang, Yi- Chun
論文名稱:基於色彩味覺之自動化深度調色研究
論文名稱(外文):Research on Automated Deep Color Grading Based on Color Taste
指導教授:周遵儒周遵儒引用關係王希俊王希俊引用關係
指導教授(外文):Chou, Tzren-RuWang, Hsi-Chun
口試委員:呂俊賢王希俊周遵儒
口試委員(外文):Lu, Chun-ShienWang, Hsi-ChunChou, Tzren-Ru
口試日期:2022-01-26
學位類別:碩士
校院名稱:國立臺灣師範大學
系所名稱:圖文傳播學系碩士在職專班
學門:傳播學門
學類:圖文傳播學類
論文種類:學術論文
論文出版年:2022
畢業學年度:110
語文別:中文
論文頁數:64
中文關鍵詞:調色一級調色深度學習深度調色色彩共感覺
外文關鍵詞:Color GradingPrimary Color GradingDeep LearningDeep Color GradingChromes Thesia
相關次數:
  • 被引用被引用:0
  • 點閱點閱:185
  • 評分評分:
  • 下載下載:3
  • 收藏至我的研究室書目清單書目收藏:0
色彩是影像敘事的關鍵要素之一,影視製作的色彩設計在前置階段就已開始;美術指導針對劇情調性做場景的色彩設計,妝髮會做測試,戲服會配合場景及劇情作色彩搭配,攝影指導決定畫面構圖、燈光呈現的方式等,這些都會對整部影視作品的色彩及質感產生影響。殺青後將設計好的色彩交由調光師將所有的色彩及質感設計做最完美的呈現,憑著豐富經驗所累積的美學藝術營造特定情緒氛圍,引導觀眾走入劇情裡。因此,調光師在影視的後期製作裡扮演著極其重要的角色。近年來,隨著OTT(over-the-top)與自媒體的盛行,各播映平台對於影像作品的需求量大增,但後期調色耗時、費工且費用昂貴,因此,若能設計自動化的調色方法必定能解決這些問題。
本研究將學術與實務結合,透過深度學習(Deep Learning)的方式,設計一套自動化的一級調色(Primary Color Grading)方法,以味覺中的酸、甜、苦、辣色調風格作為深度學習的目標。在客觀的效果評估方面,峰值信噪比(Peak Signal to Noise Ratio, PSNR)的數值皆在20以上,另外,在結構相似性指標(Structural Similarity Index Measure, SSIM)方面,數值都接近1,足證用此方法能產製出優良的色調影像品質。在主觀評估上,受測者觀看自動化深度調色(Deep Color Grading)的動態影像後,因色彩共感覺(Chromes Thesia)的作用而有高達82%的色彩味覺識別率,皆能指出該色調所要傳達的味道,這意味著此方法所產製出的色調風格受大眾認同。此外,相較於人工調色的動態影像,雖然總體分數深度調色只有32.81%的認同度,但其中苦味深度調色的認同度卻比人工調色高出26%,證明此方法有很大的進步空間與潛能。
綜觀之,本研究所設計的自動化深度調色方法具有相當大的可行性,雖然目前無法直接應用於調色作業,但可以為非色彩專業者產出參考圖像。
Color is one of the key elements of image narrative, and the color design of film and television production has begun in the pre-production stage; The art director will do the color design of the scene for the plot tone, the makeup and hair will be tested, the costume will match the scene and the plot for color matching, and the director of photography will decide on the composition of the picture, the way the lighting is presented, etc., which will have an impact on the color and texture of the entire film and television work. After the completion of the design, the designed colors are handed over to the dimmer to make the most perfect presentation of all the colors and texture designs, and the aesthetic art accumulated by rich experience creates a specific emotional atmosphere and guides the audience into the plot. Therefore, the dimmer plays an extremely important role in the post-production of film and television. In recent years, with the prevalence of OTT (over-the-top) and self-media, the demand for video works on various broadcast platforms has increased significantly, but the later color grading is time-consuming, labor-intensive and expensive, so if you can design automated color grading methods, you can definitely solve these problems.
This study combines academic and practical methods, and through deep learning, designs an automated primary color grading method, taking the sour, sweet, bitter, and spicy color styles in the taste sense as the goal of deep learning. In terms of objective effect evaluation, the peak signal to noise ratio (PSNR) value is above 20, and in addition, in the structural similarity index measure (SSIM), the value is close to 1, which proves that this method can produce excellent tonal image quality. In terms of subjective evaluation, after the subjects watched the dynamic image of the automated deep color grading, they had a color taste recognition rate of up to 82% due to the role of color co-sensing (Chromes Thesia), which can indicate the taste to be conveyed by the hue, which means that the tonal style produced by this method is recognized by the public. In addition, compared with the dynamic image of artificial color grading, although the overall score depth grading is only 32.81% of the recognition, the recognition degree of the bitter depth color correction is 26% higher than that of the artificial color grading, which proves that this method has a lot of room for improvement and potential. In summary, the automated depth grading method designed by the Institute is quite feasible, and although it cannot be directly applied to color grading operations at present, it can produce reference images for non-color professionals.
第一章 緒 論 1
 第一節 研究背景與動機 1
 第二節 研究目的與問題 4
 第三節 研究範圍與限制 4
 第四節 名詞釋義 5
 第五節 研究流程 6
第二章 文獻探討 7
 第一節 調光師的職能角色 7
 第二節 色彩的通感與味覺之關聯 16
第三節 深度學習 21
第四節 文獻探討小結 25
第三章 研究方法 26
 第一節 研究架構 26
 第二節 研究工具 26
 第三節 自動化深度調色方法設計 29
 第四節 主觀影像評量 36
第四章 研究結果與討論 42
 第一節 自動化深度調色方法的客觀分析 42
 第二節 自動化深度調色方法的主觀評估 47
第五章 研究結論與建議 53
 第一節 研究結論 53
 第二節 研究建議 54
參考文獻 55
 英文文獻 55
 中文文獻 60
 網路資料 61

附件一、主觀影像評量問卷 62
參考文獻
(英文文獻)
1. Arrighetti, W.(2017). The academy color encoding system (ACES): a
professional color-management framework for production, post-production and
archival of still and motion pictures. Journal of imaging, 6, 2-37.
2. Artigues, V.(2017) Color grading with neural network. International
symposium on symbolic and numeric algorithms for scientific computing ,
(pp 286-287),Romania. IEEE.
3. Ariani, D. R., & Neta, F.(2021).Penerapan teknik color grading dan musik
scoring pada tahap paska produksi film horror Waktu Terlarang. Journal of
applied ultimedia and networking, 5(1), 29-41.
4. Bayarri, S., Calvo, C., Costell, E., & Durán, L. (2001). Influence of Color on
Perception of Sweetness and Fruit Flavor of Fruit Drinks. Food Science and
Technology International, 7(5), 399–404.
5. Bonneel, N., Sunkavalli, K., Paris, S., Pfister, H.(2013). Example based video
color grading. Harvard university, Massachusetts.
6. Brands, C. M.(2014). Color Grading on set and in post .Doctoral dissertation
rochester institute of technology, New York .
7. Cheskin, L. (1957). How to predict what people will buy. Liveright, New York.
8. Davinci resolve engineering team (2021). Davinci resolve new features guide.
Blackmagic design , 115.
9. Deliza, R. (1996). The effects of expectation on sensory perception and
acceptance. The university of reading, United Kingdom.
10. Dubose, C. N., Cardello, A. V., & Maller, O.(1980). Effects of colorants and
flavorants on identification, perceived flavor intensity, and hedonic quality of
fruit‐flavored beverages and cake. Journal of Food Science, 45(5), 1393-1399.
11. Deliza, R., & Ares, G. (2010). Studying the influence of package shape and
colour on consumer expectations of milk desserts using word association and
conjoint analysis. Food quality and preference, 21, 930-937.
12. Duchêne, S., Aliaga, C., Pouli, T., & Pérez, P.(2017). Mixed illumination analysis
in single image for interactive color grading. Proceedings of the Symposium on
Non-Photorealistic Animation and Rendering(pp. 1-10).LA:Association for
computing machinery.
13. Faridul, H. S., Pouli, T., Chamaret, C., Stauder, J., Trémeau, A., & Reinhard, E.
(2014). A Survey of Color Mapping and its Applications. Eurographics state of
the art reports, 3(2), 1.
14. Gaggioni, H., Dhanendra, P., Yamashita, J., Kawada, N., Endo, K., & Clark, C.
(2009). S-log: A new lut for digital production mastering and interchange
application. Tokyo, Sony.
15. Guiné, R. P., Correia, P., Florença, S. D. G. E., Moya, K., & Anjos, O.(2021).
Insights into the consumption of edible flowers in Costa Rica. Exploring cities
and countries of the world, 3, 179-207.
16. Gibbs, J. L. (2018). Video color grading via deep neural networks. Iadis-
international journal on computer science and information systems, 13(2),
1-15.
17. 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.
18. Gatys, L. A., Ecker, A. S., Bethge, M., Hertzmann, A. & Shechtman, E. (2017).
Controlling perceptual factors in neural style transfer, Conference on Computer
Vision and Pattern Recognition(pp.3730-3738). Honolulu. IEEE.
19. Horé, A., Ziou, D. (2010)Image quality metrics: PSNR vs. SSIM, International
conference on pattern recognition( pp. 2366-2369). Turkey. IEEE.
20. Hurkman, A. V. (2013) . Color correction handbook: professional
techniques for video and cinema. Pearson education.
21. Huang, H., Wang, H., Luo, W., Ma, L., Jiang, W., Zhu, X., & Liu, W.(2017)Real-
time neural style transfer for videos, Conference on Computer Vision and
Pattern Recognition, (pp. 7044-7052), Honolulu. IEEE.
22. Ho, M. M., Zhou, J. (2021). Deep preset: blending and retouching photos
with color style transfer. Winter conference on applications of computer vision,
(pp. 2112-2120),Waikoloa. IEEE.
23. International telecommunication union (2020). The subjective evaluation
method of TV image quality. 106-137.
24. Johnson, J., Clydesdale, F. M. (1982). Perceived sweetness and redness in
colored sucrose solutions. Journal of food science, 47(3), 747-752.
25. Kang, J. U., Kim, Y. J., Kim, Y. J., Nam, Y. D., Seo, M. C., Sung, S. W., Lee, S. U.
(2017). Fall Conference of the Korea Broadcasting and Media Engineering
Society. Digital imaging Technician system design(pp. 146-148),Seoul.
26. Kang S.R., Faber C., Ladjahasan N., Quam A. (2021). Color and flavor
perception. Advances in the human side of service engineering, 226-232.
27. Long, D. (2014). Color grading on set and in post. Unpublished doctoral
dissertation, Rochester institute of technology, New York.
28. Mari, A. D. (2019). Émergence des Digital Imaging Technician : vers la
reconnaissance d’un nouveau métier . Open edition journals. 12.
29. O'Meara, J. (2021). Digital Color Technologies: Color grading, restoration,
archives and criticism. Teaching media quarterly, 9(1), 2-14.
30. Popa, D. M. (2017). On image recoloring color grading. Journal of
information systems & operations management, 11(1),170-180.
31. Pouli, T. & Phung,T. H. (2018). VR color grading using key views. Proceedings
of the virtual reality international conference(pp. 1-8), New York.
32. Pitié, F. (2020). Advances in colour transfer.IET Computer Vision, 14, 304-322.
33. Pitié, F., Kokaram A. C., Dahyot, R. (2007) Automated colour grading using
colour distribution transfer, Computer Vision and Image Understanding, 107,
123-137.
34. Park, J., Kim, K. W., Jung, J. J. & Park, S. (2020). Image statistics conversion for
color transfer, International symposium on broadband multimedia systems and
broadcasting (pp. 1-4), Paris.
35. Reinhard, E., Stark, M., Shirley, P., & Ferwerda, J. (2002) Photographic tone
reproduction for digital images, Proceedings of the 29th annual conference on
Computer graphics and interactive techniques, 267-276.
36. Romeu, J. V., & Vicente, D. M. M. L. S. (1968). Influyen los colores en el
sabor?. Revista Interamericana de Psicología/Interamerican Journal of
Psychology, 2(3),143-157.
37. Sharma, A. (2019). Understanding RGB color spaces for monitors, projectors,
and televisions. Information Display, 35,17-43.
38. Stillman, J. A. (1993). Color influences flavor identification in fruit flavored
beverages. Journal of Food Science, 58(4), 810-812.
39. Spence, C., Levitan, C. A., Shankar, M. U. et al. (2010)Does food color
influence taste and flavor perception in humans. Chemosensory perception. 3
(1), 68–84.
40. Trentin, E. & Freno, A.(2009). Unsupervised nonparametric density
estimation: A neural network approach. Proceedings of international joint
conference on neural networks, (pp.14-19)Atlanta, Georgia, USA.
41. Westling, J. (2019). How new technology affects professionals in the motion
picture industry. Unpublished doctoral dissertation, Högskolan Dalarna,
Sverige Falun, Borlänge.
42. 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 (pp. 87-92).
Poznan, Poland. IEEE.
43. Xue, S., Agarwala, A., Dorsey, J., & Rushmeier, H. (2013). Learning and
applying color styles from feature films. In Computer Graphics Forum . 32(7),
255-264.
44. Xiao, X., & Ma, L. (2006). Color transfer in correlated color space. In
proceedings of the 2006 ACM international conference on virtual reality
continuum and its applications, 305-309.
45. Zhang, X. Luan Y. Li, X. (2018) Real-time image style transformation based on
deep learning. Journal of Electronic Imaging, 27(4), 68-84.
46. Zhao, 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.
47. Zabaleta, I., & Bertalmío, M. (2021). Photorealistic style transfer for video.
Signal Processing: Image Communication, 95.
(中文文獻)
1. 丁祈方(2017)。數位電影色調創作管理模式之研究:從攝影到一級調光。藝術學
報,85-104。
2. 丁祈方、張國甫(2011)。數位電影製作RAW檔案之運用研究-以短片《杏歡》為
例。藝術學報,195-223。
3. 王安霞(2006) 。包裝形象的視覺設計,南京:東南大學出。
4. 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
市:行政院。
5. 李銘龍(1994)。 應用色彩學。台北市:藝風堂。
6. 阮綠茵、張家豪(2011)。味覺之色彩聯想。流行色,10,90-94。
7. 李貴連、嚴貞(2008)。「五感」設計模式之建構初探-以食品類包裝設計為例。設
計研究,(8),156-164。
8. 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)
9. 林書堯(1977)。色彩認識論,台北:三民。
10. 林珈儀、林承謙(2020)探討枕形袋零食包裝設計-以辣味零食為例。商業設計學
報,24, 165-180。
11. 邱俊維(2014)。電影後期製作高階色彩調整技術之研究–以微電影之色彩調整為
例。未出版碩士論文,中國文化大學,台北市。
12. 張雷(譯)(2014)色彩心理學。海口: 南海出版公司(野村順一,1985)。
13. 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。
14. 章順凱(2010)。兒童食品包裝中味覺的色彩表現。鄭州輕工業學院學報,11,21-
23,42。
15. 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。
16. 張寧、何璐申(2015)。數字調色的藝術-圖解DaVinci Resolve。北京:電子工業。
17. 葉欣睿(譯)(2020)。Deep learning深度學習必讀-讓Kears大神帶你用Python
實作。台北:旗標。(Chollet, F., 2015)
18. 雍自鴻(2007) 。色彩共感覺。蘇州大學學報,27,42-44。
19. 廖汝文(2006)。視覺與嗅覺之關聯性研究。未出版碩士論文,中原大學系,桃
園。
20. 戴孟宗(2011)。現代色彩學:色彩理論、感知與應用。新北市 : 全華圖書。
21. 謝明憲(2018)。調色表現應用於影片之製作。未出版碩士論文,中國文化大學,
台北市。

(網站資料)
Sony(2010). Technical summary for S-Gamut3.Cine/S-Log3 and S-Gamut3/S-Log3. https://pro.sony/s3/cms-static-content/uploadfile/06/1237494271406.pdf
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top