• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.157-168
• /
• 2016

In image processing and computer vision fields, mean squared error (MSE) has popularly been used as an objective metric in image quality optimization problems due to its desirable mathematical properties such as metricability, differentiability and convexity. However, as known that MSE is not highly correlated with perceived visual quality, much effort has been made to develop new image quality assessment (IQA) metrics having both the desirable mathematical properties aforementioned and high prediction performances for subjective visual quality scores. Although recent IQA metrics having the desirable mathematical properties have shown to give some promising results in prediction performance for visual quality scores, they also have high computation complexities. In order to alleviate this problem, we propose a new fast IQA metric using a simple Laplace operator. Since the Laplace operator used in our IQA metric can not only effectively mimic operations of receptive fields in retina for luminance stimulus but also be simply computed, our IQA metric can yield both very fast processing speed and high prediction performance. In order to verify the effectiveness of the proposed IQA metric, our method is compared to some state-of-the-art IQA metrics. The experimental results showed that the proposed IQA metric has the fastest running speed compared the IQA methods except MSE under comparison. Moreover, our IQA metric achieves the best prediction performance for subjective image quality scores among the state-of-the-art IQA metrics under test.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.827-835
• /
• 2019

In the pooling stage of a full reference image quality assessment (FR-IQA) technique, the global perceived quality for any distorted image is usually measured from the quality of its local image patches. But all the image patches do not have equal contribution when estimating the overall visual quality since the degree of degradation on those patches depends on various considerations i.e., types of the patches, types of the distortions, distortion sensitivities of the patches, saliency score of the patches, etc. As a result, weighted pooling strategy comes into account and different weighting mechanisms are used by the existing FR-IQA methods. This paper performs a thorough analysis and proposes a novel weighting function by considering the luminance adaptation as well as the visual saliency effect to offer more appropriate local weights, which can be adopted in the existing FR-IQA frameworks to improve their prediction accuracy. The extended experimental results show the effectiveness of the proposed weighting function.

• Journal of Multimedia Information System
• /
• v.9 no.2
• /
• pp.75-86
• /
• 2022

The existing image quality assessment (IQA) datasets have a small number of samples. Some methods based on transfer learning or data augmentation cannot make good use of image quality-related features. A No Reference (NR)-IQA method based on multi-task training and quality awareness is proposed. First, single or multiple distortion types and levels are imposed on the original image, and different strategies are used to augment different types of distortion datasets. With the idea of weak supervision, we use the Full Reference (FR)-IQA methods to obtain the pseudo-score label of the generated image. Then, we combine the classification information of the distortion type, level, and the information of the image quality score. The ResNet50 network is trained in the pre-train stage on the augmented dataset to obtain more quality-aware pre-training weights. Finally, the fine-tuning stage training is performed on the target IQA dataset using the quality-aware weights to predicate the final prediction score. Various experiments designed on the synthetic distortions and authentic distortions datasets (LIVE, CSIQ, TID2013, LIVEC, KonIQ-10K) prove that the proposed method can utilize the image quality-related features better than the method using only single-task training. The extracted quality-aware features improve the accuracy of the model.

• Journal of KIISE
• /
• v.44 no.9
• /
• pp.992-1004
• /
• 2017

To assess image quality accurately, an image quality assessment (IQA) metric is required to reflect the human visual system (HVS) properly. In other words, the structure, color, and contrast ratio of the image should be evaluated in consideration of various factors. In addition, as mobile embedded devices such as smartphone become popular, a fast computing speed is important. In this paper, the proposed IQA metric combines color similarity, gradient similarity, and phase similarity synergistically to satisfy the HVS and is designed by using optimized pooling and quantization for fast computation. The proposed IQA metric is compared against existing 13 methods using 4 kinds of evaluation methods. The experimental results show that the proposed IQA metric ranks the first on 3 evaluation methods and the first on the remaining method, next to VSI which is the most remarkable IQA metric. Its computing speed is on average about 20% faster than VSI's. In addition, we find that the proposed IQA metric has a bigger amount of correlation with the HVS than existing IQA metrics.

• Journal of Broadcast Engineering
• /
• v.20 no.6
• /
• pp.818-826
• /
• 2015

Recently, objective image quality assessment (IQA) methods that elaborately reflect the visual quality perception characteristics of human visual system (HVS) have actively been studied. Among those characteristics of HVS, luminance adaptation (LA) effect, indicating that HVS has different sensitivities depending on background luminance values to distortions, has widely been reflected into many existing IQA methods via Weber's law model. In this paper, we firstly reveal that the LA effect based on Weber's law model has inaccurately been reflected into the conventional IQA methods. To solve this problem, we firstly derive a new LA effect-based Local weight Function (LALF) that can elaborately reflect LA effect into IQA methods. We validate the effectiveness of our proposed LALF by applying LALF into SSIM (Structural SIMilarity) and PSNR methods. Experimental results show that the SSIM based on LALF yields remarkable performance improvement of 5% points compared to the original SSIM in terms of Spear rank order correlation coefficient between estimated visual quality values and measured subjective visual quality scores. Moreover, the PSNR (Peak to Signal Noise Ratio) based on LALF yields performance improvement of 2.5% points compared to the original PSNR.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.11a
• /
• pp.81-83
• /
• 2015

객관적 영상 화질 측정(Image Quality Assessment: IQA)방법은 영상 화질 최적화 문제해결을 목적으로 하는 영상 처리 및 컴퓨터 비전 분야에 매우 중요하게 사용된다. 이를 위해, 저복잡도, 고성능 및 좋은 수학적 특성(예를 들어, 척도성(metricability), 미분가능성(differentiability) 및 볼록 성질(convexity))을 모두 만족시키는 객관적 IQA 방법이 활발히 연구되어 왔다. 그러나, 위해 위에서 언급한 좋은 수학적 특성을 가지는 대부분의 객관적 IQA 방법들은 좋은 수학적 특성을 만족시키기 위해 상당한 예측성능의 감소를 초래했다. 본 논문은 위에서 언급한 좋은 수학적 특성을 모두 만족시키면서, 예측 성능이 향상된 새로운 IQA 방법을 제안한다. 인간 시각 체계의 감수영역은 광도 입력에 대해 공간 도메인에서 미분 형태의 응답을 가지므로, 제안 방법은 이러한 시각 체계 응답을 모방하여 기울기 연산자를 도입한다. 제안한 방법에서 도입한 기울기 연산자는 매우 단순하게 설계되어, 계산 복잡도가 매우 낮다. 광범위한 실험 결과, 제안하는 IQA 방법은 기존 수학적 특성이 좋은 IQA 방법들 대비 더 좋은 성능을 보이면서 계산 복잡도 또한 낮았다. 따라서 제안 IQA 방법은 다양한 영상 화질 최적화 문제에 매우 효과적으로 적용될 수 있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.7
• /
• pp.2938-2956
• /
• 2020

Objective image quality assessment (IQA) models have been developed by effective features to imitate the characteristics of human visual system (HVS). Actually, HVS is extremely sensitive to color degradation and complex texture changes. In this paper, we firstly reveal that many existing full reference image quality assessment (FR-IQA) methods can hardly measure the image quality with contrast and masking texture changes. To solve this problem, considering texture masking effect, we proposed a novel FR-IQA method, called Texture and Color Quality Index (TCQI). The proposed method considers both in the masking effect texture and color visual perceptual threshold, which adopts three kinds of features to reflect masking texture, color difference and structural information. Furthermore, random forest (RF) is used to address the drawbacks of existing pooling technologies. Compared with other traditional learning-based tools (support vector regression and neural network), RF can achieve the better prediction performance. Experiments conducted on five large-scale databases demonstrate that our approach is highly consistent with subjective perception, outperforms twelve the state-of-the-art IQA models in terms of prediction accuracy and keeps a moderate computational complexity. The cross database validation also validates our approach achieves the ability to maintain high robustness.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.257-271
• /
• 2016

The Structural SIMilarity (SSIM) index is one of the most widely-used methods for perceptual image quality assessment (IQA). It is based on the principle that the human visual system (HVS) is sensitive to the overall structure of an image. However, it has been reported that indices predicted by SSIM tend to be biased depending on the type of distortion, which increases the deviation from the main regression curve. Consequently, SSIM can result in serious performance degradation. In this study, we investigate the aforementioned phenomenon from a new perspective and review a constant that plays a big role within the SSIM metric but has been overlooked thus far. Through an experimental study on the influence of this constant in evaluating images with SSIM, we are able to propose a new solution that resolves this issue. In the proposed IQA method, we first design a system to classify different types of distortion, and then match an optimal constant to each type. In addition, we supplement the proposed method by adding color perception-based structural information. For a comprehensive assessment, we compare the proposed method with 15 existing IQA methods. The experimental results show that the proposed method is more consistent with the HVS than the other methods.

• Geophysics and Geophysical Exploration
• /
• v.24 no.1
• /
• pp.6-19
• /
• 2021

Subsurface physical properties can be obtained and imaged by seismic exploration, and various algorithms have been developed for this purpose. In this regard, root mean square error (RMSE) has been widely used to quantitatively evaluate the accuracy of the developed algorithms. Although RMSE has the advantage of being numerically simple, it has limitations in assessing structural similarity. To supplement this, full-reference image quality assessment (FR-IQA) techniques, which reflect the human visual system, are being investigated. Therefore, we selected six FR-IQA techniques that could evaluate the obtained physical properties. In this paper, we used the full-waveform inversion, because the algorithm can provide the physical properties. The inversion results were applied to the six selected FR-IQA techniques using three benchmark models. Using salt models, it was confirmed that the inversion results were not satisfactory in some aspects, but the value of RMSE decreased. On the other hand, some FR-IQA techniques could definitely improve the evaluation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.29-32
• /
• 2020

Due to the lack of improper image acquisition process, noise induction is an inevitable step. As a result, objective image quality assessment (IQA) plays an important role in estimating the visual quality of noisy image. Plenty of IQA methods have been proposed including traditional signal processing based methods as well as current deep learning based methods where the later one shows promising performance due to their complex representation ability. The deep learning based methods consists of several convolution layers and down sampling layers for feature extraction and fully connected layers for regression. Usually, the down sampling is performed by using max-pooling layer after each convolutional block. We reveal that this max-pooling causes information loss despite of knowing their importance. Consequently, we propose a better IQA method that replaces the max-pooling layers with strided convolutions to down sample the feature space and since the strided convolution layers have learnable parameters, they preserve optimal features and discard redundant information, thereby improve the prediction accuracy. The experimental results verify the effectiveness of the proposed method.