Earticle

In order to improve the edge segmentation effect of the level set image segmentation and avoid the influence of the initial contour on the level set method, a saliency level set image segmentation model based on local Renyi entropy is proposed. Firstly, the saliency map of the original image is extracted by using saliency detection algorithm. And the outline of the saliency map can be used to initialize the level set. Secondly, the local energy and edge energy of the image are obtained by using local Renyi entropy and Canny operator respectively. At the same time, new adaptive weight coefficient and boundary indication function are constructed. Finally, the local binary fitting energy model (LBF) as an external energy term is introduced. In this paper, the contrast experiments are implemented in different image database. The robustness of the proposed model for segmentation of images with intensity inhomogeneity and complicated edges is verified.

Image compression is an essential technique for saving time and storage space for the gigantic amount of data generated by images. This paper introduces an adaptive source-mapping scheme that greatly improves bit-level lossless grayscale image compression. In the proposed mapping scheme, the frequency of occurrence of each symbol in the original image is computed. According to their corresponding frequencies, these symbols are sorted in descending order. Based on this order, each symbol is replaced by an 8-bit weighted fixed-length code. This replacement will generate an equivalent binary source with an increased length of successive identical symbols (0s or 1s). Different experiments using Lempel-Ziv lossless image compression algorithms have been conducted on the generated binary source. Results show that the newly proposed mapping scheme achieves some dramatic improvements in regards to compression ratios.

Recently, there has been an increase in the number of hazardous events, such as fire accidents. Monitoring systems that rely on human resources depend on people; hence, the performance of the system can be degraded when human operators are fatigued or tensed. It is easy to use fire alarm boxes; however, these are frequently activated by external factors such as temperature and humidity. We propose an approach to fire detection using an image processing technique. In this paper, we propose a fire detection method using multichannel information and gray level co-occurrence matrix (GLCM) image features. Multi-channels consist of RGB, YCbCr, and HSV color spaces. The flame color and smoke texture information are used to detect the flames and smoke, respectively. The experimental results show that the proposed method performs better than the previous method in terms of accuracy of fire detection.

Level set methods are the numerical techniques for tracking interfaces and shapes. They have been successfully used in image segmentation. A new variational level set evolving algorithm without re-initialization is presented in this paper. It consists of an internal energy term that penalizes deviations of the level set function from a signed distance function, and an external energy term that drives the motion of the zero level set toward the desired image feature. This algorithm can be easily implemented using a simple finite difference scheme. Meanwhile, not only can the initial contour can be shown anywhere in the image, but the interior contours can also be automatically detected.

의료 정보의 상호운용성 향상을 위해서 Health level 7은 의료 정보 교환을 위한 차세대 체계인 Fast health interoperability resource (FHIR)를 개발하였다. 그러나, 이를 이용하여 임상 정보를 포함한 3차원 의료 영상을 교환 하려는 시도는 없어 새로운 방법을 제시하고자 한다. CT 영상에서 만들어진 3차원 의료 영상을 javascript object notation (JSON) 형식으로 전환하고, 임상 정보를 추가하였다. 우리는 시험용 FHIR 서버를 만들고, 클라이언트는 postman을 사용하였다. 생성된 JSON 파일은 body에 첨부하여 전송되었다. JSON 형식으로 전송된 3차원 의료 영상 은 웹 브라우저를 통해서 볼 수 있었고, 원시 코드를 확인하여 동봉된 임상 정보를 볼 수 있었다. 우리는 3차원 의료 영상 교환을 최초로 시행하였다. 이 방법을 적용한 앱이나 FHIR 리소스 개발을 위해 추가적인 연구가 필요할 것이다.

For improving interoperability of medical information, health level 7 has initiated the development of a next-generation framework for the exchange of medical information called the Fast health interoperability resources (FHIR). However, there was no attempt to exchange the medical three-dimensional (3D) image with clinical data via FHIR. Thus, we designed a new method. The 3D image to be made from computed tomography was converted to the javascript object notation (JSON) file format, and clinical data was added. We made a test FHIR server, and the client used the postman. The JSON file was attached to the body, and was then transmitted. The transmitted 3D image could be seen through a web browser, and attached clinical data was identified in the source code. This is the first attempt to exchange the medical 3D image. Additional researches will be needed to develop applications or FHIR resources that apply this method.

To measure water levels from remote cites using a narrowband channel, this paper developed a difference image based JPEG communication scheme and a water level measurement scheme using the sparsely sampled images in time domain. In the slave system located in the field, the images are compressed using JPEG after changed to difference images, among which in a period of data collection those showing larger changes are sampled and transmitted. To measure the water level from the images received in the master system which may contain noises caused by various sources, the averaging scheme and Gaussian filter are used to reduce the noise effects and the Y axis profile of an edge image is used to read the water level. Considering the wild condition of the field, a simplified camera calibration scheme is also introduced. The implemented slave system was installed at a river and its performance has been tested with the data collected for a month.

전립선 초음파영상은 전립선암, 전립선비대증, 전립선염을 진단하고 전립선암의 생검과 전립선비대에서 전립선 크기 확인 등을 위해서 사용된다. 전립선비대증은 노인 남성의 가장 흔한 질병 중의 하나이다. 전립선은 주변구역, 중심구역, 이행구역과 전방 섬유근 간질부분 4개 구획으로 나누어진다. 전립선비대증은 조직학적으로 전립선 이행구역에서 결절성 증식을 동반한 요도주위의 진행성 과증식이 특징으로 이 결절로 인한 요도 폐쇄를 야기함에 따라 하부요로 증상을 유발한다. 그러므로 본 연구에서는 정상 전립선 이행구역 영상과 전립선비대 이행구역 영상에 대한 컴퓨터 알고리즘을 이용하여 정량적인 분석을 하였다. GLCM을 적용하여 정상영상 60증례와 전립선비대증영상 60증례을 분석영역($50{\times}50$ 픽셀)으로 설정하고, 각 영상에서 Autocorrelation, Contrast, Cluster Prominence, Entropy, Max Probability, Sum average 6가지 파라미터를 비교하여 분석하였다. 결과적으로 Autocorrelation, Cluster Prominence, Entropy, Sum Average 4개의 파라미터에서는 병변의 질감 검출 효율이 92-98%로 높게 나왔다. 이에 전립선 이행구역의 결절성 증식 변화를 정량적인 영상분석으로 확인 할 수 있었다. 향후 전립선비대증 진단에 있어 2차적인 수단으로 가능할 것으로 기대되며, 다양한 전립선 초음파 영상에 있어 기초 자료가 될 것으로 사료된다.

Prostate ultrasound is used to diagnose prostate cancer, BPH, prostatitis and biopsy of prostate cancer to determine the size of prostate. BPH is one of the common disease in elderly men. Prostate is divided into 4 blocks, peripheral zone, central zone, transition zone, anterior fibromuscular stroma. BPH is histologically transition zone urethra accompanying excessive nodular hyperplasia causes a lower urinary tract symptoms(LUTS) caused by urethral closure as causing the hyperplastic nodule characterized finding progressive ambient. Therefore, in this study normal transition zone image for hyperplasia prostate and normal transition zone image is analyzed quantitatively using a computer algorithm. We applied texture features of GLCM to set normal tissue 60 cases and BPH tissue 60cases setting analysis area $50{\times}50pixels$ which was analyzed by comparing the six parameters for each partial image. Consequently, Disease recognition detection efficiency of Autocorrelation, Cluster prominence, entropy, Sum average, parameter were high as 92~98%.This could be confirmed by quantitative image analysis to nodular hyperplasia change transition zone of the prostate. This is expected secondary means to diagnose BPH and the data base will be considered in various prostate examination.

A more accurate understanding of the irrigation water supply is necessary for efficient agricultural water management. Although we measure water levels in an irrigation canal using ultrasonic water level gauges, some errors occur due to malfunctions or the surrounding environment. This study aims to apply CNN (Convolutional Neural Network) Deep-learning-based image classification and segmentation models to the irrigation canal's CCTV (Closed-Circuit Television) images. The CCTV images were acquired from the irrigation canal of the agricultural reservoir in Cheorwon-gun, Gangwon-do. We used the ResNet-50 model for the image classification model and the U-Net model for the image segmentation model. Using the Natural Breaks algorithm, we divided water level data into 2, 4, and 8 groups for image classification models. The classification models of 2, 4, and 8 groups showed the accuracy of 1.000, 0.987, and 0.634, respectively. The image segmentation model showed a Dice score of 0.998 and predicted water levels showed R² of 0.97 and MAE (Mean Absolute Error) of 0.02 m. The image classification models can be applied to the automatic gate-controller at four divisions of water levels. Also, the image segmentation model results can be applied to the alternative measurement for ultrasonic water gauges. We expect that the results of this study can provide a more scientific and efficient approach for agricultural water management.

This study was conducted using a self boarding questionnaire survey to investigate body image perception, dietary habits and nutrient intakes according to interest level in health of female university students in Masan area (n=302). The subjects were divided into 2 groups according to interest level in health ('High' group, n=101, 'Low' group, n=201). Body image according to BMI was significantly different regardless of interest level in health (p<0.001). The answer percentage indicated that the purpose of weight control is health, regular use of the scale, and regular exercise were significantly higher in the high group (p<0.05). Nutrient knowledge score (p<0.01) and food frequency score (p<0.001) were significantly higher in the high group (p<0.01). There were no significant differences in nutrient intake, but intake, NAR and INQ of vitamin C were significantly higher in the high group (p<0.001). Nutrition knowledge score (p<0.01), food intake frequency score (p<0.01), and INQ and NAR of vitamin C (p<0.01) were positively correlated with the interest level in health. These results will be useful as a basis for the development of effective nutrition education programs in order to increase interest level in health and apply well in real life what have learned through the correct nutrition knowledge.

농업용 저수지는 농업용수 공급에 있어서 매우 중요한 생산기반시설로, 우리나라 농업용수의 60% 정도를 공급하고 있다. 다만, 여러 문제로 인해 농업용수의 효율적인 공급에 어려움이 발생하고 있으며, 효과적인 공급 및 관리 체계 구현을 위한 정확한 실시간 저수위 혹은 저수량 추정이 필요하다. 본 연구에서는 영상정보를 활용한 딥러닝 기반 농업용 저수지 수위 인식 모델을 제안하였다. 개발한 모델은 (1) CCTV 영상정보 자료 수집 및 분석, (2) U-Net 이미지 분할 방법을 통한 입력 자료 생성, 그리고 (3) CNN과 ResNet 모델을 통한 수위 인식 세 단계로 구성된다. 모델은 두 농업용 저수지(G저수지와 M저수지)의 영상자료와 저수위 시계열자료를 활용하여 구현하였다. 적용 결과 이미지 분할 모델의 성능은 매우 우수한 것으로 나타났으며, 수위 인식 모델의 경우 수위 분류 계급구간에 따라 성능이 상이한 것으로 나타났다. 특히 영상자료의 픽셀 변동이 클수록 정확도 80% 이상이 확보 가능한 것으로 확인되었으나, 그렇지 않은 경우, 정확도가 50% 수준인 것으로 나타났다. 본 연구에서 개발한 모델은 향후 이미지 자료가 추가로 확보될 경우, 그 활용도 및 정확도가 더 높아질 것으로 기대한다.

The agricultural reservoir is a critical water supply system in South Korea, providing approximately 60% of the agricultural water demand. However, the reservoir faces several issues that jeopardize its efficient operation and management. To address this issues, we propose a novel deep-learning-based water level recognition model that uses CCTV image data to accurately estimate water levels in agricultural reservoirs. The model consists of three main parts: (1) dataset construction, (2) image segmentation using the U-Net algorithm, and (3) CCTV-based water level recognition using either CNN or ResNet. The model has been applied to two reservoirs G-reservoir and M-reservoir with observed CCTV image and water level time series data. The results show that the performance of the image segmentation model is superior, while the performance of the water level recognition model varies from 50 to 80% depending on water level classification criteria (i.e., classification guideline) and complexity of image data (i.e., variability of the image pixels). The performance of the model can be improved if more numbers of data can be collected.

본 연구는 교육서비스품질, 진로결정관계성, 직업이미지, 진로결정수준과 진로결정자기효능감에 대한 영향 관계를 통 합적으로 구명하기 위하여 수행되었으며 실증분석은 Spss 26.0 및 Process Macro 4.2 통계 프로그램을 활용하였다. 실증분석 결과 첫째, 교육서비스품질과 진로결정관계성이 직업이미지와 진로결정수준에 글로벌지원 요인을 제외하고 유 의한 영향을 미치는 것으로 나타났다. 둘째, 직업이미지는 진로결정수준에 긍정적인 영향 관계가 나타났다. 셋째, 직업이 미지는 교육서비스품질과 진로결정관계성이 진로결정수준에 미치는 영향관계에서 글로벌 지원 변인을 제외하고 매개효과 를 나타났다. 넷째, 진로결정자기효능감의 조절효과를 분석 결과, 교수역량, 교육, 취업지원(교육서비스품질) 및 모델링, 조언(진로결정관계성)의 독립 변인 모형에서 조절효과가 유의하게 나타났다. 이 결과를 토대로 학생들에게 진로결정에 확 신을 줄 수 있는 기초자료를 제공하고, 단순히 취업률향상을 넘어 미래지향적인 교육서비스전략을 제시하고자 대학교 관 계자, 그리고 대학생 및 연구자에게 시사점을 밝힌다.

This study was conducted to comprehensively investigate the relationship between educational service quality, career decision relationship, job image, career decision level, and career decision self-efficacy. As a result of the empirical analysis, first, it was found that the relationship between educational service quality and career decision had a significant effect on job image and career decision level, excluding global support factors. Second, job image had a positive effect on the level of career decision-making. Third, occupational image showed a mediating effect in the relationship between educational service quality and career decision relationship on career decision level, excluding global support variables. Fourth, as a result of analyzing the moderating effect of career decision self-efficacy, the moderating effect was significantly found in the independent variable model of teaching competence, education, employment support (educational service quality), modeling, and advice (career decision relationship). Based on these results, we provide basic data that can give students confidence in their career decisions, and reveal implications for university officials, university students, and researchers in order to present future-oriented educational service strategies beyond simply improving the employment rate.

본 연구는 부적합 브랜드 확장에서 자아일치성과 광고유형이 확장제품에 대한 소비자평가에 어떠한 영향을 미치는 지를 살펴보았다. 부적합 확장의 유형은 온건한 부적합 확장과 높은 부적합 확장으로 조작적 정의를 하였으며, 광고유형은 정교화 광고와 관련성 광고로 조작적 정의하였다. 즉, 부적합 확장(온건한 부적합 확장 vs. 높은 부적합 확장), 광고유형(정교화 광고 vs. 관련성 광고), 자아일치성(낮은 자아일치성 vs. 높은 자아일치성)을 적용하여 2X2X2 집단 간 실험설계를 사용하여 부적합 브랜드 확장에 대한 소비자평가를 측정하였다. 본 연구의 연구결과를 요약하면 다음과 같다. 첫째, 정교화 광고가 관련성 광고보다 확장제품에 대한 소비자평가에 더 호의적인 영향을 미치는 것으로 나타났다. 그리고 자아일치성이 높은 집단이 자아일치성이 낮은 집단보다 확장제품에 대한 소비자평가가 더 호의적인 것으로 나타났다. 둘째, 부적합 확장성과 광고유형 간의 상호작용효과는 유의한 것으로 나타났다. 그리고 자아일치성과 광고유형 간에도 상호작용효과가 유의하게 나타났다. 하지만 부적합 확장과 자아일치성 간에는 상호작용효과가 유의하지 않은 것으로 나타났다. 셋째, 부적합 확장정도와 광고유형과 자아일치성 정도에 따라 확장제품의 3원 상호작용효과를 검증한 결과 자아일치성이 낮으며 온건한 부적합 확장인 경우 정교화 광고가 관련성 광고보다 확장제품에 대한 소비자평가에 긍정적인 영향을 주는 것으로 나타났다. 하지만 자아일치성이 높은 집단은 부적합 확장의 정도와 광고유형이 소비자평가에 유의한 영향을 미치지 못하는 것으로 나타났다.

The purpose of this study is to investigate advertising can influence consumer's evaluation of incongruent brand extensions. In this study extensions were manipulated such that they were moderately incongruent, and highly incongruent extension. And advertisement types were manipulated functional ad and symbolic ad. This paper used a 2X2X2 between subject experiment design on the basis of ad type(functional ad vs. symbolic ad), incongruent extension level(moderately incongruent vs. highly incongruent), self-image congruity level(low vs. high), and then measured consumer's evaluation in incongruent brand extensions. The research findings are as follows: First, consumers perceived the functional ad more favorably evaluated than symbolic ad. In addition high self-image congruity group has more favorably evaluated than low self-image congruity one on consumer evaluation of incongruent extensions. Second, there was significant differences in the interaction effect between incongruent extension and advertising type. In addition, the interaction effect between self-image congruity and advertising type was significant. However, there was no significant interaction effect of incongruent extension level and self-image congruity. And finally, there was significant three-way interaction effect among incongruent extensions, advertising type, self-image congruity. When the self-image congruity level is low, with moderately incongruent extensions, the functional ad has more effective than symbolic ad. However, when self-image congruity is high, there was no significant differences on consumer evaluation on incongruent extensions.

최근 CCTV 카메라와 스마트폰 카메라를 비롯한 각종 상 획득 장치들이 격히 증가하고 있으며, 이들 장치들은 매 순간마다 엄청나게 많은 상 데이터를 생성하고 있다. 이러한 방한 상 데이터를 어떻게 하면 효율으로 활용할 것인가 하는 것이 오늘날 지능형 비디오 시스템에서 가장 큰 문제로 두되고 있다. 이를 한 가장 기본인 단계로 서 비디오 스트림에서 원하는 상 임을 효과으로 찾아내는 것이 요하다. 본 논문에서는 상 특징에 기반하 는 3-단계 Haar 웨이블릿 변환을 사용하는 비디오 쿼리 알고리즘을 제안한다. 웨이블릿 변환이 가지는 계층 구조는 공간 역과 스일링 역에서의 특징을 사용가능하게 한다. 본 논문에서는 입력되는 상의 3-단계 Haar 웨이블릿 특징과 비디오 스트림에서의 각 임의 Haar 웨이블릿 특징과의 정합에 의해 원하는 임을 찾도록 한다. 실험 결과, 제안된 방법이 다른 알고리즘에 비해 정확도에서 약 1~8% 우수한 성능을 보이는 것을 확인하다.

Recently image capturing devices such as CCTV camera and smartphone camera are increasing rapidly, these devices produce a lot of image data in every moment. Using huge image data efficiently is one of the most important and big problem of modern intelligent video system. As a basic fundamental step for an intelligent video system, finding a specific image frame from a video stream is very important. This paper proposes a video query algorithm using 3-level Haar wavelet transform based on image features. Hierarchical structure of wavelet transform can have features in both space domain and scaling domain. In this paper, we can find a specific frame by matching 3-level Haar wavelet transform features of input query image and Haar wavelet features of every frame in the stream. Experimental results ascertain that the proposed algorithm has 1~8% superior performance in querying accuracy to other algorithms.

[목적] 본 연구는 군집별 특성에 따라 골프장 IMC활동이 골프장 이미지, 구매행동에 미치는 영향을 규명하는데 목적이 있다. [방법] 골프 참여자의 참여수준을 구분하기 위한 군집분석과 참여수준의 관여정도를 파악하기 위한 교차분석, 각 요인별 인과관계를 분석하기 위한 다중회귀분석을 실시하였다. [결과] 첫째, 군집 1(저수준)에서는 IMC활동의 하위요인 중 판매촉진과 인적서비스가 좋을수록 골프장 이미지와 구매행동이 높아짐을 알 수 있었고 군집 2(고수준)는 IMC활동의 하위요인 중 인적서비스와 홍보, 이벤트가 좋을수록 골프장 이미지와 구매행동이 높 아짐을 알 수 있었다. [결론] 따라서 골프장산업의 차별화된 서비스와 인적서비스를 중심으로 한 IMC활동에 주력 하여 대처하는 태도가 필요하다.

[Purpose] The purpose of this study is to investigate the effect of golf course IMC activities on golf course image and purchase behavior according to the characteristics of cluster. [Method] The results of this study are as follows. First, the results of the multiple regression analysis were used to analyze the causal relationship between each participant. [Result] First, in the cluster 1 (low level), the image of the golf course and the purchase behavior were found to be higher as the sales promotion and human service were the sub - factors of the IMC activity. The cluster 2 (high level) the better the event, the higher the image of the golf course and the purchasing behavior. [Conclusion] Therefore, it is necessary to focus on IMC activities centering on differentiated services and human services in the golf course industry.

최근에는 증강 현실 기술과 가상 현실 기술이 사용되는 의료 영상 분야에서 Low-end 시스템에 대한 정확한 인체 모델을 시각화하는 것이 중요하다. 모델의 기하구조를 줄이면 원래 모양과 다른 점이 나타나고 그 차이를 오류로 간주한다. 따라서 기하구조를 축소하면서 오류를 최소화해야 한다. 본 연구에서는 CT 나 MRI 등의 단층 영상에서 인체 장기에 해당하는 영역을 분할하여 3 차원 기하학적 모델을 생성함으로써 다중 해상도의 상세 단계 모델의 재구성 방법을 구현했다. 실험에서 가상 현실 플랫폼은 척추 영역을 재구성한 모델의 모양을 검증하기 위해 구축되었다. 가상 현실 플랫폼을 이용하여 3D 인체 모델과 환자 정보를 확인할 수 있다.

In recent years, it is important to visualize an accurate human body model for the low-end system in the medical imaging field where augmented reality technology and virtual reality technology are used. Decreasing the geometry of a model causes a difference from the original shape and considers the difference as an error. So, the error should be minimized while reducing geometry. In this study, the organ areas of a human body in the tomographic images such as CT or MRI is segmented and 3D geometric model is generated, thereby implementing the reconstruction method of multiple resolution level-of-detail model. In the experiment, a virtual reality platform was constructed to verify the shape of the reconstructed model, targeting the spine area. The 3D human body model and patient information can be verified using the virtual reality platform.

Because the single chaotic mapping easily creates security weaknesses in the image encryption algorithm, the security needs to be improved. Aiming at this problem, a bit-level image encryption algorithm based on composite chaotic mapping (CCM-IEA) is proposed. First of all, the algorithm scrambles the plain image on bit level through the Cat mapping for the first time. And then the Henon mapping of two dimensional discrete is used to scramble for the second time. Finally, image diffusion is operated through the one dimensional Logistic mapping, and the data sensitivity is enhanced. The experimental results show that the performance of the CCM-IEA algorithm is better on the histogram, information entropy and correlation analysis. Compared with the single chaotic images encryption algorithm, the CCM-IEA algorithm has the ability to resist the information entropy analysis and correlation analysis. It can be seen that the CCM-IEA algorithm has high safety performance and good encryption effect.

Data fusion aims at synergistic use of information and knowledge from different sources to aid in the overall understanding of a phenomenon. In the domain of remote sensing, where images are acquired by multiple sources or by the same source in multiple acquisition contexts, the data made available by different sources are complementary to each other, proper fusion of the data can bring better and consistent interpretation of the scene. The paper presents application of Kalman filter at pixel-level fusion. The input data collected from Ozone Monitoring Instrument (OMI) on NASA’s Aura satellite is subjected to the proposed algorithm. The performance of the algorithm is evaluated by few well-known image quality metrics.