An Underwater Color Image Quality Evaluation Metric

By Miao Yang, Arcot Sowmya. IEEE Transactions on Image Processing, 2015

1,355 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/a18e6b5f23132f52a537e17158f6a14fa8de2e45

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. Chongyi Li
2. Chunle Guo
3. Runmin Cong
4. Wenqi Ren
5. Peixian Zhuang
6. Chunli Zhu
7. Liheng Bian
8. Lintao Peng

In Media Technology

1. Chongyi Li
2. Runmin Cong
3. Peixian Zhuang
4. Chunle Guo
5. Chunli Zhu
6. Liheng Bian
7. Lintao Peng
8. Wenqi Ren

Citations in the corpus

• Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, neutral): “The first image in each line represents the original image, the middle three images represent the segmentation results of FastSCNN, ContextNet and FastICENet respectively, and the last image represents the ground-truth.”
• Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding (2021, methodology): “For Test-C60 and SQUID that do not have corresponding ground truth images, we employ the no-reference evaluation metrics UCIQE [54] and UIQM [55] to measure the performance of different methods.”
• Underwater Image Enhancement Using a Multiscale Dense Generative Adversarial Network (2020, methodology): “To make our results more convincing, we employ two no-reference metrics to evaluate the underwater images, e.g., underwater color image quality evaluation (UCIQE) [39] and underwater image quality measure (UIQM) [40].”
• Color Balance and Fusion for Underwater Image Enhancement (2018, methodology): “Table II provides the associated quantitative evaluation, using three recent metrics: PCQI [64], UCIQE [65], and UIQM [66].”
• Internet of Underwater Things and Big Marine Data Analytics—A Comprehensive Survey (2020, background): “It can also act as a guide for determining the data bandwidth required by the underwater communication algorithms, as well as by other decision-making processes [196].”
• UIEC^2-Net: CNN-based Underwater Image Enhancement Using Two Color Space (2021, methodology): “Meanwhile, we choose underwater color image quality evaluation (UCIQE) [58] and underwater image quality mea-T We set c 1 = 0 .”
• Real-World Underwater Enhancement: Challenges, Benchmarks, and Solutions Under Natural Light (2019, background): “The other one is the underwater color image quality evaluation (UCIQE) [46], which uses a linear combination of the chroma, saturation, and contrast of underwater images in the CIElab color space.”
• U-Shape Transformer for Underwater Image Enhancement (2021, methodology): “For images in the non-reference testing dataset, nonreference evaluation metrics UCIQE [48] and UIQM [34] are employed, in which higher UCIQE or UIQM score suggests better human visual perception.”
• Generalization of the Dark Channel Prior for Single Image Restoration (2018, methodology): “Image restoration methods can involve objective evaluation [32]–[35].”
• Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset (2018, background): “Since it is impossible to obtain medium-free in situ images, comparisons in the existing literature are either based on photos of a color card taken from a short range, e.g. [13], [16], [23], or based on non-reference image quality metrics [42], [43].”
• Underwater Image Enhancement by Dehazing With Minimum Information Loss and Histogram Distribution Prior (2016, positive): “Table IV summarizes the average MSE, PSNR, entropy, PCQI, UCIQE, and PT results on the 500 tested underwater images with a size of 720×1280.”
• Underwater Image Restoration Based on Image Blurriness and Light Absorption (2017, methodology): “2) No-Reference Quality Assessment: One can also objectively evaluate underwater image restoration methods on real images [18]–[20].”
• Underwater Image Enhancement via Weighted Wavelet Visual Perception Fusion (2024, methodology): “…to evaluate the enhancement performance of different methods quantitatively, and they are average gradient (AG) [36], information entropy (IE) [64], edge intensity (EI) [36], underwater color image quality evaluation metric (UCIQE) [66], and colorfulness contrast fog density index (CCF) [67].”
• PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN With Dual-Discriminators (2023, methodology): “In addition, we also use some non-reference metrics for evaluation, including UIQM [63], FDUM [64], UCIQE [65], and CCF [66].”
• Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors (2022, positive): “For the 300 underwater images without the corresponding ground truth images, we employ the four non-reference evaluation metrics UIQM [41], UCIQE [42], PCQI [43], and Entropy [39] to measure the performance of different methods.”
• Enhancement of Underwater Images With Statistical Model of Background Light and Optimization of Transmission Map (2019, background): “quantitative metrics (Entropy (S), the Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) [56], and Underwater color image-quality evaluation (UCIQE) [7]).”