基於快速單張影像處理演算法用於對比度增強與除霧之研究

Contrast Enhancement and Dehazing Based on Fast Single-Image Processing Algorithm

董子嘉(Tzu-Chia Tung)

指導教授 ： 傅楸善

國立臺灣大學/電機資訊學院/資訊網路與多媒體研究所/博士(2022年)

https://doi.org/10.6342/NTU202203179

摘要

近年來對數位影像和多媒體應用的需求不斷增加，其中一個需求就是盡可能地獲取完整的影像動態範圍資訊，即為高動態範圍 (HDR) 成像。另一需求是能夠還原在惡劣天氣條件（如煙、霾、雨、雪等）之下導致品質變差的影像。在本研究中，開發了兩種新穎的方法，分別是影像增強和除霧之影像處理法。第一種影像對比度增強方法是基於誘導範數 (induced norm) 以及局部區塊 (local patch) 實現簡單有效的高動態範圍成像。首先，使用影像局部區塊的誘導範數估計每個像素的照度。其次，提出一種預伽馬 (pre-gamma) 校正，以適當地增強照明量的對比度。伽馬校正的參數是根據影像的局部區塊動態設定。第三，將限制對比度自適應直方圖均衡 (CLAHE) 應用於處理後的影像，以進一步增強影像對比度。第四，開發一種基於局部區塊的雜訊降低演算法，透過降低影像雜訊，提高影像品質。最後，應用後伽馬校正 (post-gamma) 以些微增強影像的暗區域而不影響較亮區域。實驗結果顯示，藉由使用客觀的定量評估，本研究所提出的方法優於幾種最先進的影像品質增強技術。
第二種快速單張影像除霧方法是基於最小通道 (minimum channel) 和無區塊 (patchless) 所實現的，而不是以假設透射率 (scene transmission) 為局部恆定及使用各種濾波器來平滑透射率圖的局部區塊方法。本研究提出一種基於影像最小通道估計大氣光 (atmospheric light) 和透射率的新方法。影像最小通道的直方圖用於提取大氣光像素，並排除影像中非霧的亮像素，再應用直方圖均衡和影像乘法以獲得更好的視覺品質。為了驗證所提出方法的性能，從資料庫 I-HAZE、O-HAZE 和網站中收集 100 張影像。從客觀的定量評估顯示，所提出的方法優於幾種最先進的影像除霧演算法。另一方面，從主觀分析來看，所提出的方法在顏色還原方面明顯優於大多數的影像除霧演算法。此外，時間評估結果表明，我們提出的方法是最先進的影像除霧方法當中最快的，而且比第二快的方法快約 15 倍。本研究的主要貢獻是能夠顯著減少影像處理時間，其原因為所提出的無區塊演算法不需要使用任何濾波器和複雜演算法。除了顯著降低運算處理時間之外，本研究所提出的方法還可以獲得更好的影像視覺品質。

關鍵字

誘導範數 ； 局部區塊 ； 限制對比度自適應直方圖均衡化 ； 最小通道 ； 無區塊 ； 影像乘法

並列摘要

Recently, the requirement for digital photography and multimedia applications has been increasing. One of these requirements is to obtain as much complete image dynamic range information as possible, which is called High Dynamic Range (HDR) imaging. The other of these requirements is to recover poor quality images produced when capturing images in bad weather conditions, such as smoke, haze, rain, snow, and so on. In this study, two novelty approaches are developed for image processing in image enhancement and haze removal respectively. Firstly, a simple and effective Image Contrast Enhancement Based on Induced Norm and local patch approach (ICEBIN) is proposed to achieve high dynamic range imaging. First, the illumination of each pixel is estimated by using an induced norm of a patch of the image. Second, a pre-gamma correction is proposed to enhance the contrast of the illumination component appropriately. The parameters of gamma correction are set dynamically based on the local patch of the image. Third, an automatic Contrast-Limited Adaptive Histogram Equalization (CLAHE) whose clip point is automatically set is applied to the processed image for further image contrast enhancement. Fourth, a noise reduction algorithm based on the local patch is developed to reduce image noise and increase image quality. Finally, a post-gamma correction is applied to slightly enhance the dark regions of images and not affect the brighter areas. Experimental results show that the proposed method has its superiority over several state-of-the-art enhancement quality techniques by using qualitative and quantitative evaluations.
Secondly, instead of using the local patch approach, which assumes the scene transmission to be locally constant and uses various filters to smooth the transmission map, this study proposes a fast single image haze removal method based on the minimum channel and patchless approach (MCPA). A new simple approach to estimate the atmospheric light and the scene transmission is proposed based on the minimum channel of images. The histogram of the minimum channel of the image is used to extract the atmospheric light pixels and exclude the non-hazy bright pixels in the image. The histogram equalization and image multiplication are applied to achieve better visual quality. In order to verify the performance of the proposed method, 100 images are collected from datasets I-HAZE, O-HAZE, and websites. Experimental results show that our proposed method outperforms up-to-date state-of-the-art haze removal algorithms using quantitative evaluations. From subjective comparisons, the proposed method outperforms most current haze removal algorithms in color restoration. Also, time assessment results show that our proposed method is the fastest among the up-to-date state-of-the-art haze removal methods and is about 15 times faster than the second-fastest method. The main contribution of the proposed method is significantly reducing computation time because it uses a patchless approach that does not need any filter and complicated algorithms. In addition to significantly reducing the computational processing speed, our proposed method can achieve better visual quality.

並列關鍵字

Induced norm ； Local patch ； CLAHE ； Minimum channel ； Patchless ； Image multiplication

參考文獻

[1] P. E. Debevec, and J. Malik, “Recovering High Dynamic Range Radiance Maps from Photographs,” in Proceedings of the 24th Annual Conference on Computer Graphics and Interactive Techniques, New York, NY, USA, pp. 369–378, 1997.

[2] T. Mitsunaga, and S. K. Nayar, “Radiometric Self Calibration,” in Proceedings IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Fort Collins, CO, USA, pp. 374-380, 1999.

[3] M. A. Robertson, S. Borman, and R. L. Stevenson, “Estimation-Theoretic Approach to Dynamic Range Enhancement Using Multiple Exposures,” Journal of Electronic Imaging, vol. 12, no. 2, pp. 219-228, 2003.

[4] S. B. Kang, M. Uyttendaele, S. Winder, and R. Szeliski, “High Dynamic Range Video,” Acm Transactions on Graphics, vol. 22, no. 3, pp. 319-325, 2003.

[5] E. Reinhard, W. Heidrich, P. Debevec, S. Pattanaik, G. Ward, and K. Myszkowski, High Dynamic Range Imaging: Acquisition, Display, and Image-Based Lighting, Morgan Kaufmann, Burlington, Massachusetts, 2010, pp. 91-117.