Contextual and Variational Contrast Enhancement

By Turgay Çelik, Tardi Tjahjadi. IEEE Transactions on Image Processing, 2011

510 citations recorded by the source corpus.

This paper proposes an algorithm that enhances the contrast of an input image using interpixel contextual information. The algorithm uses a 2-D histogram of the input image constructed using a mutual relationship between each pixel and its neighboring pixels. A smooth 2-D target histogram is obtained by minimizing the sum of Frobenius norms of the differences from the input histogram and the uniformly distributed histogram. The enhancement is achieved by mapping the diagonal elements of the input histogram to the diagonal elements of the target histogram. Experimental results show that the algorithm produces better or comparable enhanced images than four state-of-the-art algorithms.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/776063114234992a774abd6f8d34632acd72ae36

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Ming-Hsuan Yang
2. Wenhan Yang
3. Ling Shao
4. Jiaying Liu
5. Luc Van Gool
6. Xiaojie Guo
7. Lei Zhang
8. Haibin Ling

In Media Technology

1. Xiaojie Guo
2. Jiayi Ma
3. Ming-Hsuan Yang
4. Yu Li
5. Feng Lu
6. Feifan Lv
7. Radu Timofte
8. Lei Zhang

Citations in the corpus

• An Experiment-Based Review of Low-Light Image Enhancement Methods (2020, methodology): “In [89], the contextual and variational contrast (CVC) enhancement algorithm was proposed; in this algorithm, the two-dimensional histogram and context information model of the input image are used to implement nonlinear data mapping to enhance a weakly lighted image.”
• LIME: Low-Light Image Enhancement via Illumination Map Estimation (2017, background): “The operations of HE, AHE and GC are executed on the V channel of images by first converting it from the RGB colorspace to the HSV one and then converting the processed HSV back to the RGB CVC: 0.55 LDR: 0.33 MF: 0.55 DeHz: 0.88 NPE: 0.66 LIMEE AHE: 0.33 CVC: 0.33 LDR: 0.33 MF: 0.55 DeHz: 0.66 NPE: ”
• Kindling the Darkness: A Practical Low-light Image Enhancer (2019, background): “One technical line, with histogram equalization (HE) [1, 6, 24] and its follow-ups [20, 27] as representatives, tries to map the value range into [0, 1] and balance the histogram of outputs for avoiding the truncation problem.”
• Attention Guided Low-Light Image Enhancement with a Large Scale Low-Light Simulation Dataset (2019, methodology): “[4] propose to analyze and penalize the unnatural visual effects for better visual quality; DHECI [54] introduces and uses the differential gray-level histogram; CVC [9] uses the interpixel contextual information; LDR [46] focuses on the layered difference representation of 2D histogram to try to en”
• MSR-net: Low-light Image Enhancement Using Deep Convolutional Network (2017, background): “For example, contextual and variational contrast enhancement [5] tries to find a histogram mapping to get large gray-level difference.”
• STAR: A Structure and Texture Aware Retinex Model (2019, methodology): “We compare the proposed STAR model with previous competing low-light image enhancement methods, including HE [47], MSRCR [19], Contextual and Variational Contrast (CVC) [48], Naturalness Preserved Enhancement (NPE) [5], LDR [49], SIRE [32], MF [50], WVM [7], LIME [6], and JieP [8].”
• A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement (2017, methodology): “By extending the notion of the histogram, some algorithms take spatial image features into consideration to further improve the performance [3], [6], [7].”
• MBLLEN: Low-Light Image/Video Enhancement Using CNNs (2018, methodology): “…and penalize the unnatural visual effects for better visual quality; DHECI [29] introduces and uses the differential gray-level histogram; CVC [5] uses the interpixel contextual information; LDR [26] focuses on the layered difference representation of 2D histogram to try to enlarge the…”
• A fusion-based enhancing method for weakly illuminated images (2016, methodology): “In this experiment, we use 40 different kinds of weakly illumination images and enhance them using [1,10,16,20,22,23] and our proposed method.”
• Contrast Enhancement Based on Layered Difference Representation of 2D Histograms (2013, methodology): “The layered difference representation (LDR): the transformation function x = [x0, x1, · · · , x255]T and the difference variables dlk’s are shown in a tree-like pyramidal structure.”
• Efficient Contrast Enhancement Using Adaptive Gamma Correction With Weighting Distribution (2013, methodology): “The Contextual and Variational Contrast (CVC) enhancement method is more effective at showing the visual quality of the image, because it directly constructs an a priori probability, which further represents details of the image [17].”
• Beyond Brightening Low-light Images (2021, background): “One technical line, with histogram equalization (HE) (Pisano et al. 1998; Cheng and Shi 2004; Abdullah-Al-Wadud et al. 2007) and its follow-ups (Turgay and Tardi 2011; Lee et al. 2013) as representatives, tries to map the value range into [0, 1] and balance the histogram of outputs for avoiding the…”
• Learning a Simple Low-Light Image Enhancer from Paired Low-Light Instances (2023, background): “The former enhances the contrast of an image by redistributing the luminous intensity on the histogram [3, 14].”
• Learning a Deep Single Image Contrast Enhancer from Multi-Exposure Images (2018, methodology): “histogram-based methods (CVC [5] and AGCWD [6]), Retinex-based methods (NEP [8], SRIE [3] and LIME [1]) and Li’s method [59].”
• Low-Light Image Enhancement via a Deep Hybrid Network (2019, methodology): “Global based HE methods [27]–[30] use the histogram information of the entire input image for the transformation function estimation.”