• 한국의상디자인학회지
• /
• 제25권2호
• /
• pp.1-16
• /
• 2023

Due to the current seriousness of environmental pollution and the eco-friendly movement of the fashion industry, research on sustainable fashion design is being actively conducted. In this study, consumer perception of upcycling products, are divided into image, function, and meaning; and image is further divided into shape, color, and material. It was redefined as pattern, and image recognition was evaluated among men and women in their 20s and 30s, and men and women in their 40s and 50s used as subjects. First, factors that determine each image were extracted based on qualitative analysis of the precedent cases of upcycling bags, and quantitative analysis of the subjects was induced through a questionnaire. As a result of the analysis of evaluation items related to image association, the average frequency analysis of all subjects for each stimuli and the cognitive variance of the frequency analysis by generation by gender were found to be similar. However, awareness of some stimuli by generation showed a significant difference. Overall, in the three stimuli with high overall preference, common features, such as the basic box-shaped symmetrical structure, the monochromatic color of the Munsell system, solid and practical texture, and appropriate use of patterns were identified. In addition, it was confirmed that there was a difference with factors such as femininity, simplicity, touch, and splendor in the measurement factors. In conclusion, it is considered that the main significance of this study is that it excluded the recognition and meaning of upcycling products and explored the original design and image elements of products. Therefore, it is expected that this study will be used as a basic data for responding to the gender image of each generation as an alternative method of sustainable fashion design, and it will be an opportunity to expand the scope of the study to a detailed study beyond the biased topic.

• 한국멀티미디어학회논문지
• /
• 제22권8호
• /
• pp.860-873
• /
• 2019

LCD backlight boosting and the integration of boosting and dimming are proposed based on image analysis to maximize perceptual image qualities and to reduce display system power. Based on the histogram of the image data, methods for selecting an image suitable for boosting and for adjusting the optimum backlight brightness are proposed. A comprehensive combined optimization method of LCD backlight boosting, dimming and bypass based on image characteristics is also described. Perceptual image quality enhancement and power consumption are evaluated based on well known image databases. Average subjective image quality is improved by 24.8%, RMS contrast is improved more than 20%, and average power consumption is reduced by 15.94% compared to conventional uniform boosting.

• 전기학회논문지
• /
• 제64권7호
• /
• pp.1104-1113
• /
• 2015

In this paper, we propose Two-Dimensional Robust Face Recognition System Realized with the Aid of Facial Symmetry with Illumination Variation. Preprocessing process is carried out to obtain mirror image which means new image rearranged by using difference between light and shade of right and left face based on a vertical axis of original face image. After image preprocessing, high dimensional image data is transformed to low-dimensional feature data through 2-directional and 2-dimensional Principal Component Analysis (2D)2PCA, which is one of dimensional reduction techniques. Polynomial-based Radial Basis Function Neural Network pattern classifier is used for face recognition. While FCM clustering is applied in the hidden layer, connection weights are defined as a linear polynomial function. In addition, the coefficients of linear function are learned through Weighted Least Square Estimation(WLSE). The Structural as well as parametric factors of the proposed classifier are optimized by using Particle Swarm Optimization(PSO). In the experiment, Yale B data is employed in order to confirm the advantage of the proposed methodology designed in the diverse illumination variation

• 한국인터넷방송통신학회논문지
• /
• 제24권1호
• /
• pp.65-74
• /
• 2024

최근 자율주행 분야에서는 영상 처리 기술이 중요한 역할을 하고 있다. 그 중에서도 영상 식별 기술은 자율주행 차량의 안전성과 성능에 매우 중요한 역할을 한다. 이에 따라 본 논문에서는 융복합 영상 식별 시스템을 개발하여 자율주행 차량의 안전성과 성능을 향상시키는 것을 목표로 한다. 본 연구에서는 다양한 영상 식별 기술을 활용하여 차량주변 환경의 객체를 인식하고 추적하는 시스템을 구축한다. 이를 위해 머신 러닝과 딥 러닝 알고리즘을 활용하며, 이미지처리 및 분석 기술을 통해 실시간으로 객체를 식별하고 분류한다. 또한, 본 연구에서는 영상 처리 기술과 차량 제어 시스템을 융합하여 자율주행 차량의 안전성과 성능을 높이는 것을 목표로 한다. 이를 위해, 식별된 객체의 정보를 차량 제어시스템에 전달하여 자율주행 차량이 적절하게 반응하도록 한다. 본 연구에서 개발된 융복합 영상 식별 시스템은 자율주행 차량의 안전성과 성능을 크게 향상시킬 것으로 기대된다. 이를 통해 자율주행 차량의 상용화가 더욱 가속화될 것으로 기대된다.

• 한국자동차공학회논문집
• /
• 제8권4호
• /
• pp.158-168
• /
• 2000

Vehicle driving simulators can provide engineers with benefits on the development and modification of vehicle models. One of the most important factors to realistic simulations is the fidelity given by a motion system and a real-time visual image generation system. Virtual reality technology has been widely used to achieve high fidelity. In this paper the virtual environment including a visual system like a head-mounted display is developed for a vehicle driving simulator system by employing the virtual reality technique. virtual vehicle and environment models are constructed using the object-oriented analysis and design approach. Accordint to the object model a three dimensional graphic model is developed with CAD tools such as Rhino and Pro/E. For the real-time image generation the optimized IRIS Performer 3D graphics library is embedded with the multi-thread methodology. Compared with the single loop apprach the proposed methodology yields an acceptable image generation speed 20 frames/sec for the simulator.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1994년도 추계학술대회 논문집
• /
• pp.499-503
• /
• 1994

The feedback control systems of welding process using visual information can improve weld qualities. However, it is very difficult to get the visual information of weld pool since welding are is much stronger than light from weld pool. To explore the possibility of extending the capability of automatic welding machines a study of a closed loop controlled welding system consisted of a GTA welding machine, a vision system, a stepping motor system and a digital computer was undertaken. Particularly, in this system, a CCD camera with 850nm long pass filter was focused on the weld pool to give a weld pool image. Subsequently, image analysis technique has been developed to measure a weld pool width. Using this weld pool width measurement, a colsed loop control system adjusted welding speed to maintain constant weld pool width.

• 한국컴퓨터정보학회논문지
• /
• 제18권5호
• /
• pp.61-68
• /
• 2013

본 논문에서는 스쿨존 시스템에서 수집된 정보를 저장하고 관리하기 위한 데이터베이스에 대한 설계 방안을 제안하고자 한다. 영상 센서를 통해 수집된 영상정보와 GPS 센서를 통해 수집된 좌표 정보는 네트워크를 통해 시스템 서버에 전달되며, 이는 상황인식을 위한 데이터베이스에 의해 관리된다. 스쿨존 서버 시스템은 데이터베이스에 수집된 정보를 가지고 특정 시나리오에 대한 분석을 수행하며, 이에 대한 결과 및 대응에 대해 모니터링 서버에 보고하거나 결과를 저장한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(4)
• /
• pp.255-258
• /
• 2000

This thesis shows controlling the mobile robot with distance information gotten with ultrasonic sensors, and analysis of captured image. The ultrasonic sensors supplies more accurate distance data in limited area but shows unstable data unlimited area while image data generally shows stable data, but this requires so much time because of amounts of calculation. So this thesis considers the merits of ultrasonic sensors and image to implement robot system .

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.585-588
• /
• 1999

This paper concentrates on an experimental results on visual only recognition tasks using an image transform approach and HMM based recognition system. There are two approaches for extracting features of lipreading, a lip contour based approach and an image transform based one. The latter obtains a compressed representation of the image pixel values that contain the speaker's mouth results in superior lipreading performance. In addition, PCA(Principal component analysis) is used for fast algorithm. Finally, HMM recognition tasks are compared with the another.

• International Journal of Contents
• /
• 제4권1호
• /
• pp.12-15
• /
• 2008

In this paper, we propose a new method of background removing for digital self-adaptive acquisition in medical X-ray imaging. We analysis the construction of video digital acquisition system and main factors of acquired image quality, propose a more efficiency method to against background non-uniformly. With proposed method, non-uniform illumination back ground was well removed without image quality degradation.