• 조명전기설비학회논문지
• /
• 제24권12호
• /
• pp.122-130
• /
• 2010

This paper presents an active ranging system based on laser structured-light image. The structured-light image processing is computationally efficient in comparison with the conventional stereo image processing, since the burdensome correspondence problem is avoidable. In order to achieve robustness against environmental illumination noise, an efficient image processing algorithm, i.e., integration of difference images with structured-light modulation is proposed. Distance equation from the measured structured light pixel distance and system parameter calibration are addressed in this paper. Experiments and analysis are carried out to verify performance of the proposed ranging system.

• 한국의류학회지
• /
• 제21권5호
• /
• pp.880-888
• /
• 1997

This study was intended to analyze the perception of consumers towards TV commercials of women's clothes and variables influencing the effectiveness of the commercials. The sample consisted of 408 female students attending Ehwa Woman's university and the survey was conducted after the TV commercials were shown to the sample. Frequency, percentage, F-test, logistic regression were used for analysis. Conclusions of the study are as follows, 1. TV commercials were grouped into three image categories, Individuality, Nobility, and Activity. The commercials of the formal clothes were perceived based on nobility factor while the commercials of the casual clothes were perceived based on individuality factor by subjects. 2. Commercial image and the brand image appeared similar in three image factors. And TV commercials were more effective when two images were perceived similar. 3. The expenditures on TV commercial influenced the awareness of commercials, therefore frequent commercial drew more awareness. 4. The models on the commercials were more effective when the image of the commercials and the image of the models were perceived similar by subjects.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 International Symposium on Remote Sensing
• /
• pp.126-129
• /
• 2008

In this paper, we proposed a method extracting an object from background of the satellite image. The image segmentation techniques have been widely studied for the technology to segment image and to synthesis segment object with other images. Proposed algorithm is to perform the edge detection of a selected object using genetic algorithm. We segment region of object based on detection edge using watershed algorithm. We separated background and object in indefinite region using gradual region merge from segment object. And, we make GUI for the application of the proposed algorithm to various tests. To demonstrate the effectiveness of the proposed method, several analysis on the satellite images are performed.

• 패션비즈니스
• /
• 제10권4호
• /
• pp.70-77
• /
• 2006

The purpose of this study is to evaluate the differences of visual image by variations in the location and width of the waist band of the one-piece dress. The stimuli are 24 samples: 8 variations of the location of the waist band and 3 variations of the width of the waist band. The data has been obtained from 50 fashion design majors. The data has analyzed by Factor Analysis, Anova, Scheff's Test and the MCA method. The results of the study are as follows. According to the result of factor analysis of the visual image based on the changes in the location and width of waist bands, three factors were identified- attractiveness, elegance and practicality. Among them, attractiveness was found to be the most important. The visual image was evaluated positively when waist bands were positioned above the natural waist line and negatively when waist bands were positioned below the natural waist line regardless of their width. In addition, the visual image based on the width of waist bands for one-piece dress was the most positive when the width was 4.5cm. No significant difference was observed in the visual image according to band width when the waist bands were positioned below the natural waist line. The interaction of visual image according to the location and width of waist bands for one-piece dress did not appear. As the main effect, significant differences were observed in all of the three factors according to the location of waist bands, but only two factors excluding elegance showed some difference according to the width of waist bands. When multiple classification analysis was applied to the factors without interaction, the location of waist bands appeared to have more significant effect on visual image than the width of waist bands.

• 융합경영연구
• /
• 제6권4호
• /
• pp.1-16
• /
• 2018

Purpose - This study will investigate and identify the relationship between brand image, brand attitude and intent to purchase based on subjects that have remembered or watched more than one storytelling marketing ad related to airlines. The purpose of the project is to secure market competitiveness by presenting the basis for and use of the marketing strategy using storytelling, which can capture the goodwill of the aerospace competition market in the future. Research, design, data, and methodology - Prior to the research model and hypothesis testing phase, a verification factor analysis was conducted to assess internal consistency among each measurement item and to ensure reliability and validity of the measurement tool. Further, the organization was assessed for validity by calculating the mean variance estimation (AVE) and the construction concept reliability (CCR) through a positive factor analysis. Hypothesis verification was analyzed through a structural equation model, and each concept set in the hypothesis was entered as a potential variable, and each measurement item was entered as an observation variable. Results - Airline's storytelling marketing has a significant impact on the brand image and two emotional and cognitive responses have been shown to influence the brand image. In addition, airline storytelling marketing has a significant impact on brand attitudes and airline storytelling marketing derived from factor analysis has shown two emotional and cognitive responses to brand attitudes. Conclusions - The parts derived based on the research results show that storytelling marketing has a strong influence on the airline's brand image and attitude, and that it is necessary for airlines to have a brand image and attitude. Also, forming a favorable brand image has a significant impact on brand attitudes. We believe that by presenting basic data to the aviation industry in future research on airline storytelling, we will be able to increase understanding and contribution to development of storytelling marketing in aviation.

• International Journal of Computer Science & Network Security
• /
• 제21권9호
• /
• pp.303-316
• /
• 2021

Digital content protection has recently become an important requirement in biometrics-based authentication systems due to the challenges involved in designing a feasible and effective user authentication method. Biometric approaches are more effective than traditional methods, and simultaneously, they cannot be considered entirely reliable. This study develops a reliable and trustworthy method for verifying that the owner of the biometric traits is the actual user and not an impostor. Watermarking-based approaches are developed using a combination of a color face image of the user and a mobile equipment identifier (MEID). Employing watermark techniques that cannot be easily removed or destroyed, a blind image watermarking scheme based on fast discrete curvelet transform (FDCuT) and discrete cosine transform (DCT) is proposed. FDCuT is applied to the color face image to obtain various frequency coefficients of the image curvelet decomposition, and for high frequency curvelet coefficients DCT is applied to obtain various frequency coefficients. Furthermore, mid-band frequency coefficients are modified using two uncorrelated noise sequences with the MEID watermark bits to obtain a watermarked image. An analysis is carried out to verify the performance of the proposed schema using conventional performance metrics. Compared with an existing approach, the proposed approach is better able to protect multimedia data from unauthorized access and will effectively prevent anyone other than the actual user from using the identity or images.

• 한국의류산업학회지
• /
• 제21권1호
• /
• pp.104-111
• /
• 2019

This study was developed using the DTP (digital textile printing) jacquard fabrics with a three-dimensional pattern for bag and evaluated the preference and emotional structure. The following conclusions were obtained. Three-dimensional patterns of 12 species using the illustrator program, including six kinds of designs based on the text and six kinds of character types based on the geometry of the basic design was developed. As a result of evaluating the preference of the three-dimensional pattern jacquard fabric, the most preferred fabric was a three-dimensional patterned jacquard fabric with a motif of the Korean consonant "ㅅ". The results of analyzing the emotional dimension of the three-dimensional pattern jacquard fabric, eight factors including simple image, feminine image, exotic image, graphic image, sporty image, masculine image, dynamic image and stereoscopic image were derived. Between emotional factors and preferences correlation analysis showed the stronger the simple image, the feminine image, and the sporty image, the more preferable. It suggested the possibility of a morphological and new fabric for bag, textile design motifs by using Hangul consonants attempt to limit the flatness of the existing geometric form patterns that can be applied to three-dimensional bag whether swirly patterns overcome.

• International Journal of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.76-85
• /
• 2019

We introduce a vision-based object detection method for real-time video surveillance system in low-end edge computing environments. Recently, the accuracy of object detection has been improved due to the performance of approaches based on deep learning algorithm such as Region Convolutional Neural Network(R-CNN) which has two stage for inferencing. On the other hand, one stage detection algorithms such as single-shot detection (SSD) and you only look once (YOLO) have been developed at the expense of some accuracy and can be used for real-time systems. However, high-performance hardware such as General-Purpose computing on Graphics Processing Unit(GPGPU) is required to still achieve excellent object detection performance and speed. To address hardware requirement that is burdensome to low-end edge computing environments, We propose sub-frame analysis method for the object detection. In specific, We divide a whole image frame into smaller ones then inference them on Convolutional Neural Network (CNN) based image detection network, which is much faster than conventional network designed forfull frame image. We reduced its computationalrequirementsignificantly without losing throughput and object detection accuracy with the proposed method.

• International journal of advanced smart convergence
• /
• 제12권3호
• /
• pp.104-108
• /
• 2023

This paper deals with research on innovative systems using Python-based artificial intelligence technology in the field of plant growth monitoring. The importance of monitoring and analyzing the health status and growth environment of plants in real time contributes to improving the efficiency and quality of crop production. This paper proposes a method of processing and analyzing plant image data using computer vision and deep learning technologies. The system was implemented using Python language and the main deep learning framework, TensorFlow, PyTorch. A camera system that monitors plants in real time acquires image data and provides it as input to a deep neural network model. This model was used to determine the growth state of plants, the presence of pests, and nutritional status. The proposed system provides users with information on plant state changes in real time by providing monitoring results in the form of visual or notification. In addition, it is also used to predict future growth conditions or anomalies by building data analysis and prediction models based on the collected data. This paper is about the design and implementation of Python-based plant growth monitoring systems, data processing and analysis methods, and is expected to contribute to important research areas for improving plant production efficiency and reducing resource consumption.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제16권4호
• /
• pp.299-307
• /
• 2016

While segmenting "complex" images (with multiple objects, many details, etc.) we experienced a need to explore new ways for time-efficient and meaningful image segmentation. In this paper we propose a new technique for image segmentation which has only one variable for controlling the expected number of segments. The algorithm focuses on the treatment of pixels in transition zones between various label distributions. Results of the proposed algorithm (e.g. on the Berkeley image segmentation dataset) are comparable to those of GMM or HMM-EM segmentation, but are achieved with significantly reduced computation time.