• Title/Summary/Keyword: Perceptual Image Quality

Search Result 76, Processing Time 0.034 seconds

Optimal Image Quality Assessment based on Distortion Classification and Color Perception

  • Lee, Jee-Yong;Kim, Young-Jin
    • 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.

Perceptual Fusion of Infrared and Visible Image through Variational Multiscale with Guide Filtering

  • Feng, Xin;Hu, Kaiqun
    • Journal of Information Processing Systems
    • /
    • v.15 no.6
    • /
    • pp.1296-1305
    • /
    • 2019
  • To solve the problem of poor noise suppression capability and frequent loss of edge contour and detailed information in current fusion methods, an infrared and visible light image fusion method based on variational multiscale decomposition is proposed. Firstly, the fused images are separately processed through variational multiscale decomposition to obtain texture components and structural components. The method of guided filter is used to carry out the fusion of the texture components of the fused image. In the structural component fusion, a method is proposed to measure the fused weights with phase consistency, sharpness, and brightness comprehensive information. Finally, the texture components of the two images are fused. The structure components are added to obtain the final fused image. The experimental results show that the proposed method displays very good noise robustness, and it also helps realize better fusion quality.

Digital Color Image Watermarking for HVS(Human Visual System) using Daubechies wavelet

  • Park, Jong-Tae;Rhee, Kang-Hyeon
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.8 no.7
    • /
    • pp.1488-1492
    • /
    • 2004
  • The digital signal has been replaced the analog signal in most of every field of multimedia including still image, animation, and audio due to the enormous extension of computer supply and the fast development of computer network. The consumers of information are able to enjoy the abundance of information because of one of the digital signal traits that very easy to regenerate the original data. Because of the trait, however, it is very hard for the producers of information to keep the copyright with the merit of original copy in quality excellency. In this paper, the watermarking technology which inserts a RGB color watermark in color image using the visual characteristics of wavelet coefficient was proposed. As a result, the PSNR value of image was varied depending on perceptual parameter, but we can obtain 32dB as a whole.

Stereoscopic Perception Improvement Using Color and Depth Transformation (컬러 및 깊이 데이터 변환을 이용하는 입체감 향상)

  • Gil, Jong-In;Jang, Seung-Eun;Seo, Joo-Ha;Kim, Man-Bae
    • Journal of Broadcast Engineering
    • /
    • v.16 no.4
    • /
    • pp.584-595
    • /
    • 2011
  • Recently, RGB images and depth maps have been supplied to academic fields. The depth maps are utilized to the generation of stereoscopic images in the diverse formats according to the users' preference. A variety of methods that use depth maps have been introduced so far. One of applications is a medical field. In this area, the improvement of the perceptual quality of 2D medical images has gained much interest. In this paper, we propose a novel scheme that expands the conventional method to 3D stereoscopic image, thereby achieving the perceptual depth quality improvement as well as 3D stereoscopic perception enhancement at the same time. For this, contrast transformation as well as depth darkening are proposed and their performance is validated through the subjective test. Subjective experiments peformed for stereoscopic enhancement as well as visual fatigue validate that the proposed method achieves better 3D perception than the usage of the original stereoscopic image and suggests the limitation in terms of the visual fatigue.

A Novel Method to Evaluate the Emotional Image Quality with CIECAM02

  • Chong, Jong-Ho;Lee, Seung-Bae;Park, Hye-Ryoung;Kim, Sang-Ho;Bae, Jae-Woo;Kim, Hye-Dong;Kim, Hun-Soo
    • 한국정보디스플레이학회:학술대회논문집
    • /
    • 2008.10a
    • /
    • pp.47-50
    • /
    • 2008
  • We propose a new method evaluating the image quality of display devices using the CIECAM02 that is the recently developed CIE color appearance model and provides an extension of the previously recommended CIE color spaces. We develop the evaluation method that quantifies the color reproduction capability, emotional gray scale (gradation), and visual perception contrast (perceptual contrast range) based on the gamut in this model.

  • PDF

The Effect of Consumer's Perceptual Characteristics for PB Products on Relational Continuance Intention: Mediated by Brand Trust and Brand Equity (PB상품에 대한 소비자의 지각특성이 관계지속의도에 미치는 영향: 브랜드신뢰 및 브랜드자산을 매개로 한 정책적 접근)

  • Lim, Chaekwan
    • Journal of Distribution Research
    • /
    • v.17 no.5
    • /
    • pp.85-111
    • /
    • 2012
  • Introduction : The purpose of this study was to examine the relationship between perceptual characteristics of consumers and intent of relational continuance for PB(Private Brand) products in discount stores. This study was conducted as an empirical study based on survey. For the empirical study, factors of PB products as characteristics perceived by consumers such as perceived quality, store image, brand image and perceived value were deduced from preceding studies. The effect of such factors on intent of relational continuance mediated by brand trust and brand equity of PB products was structurally examined. Research Model : Based on theory analysis and hypotheses, constructed a Structural Equation Model(SEM). The research model is shown in Figure 1. Research Method : This paper is based on s qualitative study of selected literature and empirical data. The survey for empirical study was carried out on consumers in Gyeonggi and Busan between January 2012 and May 2012. 300 surveys were distributed and 253 (84.3%) of them were returned. After excluding omissions and insincere responses, 245 surveys (81.6%) were used for final analysis as effective samples. Result : First of all, the Reliability was carried out for instrument used. The lower limit of 0.7 for Cronbach's Alpha as suggested by Hair et al. (1998). And Construct validity was established by carrying out exploratory factor analysis by Varimax rotation for all. Four factor result for the consumer's perceptual characteristics of PB Products, two mediating factors and one dependent factor. All constructs included in research framework have acceptable validity and reliability. Table 1 shows the factor loading, eigen value, explained variance and Cronbach's alpha for each factor. In order to assure validity of constructs, I implemented Confirmatory Factor Analysis (CFA), using AMOS 20.0. In confirmatory factor analysis, researcher can take control over the specification of indicators for each factor by hypothesizing that a specific factor is loaded with the relevant indicators. Moreover, CFA is particularly useful in the validation of scale for the measurement of specific construct. CFA result summarized Table 2 shows that the fit measures of all constructs fulfill the recommended level and loadings are significant. To test causal relationship between constructs in the research model, used AMOS 20.0 that provides a graphic module as method for analysing Structural Equation Modeling. The result of hypothesis test is shown in Table 3. As a result of empirical study, perceived quality, brand image and perceived value as selected attributes for PB products showed significantly positive (+) effect on brand trust and brand equity. Furthermore, brand trust and brand equity showed significantly positive (+) effect on intent of relational continuance. However, store image of discount stores selling the PB products was analyzed to have positive (+) effect on brand trust and no significant effect on brand equity. Discussion : Based on the results of this study, the relationship between overall quality, store image, brand image and value perceived by consumers about PB products and intent of relational continuance was structurally verified as being mediated by brand trust and brand equity. Looking at the results, a strategic approach that maximizes brand trust and equity value for PB products by large discount stores is required on top of basic efforts to improve quality, brand image and value of PB products in order to maximize consumer's intent of relational continuance and to continuously attract repeated purchase of products.

  • PDF

No-reference Image Blur Assessment Based on Multi-scale Spatial Local Features

  • Sun, Chenchen;Cui, Ziguan;Gan, Zongliang;Liu, Feng
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.14 no.10
    • /
    • pp.4060-4079
    • /
    • 2020
  • Blur is an important type of image distortion. How to evaluate the quality of blurred image accurately and efficiently is a research hotspot in the field of image processing in recent years. Inspired by the multi-scale perceptual characteristics of the human visual system (HVS), this paper presents a no-reference image blur/sharpness assessment method based on multi-scale local features in the spatial domain. First, considering various content has different sensitivity to blur distortion, the image is divided into smooth, edge, and texture regions in blocks. Then, the Gaussian scale space of the image is constructed, and the categorized contrast features between the original image and the Gaussian scale space images are calculated to express the blur degree of different image contents. To simulate the impact of viewing distance on blur distortion, the distribution characteristics of local maximum gradient of multi-resolution images were also calculated in the spatial domain. Finally, the image blur assessment model is obtained by fusing all features and learning the mapping from features to quality scores by support vector regression (SVR). Performance of the proposed method is evaluated on four synthetically blurred databases and one real blurred database. The experimental results demonstrate that our method can produce quality scores more consistent with subjective evaluations than other methods, especially for real burred images.

Improved Angle-of-View Measurement Method for Display Devices

  • Lee, Eun-Jung;Chong, Jong-Ho;Yang, Sun-A;Lee, Hun-Jung;Shin, Mi-Ok;Kim, Su-Young;Choi, Dong-Wook;Lee, Seung-Bae;Lee, Han-Yong;Berkeley, Brian H.
    • Journal of Information Display
    • /
    • v.11 no.1
    • /
    • pp.17-20
    • /
    • 2010
  • With the increasing demand for a better FPD image quality, better evaluation metrics and advanced display quality measurement methods are required to meet these needs. There are many measurement methods for evaluating the viewing angle of various display devices, but these methods, which include luminance drop, color shift, and contrast ratio decrease, are imperfect considering that human perception does not completely correlate to them. In this paper, a new method of measuring the perceptual angle of FPDs is proposed, considering human visual perception, which uses the color space of the color appearance model.

Improved Method for Angle-of-View Measurement of Display Devices

  • Lee, Eun-Jung;Chong, Jong-Ho;Yang, Sun-A;Lee, Hun-Jung;Shin, Mi-Ok;Kim, Su-Young;Choi, Dong-Wook;Lee, Seung-Bae;Lee, Han-Yong;Berkeley, Brian H.
    • 한국정보디스플레이학회:학술대회논문집
    • /
    • 2009.10a
    • /
    • pp.979-982
    • /
    • 2009
  • With increasing demand for better FPD image quality, better evaluation metrics and advanced display quality measurement methods are required to meet these needs. There are many measurement methods to evaluate viewing angle of the various different display devices. However, these methods, which include luminance drop, color shift, and contrast ratio decrease, are imperfect considering that human perception does not completely correlate to these methods. In this paper, we propose a new method for measuring perceptual angle of FPDs considering human visual perception, which uses color space of the color appearance model.

  • PDF

An Exploratory Study on Experience of Luxury Brand Virtual Fashion Show (럭셔리 패션 브랜드 가상패션쇼 경험에 대한 탐색적 연구)

  • Hyojo Jung;Eunju Ko
    • Journal of Fashion Business
    • /
    • v.27 no.2
    • /
    • pp.70-87
    • /
    • 2023
  • Today, VR, AR, and MR technologies that travel between real world and virtual world are rapidly developing. These technologies are adopted in luxury fashion brands for virtual fashion shows and runways, virtual retail shops and virtual fitting services. Despite its growth potential and social importance, virtual fashion space has been studies insufficiently. Therefore, this study aimed to examine the consumer experience on the virtual fashion space types, components of virtual fashion space, perceived value, and continuous usage intention. Prada, one of the most active luxury fashion brands in the VR field, was selected as the stimulus for an in-depth interview. Participants experienced virtual fashion show space through VR device (Oculus Quest 2 from Meta) before responding to the questions about their experience. Results showed that material space was more like virtual whereas perceptual space felt like reality. Participants could imagine about more virtual image from material space and more real image from perceptual space elements. Moreover, perceptual space enhanced the immersion, presence, and interactivity compared to material space. Most participants perceived that the virtual fashion show was useful and playful, leading to the continuous usage intention. It implies that improvements for some technical limitation from VR device and virtual contents can provide quality consumer experience in the future. Based on results of this study, fashion companies can establish useful marketing strategies for consumers' immersive and playful experiences when introducing virtual fashion space.