CID2013: A Database for Evaluating No-Reference Image Quality Assessment Algorithms

Abstract

This paper presents a new database, CID2013, to address the issue of using no-reference (NR) image quality assessment algorithms on images with multiple distortions. Current NR algorithms struggle to handle images with many concurrent distortion types, such as real photographic images captured by different digital cameras. The database consists of six image sets; on average, 30 subjects have evaluated 12-14 devices depicting eight different scenes for a total of 79 different cameras, 480 images, and 188 subjects (67% female). The subjective evaluation method was a hybrid absolute category rating-pair comparison developed for the study and presented in this paper. This method utilizes a slideshow of all images within a scene to allow the test images to work as references to each other. In addition to mean opinion score value, the images are also rated using sharpness, graininess, lightness, and color saturation scales. The CID2013 database contains images used in the experiments with the full subjective data plus extensive background information from the subjects. The database is made freely available for the research community.

Objective Consumer Device Photo Quality Evaluation

“…We test our approach and compare it with existing state-ofthe-art no-reference IQA approaches on the recently published CID2013 database [13]. This database consists of images captured from a multitude of devices.…”

“…Towards addressing these challenges, we developed a consumer-centric approach to quality assessment and tested it on a newly designed database of photographs collected from consumer devices [13]. This database does not contain simulated distortions.…”

Improving the Performance of No-Reference Image Quality Assessment Algorithm for Contrast-Distorted Images Using Natural Scene Statistics

“…2-Getting the probability distribution function (pdf) of these features. 3-The implementation was conducted over three public databases CID2013 [27], [17], TID2013 [28] and CSIQ [29]. 4-The regression method used was Support Vector Regression (SVR) with cross-validation for k = 2 to 10.…”

Toward a No-Reference Image Quality Assessment Using Statistics of Perceptual Color Descriptors

“…We incorporate four publicly available databases in Table V to evaluate the performance of the proposed metric, e.g., TID2013 DB [19], LIVE DB [45], CSIQ DB [46] and CID2013 DB [47]. They provide a comprehensive ground for evaluation as they contain diversifying visual scenes and distortion types.…”

“…In particular, the TID2013 DB is useful for our analysis as it contains a balanced mixture of chromatic and achromatic distortion types. The recently introduced CID2013 DB [47] provides the images of eight types of scenes captured by different digital devices (ranging from low to high quality cameras, including mobile phones, compact cameras, and SLR cameras); thus, it offers photographs of more real-world scenarios with many concurrent distortion sources. In order to evaluate whether a metric is statistically consistent with visual perception, predicted metric scores are compared with subjective ratings using three evaluation criteria suggested by the Video Quality Experts Group (VQEG) [48]: i) Pearson Linear Correlation Coefficient (PLCC), ii) Spearman Rank-order Correlation Coefficient (SRCC) and iii) Root Mean Squared Error (RMSE).…”