• Journal of Korea Multimedia Society
• /
• v.18 no.7
• /
• pp.827-833
• /
• 2015

In this paper, we have compared three level set-based active contour (LSAC) methods on inhomogeneous MR image segmentation which is known as an important role of brain diseases to diagnosis and treatment in early. MR image is often occurred a problem with similar intensities and weak boundaries which have been causing many segmentation methods. However, LSAC method could be able to segment the targets such as the level set based on the local image fitting energy, the local binary fitting energy, and local Gaussian distribution fitting energy. Our implemented and tested the subcortical image segmentations were the corpus callosum and hippocampus and finally demonstrated their effectiveness. Consequently, the level set based on local Gaussian distribution fitting energy has obtained the best model to accurate and robust for the subcortical image segmentation.

• Journal of Korea Multimedia Society
• /
• v.19 no.7
• /
• pp.1116-1126
• /
• 2016

Image segmentation is widely used in the pre-processing stage of image analysis and, therefore, the accuracy of image segmentation is important for performance of an image-based analysis system. An efficient image segmentation method is proposed, including a filtering process for super-pixels, improved saliency map information, and a merge process. The proposed algorithm removes areas that are not equal or of small size based on comparison of the area of smoothed superpixels in order to maintain generation of a similar size super pixel area. In addition, application of a bilateral filter to an existing saliency map that represents human visual attention allows improvement of separation between objects and background. Finally, a segmented result is obtained based on the suggested merging process without any prior knowledge or information. Performance of the proposed algorithm is verified experimentally.

• Textile Coloration and Finishing
• /
• v.19 no.2
• /
• pp.24-31
• /
• 2007

This paper addresses factors of line image quality on grain leather printed via inkjet printer. Lines were printed onto coated leather media, and line width, edge blurriness, and edge raggedness were evaluated for line image quality. Various factors influenced to wetting and capillary wicking were studied and found out that wicking through capillary between fibers causes significant feathering on leather surface similar with pulp capillary in copy Paper. Polyurethane and acrylic resin coating resulted good image qualify by reducing capillary wicking. The mixture of polyurethane and acrylic resin applied on grain leather satisfied with both image quality and surface hand. $AllWrite^{TM}$ ink brought best results of image quality, comparing with $VeraPrint^{TM}$ ink and $JetWrite^{TM}$ ink.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.1
• /
• pp.211-227
• /
• 2011

Content Based Image Retrieval (CBIR) is an approach for retrieving similar images from an image database based on automatically-derived image features. The quality of a retrieval system depends on the features used to describe image content. In this paper, we propose an image clustering system that takes a database of images as input and clusters them using k-means clustering algorithm taking into consideration color, texture and shape features. Experimental results show that the combination of the three features brings about higher values of accuracy and precision.

• Journal of Korea Multimedia Society
• /
• v.25 no.9
• /
• pp.1291-1306
• /
• 2022

The dual image-based reversible data hiding scheme embeds secret data into two images to increase the embedding capacity of secret data. The dual image-based reversible data hiding scheme can transmit a lot of secret data. Therefore, various schemes have been proposed until recently. In 2021, Chen and Hong proposed a dual image-based reversible data hiding scheme that embeds a large amount of secret data using a reference matrix, secret data, and bit values. However, in this paper, more secret data can be embedded than Chen and Hong's scheme. To achieve this goal, the proposed scheme generates polynomials and shared values using secret sharing scheme, and embeds secret data using reference matrix and septenary number, and random value. Experimental results show that the proposed scheme can transmit more secret data to the receiver while maintaining the image quality similar to other dual image-based reversible data hiding schemes.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.170-183
• /
• 2024

In producing anamorphic 3D advertisement projects, it is necessary to apply the principles of illusion art to distort the images output to the screen (Image Distortion) so that their display aligns with our visual perception in a real three-dimensional environment. We focuse on the methods of image distortion in the creation of content for anamorphic 3D advertisement screens in this thesis. We propose using Unity 3D's real-time rendering instead of the offline rendering method of compositing method, and employing UV grid mapping to replace the manual correction in Adobe After Effects(AE). The significance of this paper lies in simplifying the image distortion processing workflow in anamorphic 3D projects and optimizing the image distortion creation methods used in compositing method. In outdoor anamorphic 3D advertisement projects, the proposed image distortion creation method demonstrates significant advantages in terms of production time, process simplification, flexibility, and expansion possibilities. Our research provides new perspectives and methods for the creation of anamorphic 3D content, offering theoretical and methodological references for professionals working on similar contents.

• Nutrition Research and Practice
• /
• v.6 no.2
• /
• pp.175-181
• /
• 2012

The widespread pursuit of a thin physique may have a detrimental impact on the wellbeing of preadolescents. The influence of body image distortions on the lifestyles, dieting behaviors, and psychological factors was investigated in 631 fifth and sixth grade children in Kyeonggi-do, Korea. Children were classified into three weight groups (underweight, normal, and overweight) and three perception groups (underestimation, normal, and overestimation). Necessary information was obtained by questionnaire, and each subject's weight status was determined by the Rohrer index calculated from the annual measurement records, which were obtained from the school. According to their current weights, 57.4% of children were normal and 32.2% were overweight or obese, 16.6% of the children overestimated their body weight, and 55.2% had an undistorted body image. Overweight children had desirable lifestyles and dietary habits and presented reasonable weight control behaviors. Compared to those without distortion, the overestimated group had greater interest in weight control ($P$ = 0.003) and dissatisfaction with their body weights ($P$ = 0.011), presented unhealthy reasons to lose weight ($P$ = 0.026), and had higher scores for "feeling sad when comparing own body with others" ($P$ = 0.000) and for "easily getting annoyed and tired" ($P$ = 0.037), even though they had similar obesity indices. More subjects from the overestimation group ($P$ = 0.006) chose drama/movies as their favorite TV programs, suggesting a possible role for the media in body image distortion. These findings suggest that body image distortion can lead preadolescents to develop stress about obesity and unhealthy dieting practices, despite similar obesity indices to those without distorted body images. These results emphasize the importance of having an undistorted body image.

• Journal of the Korean Society of Physical Medicine
• /
• v.8 no.1
• /
• pp.19-27
• /
• 2013

PURPOSE: The purpose of this study is to look into relationship between image of physiotherapist and self-esteem of physiotherapy students and desirable image of physiotherapists offer to establish basic materials. METHODS: The subjects of this study are consist of 603 students of department of Physical therapy university and college in Busan and Kim-hae. Data are collected from June 9 to July 9 in 2011 by structured questionnaires. RESULTS: The result are as follows. 1. at the physiotherapist image score, the highest score question is "Physiotherapist is specialist"(3.45) and the lowest score question is "Physiotherapist is treated samely with doctor"(2.15). 2. at the self-esteem score, the highest score question is "I think that I am at least as valuable as others"(3.37) and the lowest score question is "I can be poorly sometimes"(2.81). 3. at the static results of physiotherapist image score gap by general characteristics, there are significantly different in gender(t=2.27, p=.02), similar profession distinction(t=4.30, p=.00), major satisfaction(t=5.74, p=.00), school system (t=-2.54, p=.01). 4. at the static results of self-esteem score gap by general characteristics, there are significantly different in years (f=5.14, p=.00), gender(t=4.09, p=.00), religion(f=2.87, p=.04), similar profession distinction(t=3.97, p=.00), major satisfaction(t=4.26, p=.00). 5. at the static results of good reputation of physiotherapists increase self-esteem of physiotherapy students score question are significantly different(r=0.53, p=.00). CONCLUSION: Accordingly, these results of this study that there is a very correlation between image of physiotherapist and self-esteem of physiotherapy students. Therefore, good reputation of physiotherapists increase self-esteem of physiotherapy students.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.12
• /
• pp.85-92
• /
• 2018

When using complicated image processing algorithms, we use superpixels to reduce computational complexity. Superpixel segmentation is a method of grouping pixels having similar characteristics into one group. Since superpixel is used as a preprocessing of image processing, it should be generated quickly, and the edge components of the image should be well preserved. In this paper, we propose a method of generating superpixels with a small amount of computation while preserving edge components well. In the proposed method, superpixels of an image are generated by using the existing k-mean method, and similar superpixels among the generated superpixels are merged to make final superpixels. When merging superpixels, the similarity is calculated only for superpixels. Therefore, the amount of computation is maintained small. It is shown by experimental results that the superpixel images produced by the proposed method are conserving edge information of the original image better than those produced by the existing method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.8
• /
• pp.896-902
• /
• 2019

In this paper, we proposed two methods to automatically generate color images similar to existing images using genetic algorithms. Experiments were performed on two different sizes($256{\times}256$, $512{\times}512$) of gray and color images using each of the proposed methods. Experimental results show that there are significant differences in the evolutionary performance of each technique in genetic modeling for image generation. In the results, evolving the whole image into sub-images evolves much more effective than modeling and evolving it into a single gene, and the generated images are much more sophisticated. Therefore, we could find that gene modeling, selection method, crossover method and mutation rate, should be carefully decided in order to generate an image similar to the existing image in the future, or to learn quickly and naturally to generate an image synthesized from different images.