A color intensity invariant low-level feature optimization framework for image quality assessment

Abstract

Image Quality Assessment (IQA) algorithms evaluate the perceptual quality of an image using evaluation scores that assess the similarity or difference between two images. We propose a new low level feature based IQA technique, which applies filter-bank decomposition and center-surround methodology. Differing from existing methods, our model incorporates color intensity adaptation and frequency scaling optimization at each filter-bank level and spatial orientation to extract and enhance perceptually significant features. Our computational model exploits the concept of object detection and encapsulates characteristics proposed in other IQA algorithms in a unified architecture. We also propose a systematic approach to review the evolution of IQA algorithms using unbiased test datasets, instead of looking at individual scores in isolation. Experimental results demonstrate the feasibility of our approach.

On the use of deep learning for blind image quality assessment

“…In this work we have investigated the use of deep learning for distortion-generic blind image quality assessment. We report on different design choices in three different experiments, ranging from the use of features [31] 0.94 0.94 BLIINDS-II [39] 0.92 0.91 NIQE [32] 0.92 0.91 C-DIIVINE [51] 0.95 0.94 FRIQUEE [12,14] 0.95 0.93 ShearletIQM [29] 0.94 0.93 MGMSD [1] 0.97 0.97 Low Level Features [21] 0.95 0.94 Rectifier Neural Network [45] -0.96 Multi-task CNN [20] 0.95 0.95 Shallow CNN [19] 0.95 0.96 DLIQA [16] 0.93 0.93 HOSA [49] 0.95 0.95 CNN-Prewitt [27] 0.97 0.96 CNN-SVR [26] 0.97 0.96 DeepBIQ 0.98 0.97 [31] 0.93 0.91 BLIINDS-II [39] 0.93 0.91 Low Level Features [21] 0.94 0.94 Multi-task CNN [20] 0.93 0.94 HOSA [49] 0.95 0.93 DeepBIQ 0.97 0.96…”

“…DIIVINE [34] 0.90 0.88 BRISQUE [31] 0.93 0.91 BLIINDS-II [39] 0.93 0.91 Low Level Features [21] 0.94 0.94 Multi-task CNN [20] 0.93 0.94 HOSA [49] 0.95 0.93 DeepBIQ 0.97 0.96 [31] 0.93 0.91 BLIINDS-II [39] 0.92 0.90 MGMSD [1] 0.88 0.89 Low Level Features [21] 0.89 0.88 Multi-task CNN [20] 0.90 0.91 Shallow CNN [19] 0.90 0.92 DeepBIQ 0.95 0.95 Table 9 Median LCC and median SROCC across 100 trainval-test random splits of the TID2013.…”

“…The same CNN architecture has been then used to simultaneously estimate image quality and identify the distortion type [20] on a single-type distortion dataset [41]. Kottayil et al [21] used a hybrid approach composed by a shallow CNN architecture followed by a regressor to refine the quality score prediction Features extracted from CNN pre-trained for object and scene recognition tasks, have been shown to provide image representations that are rich and highly effective for various computer vision tasks. This paper investigates their use for multiple generic distortions NR-IQA and their capability to model the complex dependency between image content and subjective image quality [2,46,8].…”

NIMA: Neural Image Assessment

“…Perceptual tuning could be quite expensive and time consuming, especially when human opinion is required. In this section, our proposed models are (a) 6.38 (7.16) (b) 6.24 (6.79) (c) 6 Kim et al [16] 0.80 0.80 ---Moorthy et al [39] 0.89 0.88 ---Mittal et al [40] 0.92 0.89 ---Saad et al [41] 0.91 0.88 ---Kottayil et al [42] 0.89 0.88 ---Xu et al [35] 0.96 0.95 ---Bianco et al [7] 0 used to tune a tone enhancement method [43], and an image denoiser [44]. A more detailed treatment is presented in [23].…”

IE-IQA: Intelligibility Enriched Generalizable No-Reference Image Quality Assessment

“…With the boom of deep learning, convolutional neural networks have been widely applied in IQA. Early attempts utilized relatively shallow networks (Kang et al, 2014 ; Kang et al, 2015 ; Kottayil et al, 2016 ) to extract features for assessing synthetic distortions. Then, deeper networks were utilized to handle more complex distortions (Bosse et al, 2017 ; Kim and Lee, 2017 ; Ma et al, 2017 ; Yan et al, 2019 ; Zhai et al, 2020 ; Zhang J. et al, 2020 ).…”