Toward an automatic subjective image quality assessment system

Abstract

Usually in the field of image quality assessment the terms "automatic" and "subjective" are often incompatible. In fact, when it comes to image quality assessment, we have mostly two kinds of evaluation techniques: subjective evaluation and objective evaluation. Only objective evaluation techniques being automatizable, while subjective evaluation techniques are performed by a series of visual assessment done by expert or non-expert observers. In this paper, we will present a first attempt to an automatic subjective quality assessment system. The system computes some perception correlated color metrics from a learning set of images. During the learning stage a subjective assessment by users is required so that the system matches the subjective opinions with computed metrics on a variety of images. Once the learning process is over, the system operates in an automatic mode using only the learned knowledge and the reference free computed metrics from the images to assess. Results and also future prospects of this work are presented. CONTEXTWhen it comes to image quality assessment, we have mostly two kinds of evaluation techniques [20] : subjective evaluation and objective evaluation. These evaluations can be done with a priori information (with reference) or without use of a priori information (reference free). Subjective approaches, which to date are the only widely recognized method of determining actual perceived quality, are complex and time-consuming, both in their preparation and execution [21]. Subjective evaluation is formalized with defined procedures [20]. Objective quality evaluation use metrics to evaluate image quality. Objective evaluation is automated, hence it costs less than a subjective evaluation, plus it can be done in real-time since it needs no user interaction. Objective quality metrics can be full reference, reduced reference or reference free [21] Moreover, automatic objective assessment systems do not necessarily correlate well with perceived quality [20,21]. Ideally, a quality assessment system would perceive and measure image or video impairments just like a human being. As long as quality metrics are not correlated with human perception, subjective evaluation is still mandatory. This explains why in some domains such as photography and old film restoration, where there is no reference to compare to, subjective quality evaluation is the most reliable technique used. In the last works we presented some original reference free metrics [22][23][24][25] that correlated well with human perception (metrics for contrast and color quality based on statistical and perceptual approaches). These perception correlated metrics were a first step to bridge the gap between subjective and automatic approaches. In fact, since perceptual correlated metrics are available, automatic computation and learning -and hence automatic assessment-become possible.In this paper, we will present a first attempt to an automatic subjective quality assessment system. The system computes some perception correlated color me...

Full reference image quality metrics for JPEG compressed images

“…Therefore, it become imperative to develop a quality assessment method that can evaluate perceptual image quality as good as human subjective evaluation. This necessitates the development of objective IQA approaches that can automatically predict perceived JPEG-compressed image quality [1][2][3][4][5].…”

No-reference lightweight estimation of 3D video objective quality

“…at sender-side) to achieve increased resilience in coded streams. In recent years, image and video quality evaluation methods based on neural networks were also proposed to estimate video quality in [8] and more recently in [9,10]. The authors in [8] use a convolutional neural network to estimate objective and subjective quality of MPEG-2 video based on several features extracted from frames.…”

“…The purpose of the method is to assess the distortion produced by coding artifacts. In [9], 978-1-4799-5751-4/14/$31.00 ©2014 IEEE a neural network is proposed to compute the subjective quality of 2D images from color metrics and in [10] the authors propose an approach based on neural networks to estimate the quality of 3D images using FR and NR methods. While previous methods were proposed for stereo video, this work proposes a lightweight method based on ANN for NR quality estimation of video synthesized from 3D video-plus-depth streams with impaired depth information.…”

3D image quality estimation (ANN) based on depth/disparity and 2D metrics

“…While some researchers use polynomial models [9] [10] for mapping different objective metrics on image quality perception, others use dedicated learning process with artificial neural network (ANN) [11][12][13][14][15]. There are different proposed types of ANN used for image and video quality assessment relaying on objective quality metrics.…”

“…Kukolj in [13] proposed new tenet, with aim to obtain most relevant input features from wide set of inputs and use those inputs for designing Modular Neural Network (MNN). MLP network configuration is frequently used, with fullreference approach in some papers [12] or no-reference approach used in [14] [15].…”