Color image database TID2013: Peculiarities and preliminary results

By Nikolay N. Ponomarenko, Oleg Ieremeiev, Vladimir Vasilyevich Lukin, Karen O. Egiazarian, Lina Jin, Jaakko T. Astola, Benoit Vozel, Kacem Chehdi, Marco Carli, Federica Battisti and 1 more. European Workshop on Visual Information Processing, 2013

568 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/4856ba68a6728fee2855077f06c0a85998e989af

How researchers see this paper

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

1. Kede Ma
2. Weixia Zhang
3. Guangtao Zhai
4. Ke Gu
5. Chaofeng Chen
6. Haoning Wu
7. Weisi Lin
8. Zhengzhong Tu

Citations in the corpus

• MCL-JCV: A JND-based H.264/AVC video quality assessment dataset (2016, background): “Clearly, this phenomenon depends on the visual content as well as the test individual.”
• A Feature-Enriched Completely Blind Image Quality Evaluator (2015, unknown): “1. from the TID2013 dataset [32].”
• NIMA: Neural Image Assessment (2017, methodology): “A few images from TID2013 are illustrated in Fig.”
• A Patch-Structure Representation Method for Quality Assessment of Contrast Changed Images (2015, methodology): “Experimental results show that the proposed PCQI method is well correlated with subjective evaluations of image quality, suggesting that the proposed model is promising at handling contrast changed images.”
• From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality (2019, methodology): “…deep NR models [42, 43, 44, 45, 46] have also been created that yield state-of-the-art performance on legacy synthetic distortion databases [24, 25, 26, 41], e.g., by pretraining deep nets [47, 48, 49] on ImageNet [50], then fine tuning, or by training on proxy labels generated by an FR model [45].”
• Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment (2016, methodology): “In [29] the distortions of the TID2013 dataset are divided into the groups Noise , Actual , Simple , Exotic , New and Color .”
• Image database TID 2013 : Peculiarities , results and perspectives (2016, background): “The main purpose of TID2008 was the analysis and verification of full-reference metrics [15] [17].”
• No-Reference Quality Assessment of Contrast-Distorted Images Based on Natural Scene Statistics (2015, methodology): “We use three databases to validate the performance of the proposed NR-CDIQA metric: CID2013 [16], TID2013 [17], and CSIQ [18].”
• TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment (2023, methodology): “1: An example from the TID2013 dataset [1] (the reference image is omitted for easier comparison).”
• Blind Image Quality Assessment Based on High Order Statistics Aggregation (2016, methodology): “Except for the commonly-used LIVE database [47], TID2013 database [48], CSIQ database [42], Toyama database [49] and LIVE multiply distorted database (MLIVE) [50], we also tested on one new screen image quality assessment database (SIQAD) [51], to show the generalization ability of the proposed meth”
• Massive Online Crowdsourced Study of Subjective and Objective Picture Quality (2015, methodology): “TID2013 [19] is a very recently introduced image quality database with an end goal to include the peculiarities of color distortions in addition to the 17 simulated spatial distortions included in TID2008.”
• Blindly Assess Image Quality in the Wild Guided by a Self-Adaptive Hyper Network (2020, methodology): “Existing synthetic IQA databases LIVE [34], TID2013 [32] and CSIQ [21] only include no more than 30 reference images as limited in the sense of image contents, while authentic IQA database LIVE Challenge [8] and KonIQ-10k [13] consists of 1169 and 10073 images containing differ- ent contents respect”
• Perceptual quality prediction on authentically distorted images using a bag of features approach (2016, methodology): “…designed, trained, and evaluated on benchmark human opinion databases such as the LIVE Image Quality Database (Sheikh, Sabir, & Bovik, 2006), the TID Databases (Ponomarenko et al., 2009, 2013), the CSIQ Database (Larson & Chandler, 2010), and a few other small databases (Callet & Autrusseau, 2005).”
• RankIQA: Learning from Rankings for No-Reference Image Quality Assessment (2017, background): “We perform experiments on the TID2013 and LIVE dataset.5 Evaluation on TID2013.”
• UGC-VQA: Benchmarking Blind Video Quality Assessment for User Generated Content (2020, background): “Several authors report SOTA performance on legacy synthetic distortion databases [68], [69] or on naturally distorted data-”