• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권10호
• /
• 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.

• 한국의류학회지
• /
• 제23권8호
• /
• pp.1119-1130
• /
• 1999

The purpose of this was to investigate the differences in recognition of brand and advertisement image according to the life style segments of adolescents. The subjects selected for the final analysis were 613 female high school students whoe were residents in Seoul Pusan and Taejeon. The statistics used for data analysis were factor analysis one-way ANOVA Duncan's multiple range test paired t-test frequency distribution and percentage by the SPSS program The results of this study were as follows : 1. The life style of adolescents wee classified into five groups : Sports Uninterest group Friend Preference/Fashion Uninterest group Sports Preference/Home Oriented group Fashion Interest group and Confidence group. 2, The brand image and advertisement image recognition didn's correspond in general 3. The brand image and advertisement image recognition were significantly different among five groups of life style. The Confidence group and Friend Preference/ Fashion Uninterest group recognized brand image and advertisement image lower than the other groups.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권10호
• /
• pp.5197-5218
• /
• 2019

Large-scale retrieval algorithm is problem for visual analyses applications, along its research track. In this paper, we propose a high-efficiency region division-based image retrieve approaches, which fuse low-level local color histogram feature and texture feature. A novel image region division is proposed to roughly mimic the location distribution of image color and deal with the color histogram failing to describe spatial information. Furthermore, for optimizing our region division retrieval method, an image descriptor combining local color histogram and Gabor texture features with reduced feature dimensions are developed. Moreover, we propose an extended Canberra distance method for images similarity measure to increase the fault-tolerant ability of the whole large-scale image retrieval. Extensive experimental results on several benchmark image retrieval databases validate the superiority of the proposed approaches over many recently proposed color-histogram-based and texture-feature-based algorithms.

• 대한임베디드공학회논문지
• /
• 제6권1호
• /
• pp.48-54
• /
• 2011

As personal or compact devices with image acquisition functionality are becoming easily available for common users, the voluminous images that need to be managed by image related services or systems demand efficient and effective methods in the perspective of image identification. The objective of image identification is to associate an image with a unique identifier. Moreover, whenever an image identifier needs to be regenerated, the newly generated identifier should be consistent. In this paper, we propose three image identifier generation methods utilizing image features: linear component, luminance area, and combination of both features. The linear component based method exploits the information of distribution of partial lines over an image, while the luminance area based method utilizes the partition of an image into a number of small areas according to the same luminance degree. The third method is proposed in order to take advantage of both former methods. In this paper, we also demonstrate the experimental evaluations for uniqueness and similarity analysis that have shown favorable results.

• 대한방사선기술학회지:방사선기술과학
• /
• 제44권3호
• /
• pp.225-229
• /
• 2021

The digital image such as medical X-ray and nuclear medicine field mainly contains noise distribution. The noise degree in image degrades image quality. That is why, the noise reduction algorithm is efficient for medical image field. In this study, we confirmed effectiveness of application for median modified Wiener filter (MMWF) algorithm for noise reduction in PET/MR image compared with median filter image, which is used as conventional noise redcution algorithm. The Jaszczak PET phantom was used by using 18F solution and filled with NaCl+NiSO4 fluids. In addition, the radioactivity ratio between background and six spheres in the phantom is maintained to 1:8. In order to mimic noise distribution in the image, we applied Gaussian noise using MATLAB software. To evlauate image quality, the contrast to noise ratio (CNR) and coefficient of variation (COV) were used. According to the results, compared with noise image and images with MMWF algorithm, the image with MMWF algorithm is increased approximately 33.2% for CNR result, decreased approximately 79.3% for COV result. In conclusion, we proved usefulness of MMWF algorithm in the PET/MR images.

• 유통과학연구
• /
• 제22권9호
• /
• pp.129-139
• /
• 2024

Purpose: This research aims to examine the impact of social media marketing on buy decisions in Indonesia's B2B market, considering the mediating roles of brand image, perceived quality, and perceived value in relation to interactive flat panel display technology. To better understand technology adoption and distribution, we utilize the innovation diffusion theory. Research Design, Data and Methodology: The Decision-Making Unit of each organization that buy interactive flat panel display technology conducted an empirical survey of 82 participants. The quantitative research design analyzed the data utilizing the PLS-SEM model. outcome: This research reveals that social media marketing significantly impacted perceived quality, brand image, perceived value, and buy decisions. The research also found that perceived quality does not significantly impact buy decisions, but perceived value and brand image significantly impacted buy decisions. This research contributes to understanding the key factorsinfluencing buy decisionsin Indonesia's B2B market. Conclusion: Thisresearch concludesthat B2B consumers in Indonesia are less concerned about product quality but prioritize the value they receive when purchasing interactive display technology. Social media marketing could impacted the distribution of interactive display technology in Indonesia's B2B market by affecting the DMU's purchasing decisions. Brandsshould leverage social media marketing to positively impact theirsuccess.

• 동력기계공학회지
• /
• 제10권4호
• /
• pp.5-10
• /
• 2006

The purpose of this study is to measure the droplet distribution and Sauter mean diameter(SMD) of biodiesel fuel, using the immersion sampling method. This method involves using an optical microscope and a CCD camera, to take an image of the droplets. These images are then measured by using a 'Sigma Scan' processing program. The results of the above experiment are summarized as followed ; (1) There can be as much as a 10% error rate when measuring the diameter of these droplets, using the image processing method and the naked eye. (2) The result of droplet size distribution test, TVO(transesterified vegetable oil) big size droplet distribution were increased at ambient pressure $6kg/cm^2$. (3) When ambient pressure increased $6kg/cm^2$ above, SMD variation of TVO and UVO(used vegetable oil) 30 are small. (4) On Rosin-Rammler analysis, droplets size distribution of UVO(used vegetable oil) 30 uniform more than TVO 20 on ambient pressure $1kg/cm^2$.

• 한국정보통신학회논문지
• /
• 제12권6호
• /
• pp.1064-1069
• /
• 2008

본 논문은 인터프레임 확률분포에 의한 비디오 감시 시스템 설계 구현에 관한 것이다. 시스템은 비디오 분석 알고리즘과 표준 JPEG 압축 알고리즘을 처리하기 위해 고성능 DSP 프로세서 기반으로 구현된다. 비디오 분석은 가중치, 평균, 분산의 3변량정규분포에 의한 인터프레임 확률분포 분석을 이용하여 특정 영역에 물체를 검출하는 알고리즘을 사용한다. 실험 결과, 시스템 처리시간이 D1$(720{\times}480)$ 영상 프레임 당 85ms 소요되었고 초당 12프레임 정도 처리한다. 규칙에 따른 특정영역 물체감시는 움직임 빠르지 않는 물체에 대해 100% 검출되었다.

• 유통과학연구
• /
• 제22권8호
• /
• pp.87-98
• /
• 2024

Purpose: This study aimed to examine the influence of private label cues, including store image, product design, price promotion, and origin image, on consumers repurchase intention by mediating consumption value from a distribution perspective. Additionally, it explored nationality's moderating role in the relationship between consumption value and repurchase intention. Research design, data and methodology: Drawing on the SOR model, data were collected from 246 consumers who had purchased private-label products in the past month. Structural equation modeling analysis was employed to test hypotheses using AMOS and SPSS. Results: Findings revealed that cues significantly impact consumers' perception of consumption value, influencing repurchase intention. Price promotion directly affected repurchase intention, while other cues indirectly influenced it through consumption value mediation. Nationality moderated the relationship between consumption value and repurchase intention, with Korean consumers showing a higher propensity to repurchase than Chinese consumers. Conclusions: Theoretical implications of the study contributed to understanding consumer behavior by confirming the impact of private label cues, elucidating their differential effects on repurchase intention, and integrating theoretical frameworks. Managerial implications underscored the significance of leveraging cues to enhance consumption value perceptions, tailoring marketing strategies to accommodate cultural nuances, and utilizing cues to bolster consumer repurchase intentions, ultimately enhancing distribution channel effectiveness.

• 유통과학연구
• /
• 제18권1호
• /
• pp.15-26
• /
• 2020

Purpose: This study is to analyze the image classification using Convolution Neural Network and Transfer Learning for Jeju Island and to suggest related implications. As the biggest tourist destination in Korea, Jeju Island encounters environmental issues frequently caused by marine debris along the seaside. The ever-increasing volume of plastic waste requires multidirectional management and protection. Research design, data and methodology: In this study, the deep learning CNN algorithm was used to train a number of images from Jeju clean and polluted beaches. In the process of validating and testing pre-processed images, we attempted to explore their applicability to coastal tourism applications through probabilities of classifying images and predicting clean shores. Results: We transformed and augmented 194 small image dataset into 3,880 image data. The results of the pre-trained test set were 85%, 70% and 86%, and then its accuracy has increased through the process. We finally obtained a rapid convergence of 97.73% and 100% (20/20) in the actual training and validation sets. Conclusions: The tested algorithms are expected to implement in applications for tourism service distribution aimed at reducing coastal waste or in CCTVs as a detector or indicator for residents and tourists to protect clean beaches on Jeju Island.