透明OLED是一種允許光線穿透的面板。每個畫素都可以獨立產生RGB光源，無需統一的背光模組。理論上，這可以讓人們同時看到透明OLED顯示的圖案和顯示器後面的場景。然而，OLED 的透明特性使其顯示器更容易受到環境光的影響。
如果要開發校準演算法，確保透明OLED能夠準確地顯示影像，而不受不同環境光源的影響，則需要針對每種照明條件建立相應的場景來驗證演算法的有效性。這個過程既耗時又昂貴。使用軟體模擬透明 OLED 在各種環境光條件下的視覺效果是一個比較簡單的解決方案，不需要物理地創建每個照明環境。然而，目前不存在這樣的模擬器。關於環境光對顯示效果影響的研究主要集中在 CRT 和 LCD 技術上，而且這些研究通常僅分析已知的光源，不能知道未知環境光對顯示效果的影響。
因此我們提出了一種方法，用來模擬透明OLED在不同環境光源下的視覺效果。此模擬器有兩個輸入：一個BMP圖檔和環境光的XYZ值。模擬器會產生一個新的BMP影像，表示輸入的BMP影像在該環境光下的顯示效果。
模擬的流程共有四個步驟:首先用改進過的GOG模型將BMP的每個pixel從RGB空間轉換到XYZ空間。第二步是預測環境光與透明OLED顯示顏色混合的結果，在這一步使用深度學習來模擬不同光源混合後的結果。為了訓練模型，我們建立了一個暗房。暗房可以更換不同色溫的燈泡，使用不同的背景材料，改變背景與透明OLED的距離，以創造不同的顯示環境。並使用CA-VP410感測器來收集不同顯示環境下的資料來訓練神經網路。第三步，檢查第二步的預測結果是否超出透明OLED的色域，並進行warping。最後一步再使用神經網路將第三步得到的結果從XYZ空間轉換到RGB空間。
最後，我們計算了預測結果與實際結果之間的 Delta E 和亮度誤差，以評估程式的效能。模擬的Delta E在1.5到2.5之間，亮度誤差在2%到4%之間。此模擬方法為不同環境條件下透明OLED的研究提供了實用工具和參考。

Transparent OLED is a panel that allows light to pass through. Each pixel independently generates RGB light sources without the need for a unified backlight module. In theory, this allows people to view both the pattern displayed by the transparent OLED and the scene behind the display simultaneously. However, the transparent nature makes its display more susceptible to ambient light.
If one were to develop a calibration algorithm that ensures the transparent OLED can display images accurately without being affected by different ambient light sources, corresponding scenarios would need to be created for each lighting condition to validate the algorithm's effectiveness. This process would be both time-consuming and expensive. Alternatively, using software to simulate the visual effects of a transparent OLED under various ambient light conditions provides a simple solution, bypassing the need to physically recreate each environment. However, no such simulator currently exists. Research on the impact of ambient light on display performance mainly focuses on CRT and LCD technologies, and these studies typically analyze only known light sources, without addressing how other ambient light sources might affect display performance.
Therefore, we proposed a method to simulate the visual effects of a transparent OLED under different ambient light sources. The simulator takes two inputs: a BMP image file and the XYZ values of the ambient light. It then generates a new BMP image, representing how the input BMP image would appear under that ambient light.
The simulation process involves four steps. First, we use a modified GOG model to convert each pixel in the BMP file from RGB color space to XYZ color space. In the second step, we predict the result of mixing the ambient light with the light emitted by the transparent OLED. This step utilizes deep learning to simulate how various light sources interact. To train the model, we constructed an experimental darkroom capable of swapping light bulbs with different color temperatures, using various background materials, and adjusting the distance between the background and the transparent OLED. We used the CA-VP410 sensor to collect data under different conditions to train the neural network. In the third step, we check whether the predicted result from step two falls outside the transparent OLED's color gamut and perform warping. The final step uses a neural network to convert the results obtained in the third step from XYZ color space to RGB color space.
We then calculated the Delta E and brightness errors between the predicted and actual results to evaluate the performance of the program. The simulated delta E falls between 1.5 and 2.5, and the brightness error is between 2% and 4%. This simulation method provides practical tools and references for the research of transparent OLEDs under different environmental conditions.

Ana C. Morgado, Tomas Souper, Ana Marques, Inês Silva, Luís Rosado. (2023). Reinforcement Learning to Improve Color Adjustments in the Ceramic Industry. ICMLT '23: Proceedings of the 2023 8th International Conference on Machine Learning Technologies.
Arne M. Bakke, Ivar Farup, Jon Y. Hardeberg. (2010). Evaluation of Algorithms for the Determination of Color Gamut Boundaries. Journal of Imaging Science and Technology.
Berns, R. S. (1996, 5). Methods for characterizing CRT displays. Displays, pp. 173-182.
CohenJacob. (1976). Statistical Power Analysis for the Behavioral Sciences. New Tork.
Corte, W. D. (1998, 7). Colour solid of CRT phosphors when ambient illumination is present. Displays, pp. 107-114. Retrieved from https://www.sciencedirect.com/science/article/pii/0141938288900017
Gail M. Sullivan, Richard Feinn. (2012). Using Effect Size—or Why the P Value Is Not Enough. Journal of graduate medical education.
Gouraud, H. (1971). Continuous shading of curved surfaces. IEEE Transactions on Computers. C-20, pp. 623–629.
Hertel, D. (2018, 10 29). Optical measurement standards for reflective e-paper to predict colors displayed in ambient illumination environments. Color Research & Application.
Hsin-Pou Huang, Minchen Wei. (2018, 2). White appearance of a tablet display under different ambient lighting conditions. Optics Express.
Jiajia Shen, Xiang Zhou. (2017, 05 15). Spectrophotometric colour matching algorithm for top-dyed mélange yarn, based on an artificial neural network. Coloration Technology.
Jiajie Fan, Yutong Li, Irena Fryc, Cheng Qian, Xuejun Fan, Guoqi Zhang. (2020, 02). Machine-Learning Assisted Prediction of Spectral Power Distribution for Full-Spectrum White Light-Emitting Diode. IEEE Photonics Journal.
Jialu Wu, Minchen Wei, Yang Yang, Wenjun Wang. (2023, 07 03). Color characterization model for OLED displays with crosstalk effects. Color Research & Application.
KANG-KYU LEE, JAE-WOO KIM, JE-HO RYU, JONG-OK KIM. (2020, 5 11). Ambient light robust gamut mapping for optical. Optics Express.
Kubota, S. (1995). Effects of ambient lighting conditions on luminance contrast and color gamut of displays with different technologies. Advances in Human Factors/Ergonomics, pp. 643-648.
LAYCOCK, J. (1985). Colour contrast calculations for displays viewed in illumination. Journal of the Institution of Electronic and Radio Engineers.
M R Pointer, G G Attridge, R E Jacobson. (2002). Gamut considerations for accurate colour reproduction on a computer display. The Imaging Science Journal.
Malathy Jawahar, Chandra Babu Narasimhan Kannana, Mehta Kondamudi Manobhai. (2014, 10 17). Artificial neural networks for colour prediction in leather dyeing on the basis of a tristimulus system. Coloration Technology.
Phong, B. T. (1975). Illumination for computer generated pictures. Communications of the ACM 18, pp. 311–317.
Raja Balasubramanian, Edul Dalal. (1997). Method for quantifying the color gamut of an output device. SPIE digital library.
S. Zhukov, A.Iones, G.Kronin. (1998, 1 1). An ambient light illumination model. Rendering Techniques ’98.
Sabine E. Susstrunk, Jack M. Holm, Graham D. Finlayson. (2000, 12 21). Chromatic adaptation performance of different RGB sensors. PROCEEDINGS OF SPIE.
Seong-En Lee, Min Su Sim, Chang-Mo Yang, Choon-Woo Kim. (2019). Evaluation of the legibility of the on-screen. Journal of Information Display.
Stamate, Asei Akanuma, Daniel. (2022). A Neural Network Approach to Estimating Color Reflectance with Product Independent Models. Artificial Neural Networks and Machine Learning.
Sung-Hak LEE, Kyu-Ik SOHNG. (2010, 08 01). A Controllable GOG Model for Ergonomic Color Reproduction of Digital Imaging Systems. IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences, pp. 1453-1456.
Wei, M. (2023). Colour characterization and specification for liquid crystal displays (LCDs) and organic light emitting diode (OLED) displays. p. 157.
XU LIHAO, XU CHUNZHI, MING RONNIER LUO. (2022). Accurate gamut boundary descriptor for displays. Optics Express, pp. 1615-1626.
Yasuhiro Yoshida, Yoichi Yamamoto. (2002). Precise Color Characterization Model for LCD and It's Evaluation of Applicability. The Journal of The Institute of Image Information and Television Engineers, pp. 1279-1290.
Yasuhiro Yoshida, Yoichi Yamamoto. (2003, 5 7). Color management of liquid crystal display placed under light environment. Electronics and Communications in Japan.
Yongmin Park, Dongwoo Kang, Sungjin Kim, Taeseong Han. (2013, 9). Simulation of Visual Quality for Transparent OLED Display. SID Symposium Digest of Technical Papers, (p. 159).
Zhang Yin, Jiang Yongwen, Lin Maohai. (2016, 4 28). A New Device Color Gamut Boundary. WILEY, pp. 173-181.
Zhi Chuan, Shi Yi, Sun Bangyong. (2016). Research on Gamut Visualization Method of the color output device. JOURNAL OF DISPLAY TECHNOLOGY.
吉武良治. (1997). 光学測定と主観評価の対応づけによる液晶ディスプレイの総合画質向上に関する研究. 照明学会誌, pp. 991-1003.
岡野幸夫, 塩谷望. (2001, 5 24). 液晶ディスプレイパネルの色再現特性とその標準色再現.
奥村英一郎、橋本憲幸. (2018). 医用LCD モニタの色温度におけるカラースケールテストパターンの色度変化. 日本放射線技術学会雑誌, pp. 546-555.