• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.288-307
• /
• 2016

Image distortions are typically characterized by degradations of structures. Dictionaries learned from natural images can capture the underlying structures in images, which are important for image quality assessment (IQA). This paper presents a general-purpose no-reference image quality metric using a GRadient-Induced Dictionary (GRID). A dictionary is first constructed based on gradients of natural images using K-means clustering. Then image features are extracted using the dictionary based on Euclidean-norm coding and max-pooling. A distortion classification model and several distortion-specific quality regression models are trained using the support vector machine (SVM) by combining image features with distortion types and subjective scores, respectively. To evaluate the quality of a test image, the distortion classification model is used to determine the probabilities that the image belongs to different kinds of distortions, while the regression models are used to predict the corresponding distortion-specific quality scores. Finally, an overall quality score is computed as the probability-weighted distortion-specific quality scores. The proposed metric can evaluate image quality accurately and efficiently using a small dictionary. The performance of the proposed method is verified on public image quality databases. Experimental results demonstrate that the proposed metric can generate quality scores highly consistent with human perception, and it outperforms the state-of-the-arts.

• Fashion & Textile Research Journal
• /
• v.17 no.3
• /
• pp.392-404
• /
• 2015

This study investigated how the image exaggeration influence consumer attitude toward product in mobile shopping. Image exaggeration was manipulated by adding light effects on image and adjusting the width for slender mirror effect. Subjects were randomly allocated to four mock-mobile website stimuli. The overall results showed that the image exaggeration had negative effect on product attitude mediated by diagnositicity. First, the mediation effect of diagnositicity between exaggeration and product attitude was tested by bootstap method. The diagnositicity fully mediated between two variables and exaggeration had negative total effect on diagnositicity. The image exaggeration had no direct effect on product attitude. Second, to test the moderating effect of image congruence between the image exaggeration and diagnositicity, conditional indirect effect of diagnositicity was analyzed. As a result, the moderating effect of image congruence was significant. When consumers perceived high self-image congruence with picture image on mobile website, the exaggeration had no negative effect on product attitude. This indicates self-image congruence counteracts the negative effect of the exaggeration on diagositicity. And the moderating effect of image aesthetics between the image exaggeration and product attitude was examinated by the conditional direct effect model. The analysis found that image aesthetics had significant moderating effects particularly on high or low levels of aesthetics. When image aesthetics was perceived as high, image exaggeration had negative effect on product attitude, whereas image aesthetics was low, image exaggeration had positive effect on product attitude. This result indicated that the positive exaggeration effects existed when images were aesthetically appealing.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1998.06a
• /
• pp.33-36
• /
• 1998

Most image restoration problems are ill-posed and need to e regularized. A difficult task in image regularization is to avoid smoothing of image edges. In this paper, were proposed an edge-preserving image restoration algorithm using block-based edge classification. In order to exploit the local image characteristics, we classify image blocks into edge and no-edge blocks. We then apply an adaptive constrained least squares (CLS) algorithm to eliminate noise around the edges. Experimental results demonstrate that the proposed algorithm can preserve image edges during the regularization process.

• Journal of the Ergonomics Society of Korea
• /
• v.9 no.2
• /
• pp.29-35
• /
• 1990

To investigate and analyze of the human brain-wave changes during 3-dimenslonal image load were expected to take not only an important basic information of 3-dimensional TV usage but also 3-dimensional image design. In this experiment, to analyze the difference of visual analyze handing system for which we present the 2- dimensional image having no parallex and 3-dimensional image by visual evoked potentials(VEP). 2-dimensional image and 3-dimensional image displayed on the screen through video. In the test, the time interval was one sec for presentation of stimulus considering united time of visual information of right eye and left eye during watching the 3-dimensional image also display time interval was 200 mesc for each stimulus image. Results are as follow, (1) N190 appears faster 16msec-20msec in the point of Fz, Cz, Pz, Oz when loaded 3D4 angle than 2D3 angle. (2) About of the P300, 3D4 angle(Otherwise, Oz point was reverse) and in the case of no equipment of liquid crystal shutter, there appeared PEAK near the P250. (3) There were 5% significant difference when the liquid crystal shutter was equiped and didn't, Therefore, this phenomenon show the possibility that Liquid crystal shutter influences on Visual Evoked Potentials.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.32 no.3
• /
• pp.505-516
• /
• 2008

Image which appears in fashion illustration on the late twentieth century is not the representative image as an equivalence to the real fashion styles but the virtual image which bears no relation to any reality. The purpose of this study is review the concept of virtuality and analyze in which way virtual image is expressed in fashion illustrations on the background of Jean Baudrillard's simulacre theory. In post-modem paintings the expression methods of image-virtualization were image mixing through photo-image appropriation, image overlapping, and the icons inserted unreasonably, the focus-out effect through scrubbing and the over-painting on the photograph. Image-virtualization in fashion illustration was expressed through image mixing and expression of image uncertainty. Image mixing was made by photo-image appropriation, image overlapping, connection of heterogeneous images and using interface image, and uncertain image was expressed through the expression of visual ambiguity and virtual movement.

• Journal of Broadcast Engineering
• /
• v.13 no.6
• /
• pp.849-858
• /
• 2008

In this paper, a no-reference perceptual metric is proposed for image quality assessment. It measures the amount of overall blockiness and blurring of the image and evaluates the amount of ringing, staircase, and mosaic noises around the strong edges. Finally, the individual scores are combined by a fuzzy integral to generate the final quality score of the image. The quality scores obtained by the proposed algorithm show strong relationship with the MOS(Mean Opinion Score) values by experts.

• Journal of Korean Society for Quality Management
• /
• v.23 no.2
• /
• pp.1-9
• /
• 1995

Two user groups, expert and non-expert, are sampled to measure the image quality of G3 facsimile. A ITU-TS tset chart No. 2 has been transmitted among some selected cities and evaluated by user groups. Their subjective evaluation to the image quality is quantified by Mean Opinion Score method. There is highly significant difference in the image quality between expert and non-expert. From modified logit model, it is concluded that there is no significance in two considered factors, the effects of the number of links and transmission time. The derived percent curves show that 80% of non-experts(90% of expert) is considering the image quality of G3 facsimile "fair, good, or excellent".

• Journal of Information Technology Applications and Management
• /
• v.25 no.2
• /
• pp.41-52
• /
• 2018

This paper presents a method for accurate camera self-calibration based on SIFT Feature Detection and image quality assessment. We performed image quality assessment to select high quality images for the camera self-calibration process. We defined high quality images as those that contain little or no blur, and have maximum contrast among images captured within a short period. The image quality assessment includes blur detection and contrast assessment. Blur detection is based on the statistical analysis of energy and standard deviation of high frequency components of the images using Discrete Cosine Transform. Contrast assessment is based on contrast measurement and selection of the high contrast images among some images captured in a short period. Experimental results show little or no distortion in the perspective view of the images. Thus, the suggested method achieves camera self-calibration accuracy of approximately 93%.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.1
• /
• pp.83-91
• /
• 2019

In this paper, we have effectively used the surface characteristics and local similarity existing in image, solved the problem that there is no CZP(Closest Zero point) that occurs in a very few images to hide secrete data into cover image by using histogram shift. By applying the proposed technique, it is possible to hide secrete data invisibly into the cover image, extract secrete data from the stego-image with no data loss, and completely restore the original cover image. It is impossible to know whether the secrete data is hidden in the stego-image because the stego-image constructed by applying the proposed technique has a good visual quality that can not distinguish the difference from the cover image. The proposed method is able to hide secrete data at various levels compared to conventional APD(Adjacent Pixel Difference) technique, and hide secrete data up to 25.1% more than APD in cover image.

• Journal of the Korean Society of Radiology
• /
• v.13 no.4
• /
• pp.623-628
• /
• 2019

The aim of this study was to design fast non local means (FNLM) noise reduction algorithm and to confirm its application feasibility in light microscopic image. For that aim, we acquired mouse first molar image and compared between previous widely used noise reduction algorithm and our proposed FNLM algorithm in acquired light microscopic image. Contrast to noise ratio, coefficient of variation, and no reference-based evaluation parameter such as natural image quality evaluator (NIQE) and blind/referenceless image spatial quality evaluator (BRISQUE) were used in this study. According to the result, our proposed FNLM noise reduction algorithm can achieve excellent result in all evaluation parameters. In particular, it was confirmed that the NIQE and BRISQUE evaluation parameters for analyzing the overall morphologcal image of the tooth were 1.14 and 1.12 times better than the original image, respectively. In conclusion, we demonstrated the usefulness and feasibility of FNLM noise reduction algorithm in light microscopic image of small animal tooth.