• Journal of Information Technology Applications and Management
• /
• 제25권2호
• /
• 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%.

• 소성∙가공
• /
• 제11권7호
• /
• pp.620-627
• /
• 2002

The purpose of this paper is the development of an automated measurement system for micro spring based on the digital image processing technique. This micro spring can be used in various engineering applications such as filament, load bearing springs, hard disk suspension and many others. Main functionality of the micro spring inspection system is to measure the representative pitch of the micro spring. The derivative operators are used for edge detection in gray level image. Measurement system developed in this paper consisted of new auto feeding mechanism to take advantage of air pressure. In the process of development of the micro spring inspection system based on the image processing and analysis, strong background technology and know-how have been accumulated to measure micro mechanical parts.

• 대한임베디드공학회논문지
• /
• 제16권1호
• /
• pp.17-27
• /
• 2021

In this paper, we develop a galaxy image classification method based on hand-crafted features and machine learning techniques. Additionally, we provide an empirical analysis to reveal which combination of the techniques is effective for galaxy image classification. To achieve this, we developed a framework which consists of four modules such as preprocessing, feature extraction, feature post-processing, and classification. Finally, we found that the best technique for galaxy image classification is a method to use a median filter, ORB vector features and a voting classifier based on RBF SVM, random forest and logistic regression. The final method is efficient so we believe that it is applicable to embedded environments.

• 유통과학연구
• /
• 제12권10호
• /
• pp.67-74
• /
• 2014

Purpose - This study analyzed how image affects customer trust and satisfaction in the online shopping mall market, which is becoming more competitive; future implications for customer management in online shopping malls were presented. Consumers visit and prefer a few shopping mall sites instead of many sites. Consumers do not visit sites that cannot provide trust and satisfaction. Therefore, establishing trust and satisfaction with differentiated image is essential for survival and growth. Specifically analyzing company image, shop image, and brand image, I studied how symbolic image, functional image, and empirical image affect satisfaction mediated by trust in the online shopping malls of hypermarket retailers. Research design, data, and methodology - To investigate the relationship between image and satisfaction of big box retailers' shopping malls in the online market, the study is based on analyzed data from questionnaires involving advanced research. From May 1st to 20th in the year 2014, a questionnaire survey targeting university students using big box retailers' shopping malls in Seoul was conducted. A total of 282 questionnaires were conducted, and 276 questionnaires were used for empirical analysis, excluding invalid data. Using the SPSS 21.0 statistics package, factor analysis and regression analysis were implemented, and effects of image on trust and satisfaction were presented. Results - First, symbolic image can affect satisfaction with only trust. Among 3 image factors, symbolic image exerts the most influence on trust; trust is important in coupling the medium to satisfaction. Second, functional image and empirical image affect satisfaction directly and indirectly with trust. Conclusions - As I classified the image of hyper market retailers' online shopping malls into symbolic, functional, and empirical image, I analyzed the effects of image on trust and satisfaction empirically. The results of the study and strategic implications are as follows. First, symbolic image can affect satisfaction with only trust. Among 3 image factors, symbolic image exerts the most influence on trust; trust is important in coupling the medium to satisfaction. The establishment of a distinctive symbolic image, such as the online shopping mall's loyalty, level of awareness, and special service, is needed. With the establishment of symbolic image, trust and satisfaction could be improved. Second, functional image and empirical image affect satisfaction directly and indirectly with trust. Especially, as functional image affects trust more than empirical image, setting and implementing a strategy for empirical image based on the right price, service, and convenience could raise trust and satisfaction. Empirical image affects trust and satisfaction substantially. Even though empirical image's influence on trust is lower than that of other three image factors, empirical image's influence on satisfaction is higher than symbolic image. Therefore, it requires a strategy for providing joyful use, and information research functions and distinctive use experience are important to improve satisfaction. This study analyzed image characteristics of hyper-market retailers' online shopping malls in the fast-growing online market; future strategic implications were presented.

• 정보처리학회논문지:컴퓨터 및 통신 시스템
• /
• 제5권9호
• /
• pp.237-246
• /
• 2016

DIBR (Depth Image Based Rendering)은 동일 시점의 색상 영상과 깊이 영상을 참조해서 임의 개수의 중간 시점 영상을 생성하는 기법으로 무안경식 다시점 입체 디스플레이를 위한 콘텐츠 제작에 활용할 수 있다. 본 연구에서는 DIBR 기법을 사용해서 생성되는 다시점 중간 영상의 객관적 품질에 깊이 정확도가 미치는 영향에 대해 설명한다. 본 연구는 먼저 사람이 인지할 수 없는 범위에서 왜곡을 보장하기 위한 최소 깊이 양자화 계수를 도출한다. 그리고 장면 구성의 특성에 따라 같은 양자화 수준에서 깊이 정보의 정확도를 효과적으로 표현하기 위한 비균등 영역분할 양자화 방법을 선형 양자화와 비교 분석한 결과를 제시한다.

• 한국실내디자인학회논문집
• /
• 제19권5호
• /
• pp.105-112
• /
• 2010

The purpose of this study is to suggest the color scheme based on the color image types through the color analysis of workstation furniture which is on the market. This color scheme of the workstation furniture is expected to be give the comfort to office environment when planning office. For this study, It is selected the three furniture firms that have a brand of office furniture and their web site that is showed color sample of furniture. The following researches are drawn based upon the purpose. First, the color image types of interior space is classified and the color image words that are suitable for each types is extracted based on the results of existing literature. Second, the distribution of its hue and tone is analysed after collecting the each firm's color sample of desk top, panel and chair. Third, the color image appearing in each furniture color is analysed by color image scale positioning. Forth, the color scheme of desk top, panel and chair is suggested by its color scheme palette. The result of this study is expected to help comfortable environment by providing the color scheme for selection of furniture color in work space. Not all color of each furniture is sufficient to be combined color scheme, the result is indicated that the color scheme of workstation by color image types is possible for color planning in office environment.

• 한국환경과학회지
• /
• 제24권11호
• /
• pp.1451-1461
• /
• 2015

The purpose of this study is to describe how nature-based ecotourism motivation of ecotourists influences destination image and satisfaction of ecotourists. In order to achieve the above purposes, the study carried out a literature study and an empirical analysis. Based on the obtained data through the literature study, the study designed a model for the empirical study. The results of this study are as follows. First, returns to nature, knowledge. fitness and escape as ecotourism motivation of ecotourist had a positive effect on each ecotourism destination image, such as cognitive and affective image. However, effect of novelty on cognitive image for destination had not significant results. Second, ecotourism destination image, such as cognitive and affective image, had a positive effect on ecotourism satisfaction of ecotourists. The results of the article provide implications for strategies for promoting ecotourism destination and suggest some guidelines for the eco-education of tourists.

• Journal of Information Processing Systems
• /
• 제11권4호
• /
• pp.601-615
• /
• 2015

Region of interest (ROI) is the most informative part of a medical image and mostly has been used as a major part of watermark. Various shapes ROIs selection have been reported in region-based watermarking techniques. In region-based watermarking schemes an image region of non-interest (RONI) is the second important part of the image and is used mostly for watermark encapsulation. In online healthcare systems the ROI wrong selection by missing some important portions of the image to be part of ROI can create problem at the destination. This paper discusses the complete medical image availability in original at destination using the whole image as a watermark for authentication, tamper localization and lossless recovery (WITALLOR). The WITALLOR watermarking scheme ensures the complete image security without of ROI selection at the source point as compared to the other region-based watermarking techniques. The complete image is compressed using the Lempel-Ziv-Welch (LZW) lossless compression technique to get the watermark in reduced number of bits. Bits reduction occurs to a number that can be completely encapsulated into image. The watermark is randomly encapsulated at the least significant bits (LSBs) of the image without caring of the ROI and RONI to keep the image perceptual degradation negligible. After communication, the watermark is retrieved, decompressed and used for authentication of the whole image, tamper detection, localization and lossless recovery. WITALLOR scheme is capable of any number of tampers detection and recovery at any part of the image. The complete authentic image gives the opportunity to conduct an image based analysis of medical problem without restriction to a fixed ROI.

• 센서학회지
• /
• 제29권2호
• /
• pp.133-140
• /
• 2020

This study proposes a method of blending visible and near infrared images to enhance edge details and local contrast. The proposed method consists of radiance map generation and color compensation. The radiance map is produced by a Laplacian pyramid and a soft mixing method based on principal component analysis. The color compensation method uses the ratio between the composed radiance map and the luminance channel of a visible image to preserve the visible image chrominance. The proposed method has better edge details compared to a conventional visible and NIR image blending method.

• Journal of Mechanical Science and Technology
• /
• 제16권12호
• /
• pp.1627-1632
• /
• 2002

In this paper, a simplified ultrasonic CT system, which uses the information in three directions, that is, 90°, ＋45° and －45°about the inspection plane, is applied to the high strength steel, and the frequency analysis method for enhancing the C scan or CT image is developed. This frequency analysis method is based on the frequency response property of the material. By comparing the magnitudes in the frequency domain, the special frequency which shows a significant difference between the welded joint and base material was found and used to obtain a C scan or CT image. Experimental results for several kinds of specimens, having a welded joint by electron beam welding, a weld joint by arc welding, on a fatigue crack, showed that the obtained C scan or CT image has better resolution than the results of previous experiments using the maximum value of the received waveform.