• Journal of Electrical Engineering and information Science
• /
• v.3 no.2
• /
• pp.222-229
• /
• 1998

In the circumstances we want to deal with, a transmission channel is limited and a global motion can happen by camera movement, and also there exists a region-of-interest(ROI) which is more important than background. So very low bit rate coding algorithm is required and processing of global motion must be considered. Also ROI must be reconstructed with required quality after decoding because of its importance. But the existing methods such as H.261, H.263 can not reconstruct ROIs with high quality because they do not consider the fact that ROIs are more important than background. So a new coding scheme is proposed that describes a method for encoding image sequences distinguishing bits between ROI and background. Experimental results show that the suggested algorithm performs well especially in the circumstances where background changes and the area of ROI is small enough compared with that of background.

• Proceedings of the Optical Society of Korea Conference
• /
• 2007.07a
• /
• pp.35-36
• /
• 2007

We report a probe using a single double clad fiber (DCF) for fluorescence spectroscopy. Bidirectional separate transmission for excitation and fluorescence light in a single fiber was implemented. A DCF coupler made by side-polished method could extract none but the collected fluorescence signals propagating in inner cladding mode, thereby diminishing the interference of silica background generated by the excitation in core mode. The experimental results show that the fluorescence spectra of biological tissues obtained using the DCF probes have much less silica background than using a standard multiple-mode fiber.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.787-789
• /
• 2005

본 논문에서는 로봇이나 감시 시스템에서 주로 쓰이고 있는 배경 모델링의 정확성을 지속 시키는 방법을 제안한다. 오브젝트를 추출하려면 정확한 배경 모델이 필요하다. 정확한 배경 모델을 유지하기 위해서는 전경의 정보가 배경 모델에 반영되면 안 된다. 본 논문에서는 오브젝트의 움직임을 기반으로 한 배경 무효화 기법을 사용하여 전경이 배경 모델에 영향을 주는 것을 방지함으로써 정확한 배경 모델을 유지하는 방법을 제안한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.823-825
• /
• 2004

본 연구에서는 필기체 한글의 글자단위의 분할을 위해 배경 세선화(Background thinning)라는 방법을 제안한다. 배경 세선화 방법은 글자와 글자 사이에 존재하는 배경의 정보를 세선화 처리하여 필기체 한글에서 많이 발생할 수 있는 중첩(Overlap)글자와 연결(Touched)글자를 서로 분할하는데 효과적인 성능을 보였다. 배경 세선화를 이용하여 글자를 분할하는 방법은 인식과정의 판단을 필요하지 않은 외적분할 방법으로 빠른 속도의 분할 성능을 보였다. 이 방법은 특히, 중첩된 글자의 분할에 탁월한 성능을 보였을 뿐만 아니라, 연결된 글자에 대해서도 좋은 성능을 보였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.609-610
• /
• 2022

본 논문에서는 게임 배경 그래픽 중 건축 구조물의 특성에 따른 건축물 모듈화 작업이 배경 그래픽 제작 통일성과 효율성에 주는 영향을 알아보고 향후 효과적인 건축물 제작 프로세스 연구의 방향을 제시한다.

• Proceedings of the IEEK Conference
• /
• 2004.08c
• /
• pp.810-813
• /
• 2004

In this paper, a background initialization for video surveillance proposed. The proposed algorithm is that the background images are sampled n frames during ${\Delta}t$ All Sampling frames are divided by $M{\times}N$ size block every frame. Average values of pixels for same location block of the sampling frames during ${\Delta}t$t are taken. then the maximum intensity $\alpha$ and the minimun intensity $\beta$ is obtained, respecticely. The intial by $M{\times}N$ size block, then average intensity $\eta$ of pixels for the block is obtained. If the average intensity $\eta$ is out of the initial range of the background image, it is decided the moving object image, and if the average intensity $\eta$ is included in the initial range of the background image. it is decided the background image. To examine the propriety of the proposed algorithm in this paper, the accuracy and robustness evaluation results for human and car in the indoor and outdoor enviroment. the error rate of the proposed method is less than the existing methods and the extraction rate of the proposed method is better than the existing methods.

• Journal of Fashion Business
• /
• v.18 no.2
• /
• pp.29-41
• /
• 2014

As the online shopping mall market faces severe competition, marketers have focused on visual factors that generate positive consumer responses in order to induce more consumers. Although product photos are crucial in the communication of product information as well as in the development of positive images of online shopping mall, there was little intention the effect of diverse types of product photo. In this study, three types of backgrounds (i.e., no background, indoor background, street background) are compared in order to explore whether consumer sensibility factors are different according to photo backgrounds. Moreover, it investigates the effect of sensibility toward photo backgrounds on consumer attitude. A total of 222 consumers participated in the experiments. As a result, six sensibility factors were generated from online model photos, including structure, upscale, uniqueness, interest, simpleness, and easiness factors. Among these factors, simpleness and structure showed the highest means; simpleness was the factor indicating the differences according to photo backgrounds. Sensibility factors affecting attitude toward online shopping malls were uniqueness in the case of no background, interest in the case of indoor background, and upscale in the case of street background photo.

• The KIPS Transactions:PartB
• /
• v.10B no.4
• /
• pp.473-478
• /
• 2003

In this paper, we propose the gesture recognition system using a motion information from extracted hand region in complex background image. First of all, we measure entropy for the difference image between continuous frames. Using a color information that is similar to a skin color in candidate region which has high value, we extract hand region only from background image. On the extracted hand region, we detect a contour using the chain code and recognize hand gesture by applying improved centroidal profile method. In the experimental results for 6 kinds of hand gesture, unlike existing methods, we can stably recognize hand gesture in complex background and illumination changes without marker. Also, it shows the recognition rate with more than 95% for person and 90∼100% for each gesture at 15 frames/second.

• The Journal of the Korea Contents Association
• /
• v.17 no.1
• /
• pp.137-144
• /
• 2017

Face detection is still a challenging task under severe face pose variations in complex background. This paper proposes an effective algorithm which can detect single or multiple faces based on skin color detection and depth information. We introduce Gaussian mixture model(GMM) for skin color detection in a color image. The depth information is from three dimensional depth sensor of Kinect V2 device, and is useful in segmenting a human body from the background. Then, a labeling process successfully removes non-face region using several features. Experimental results show that the proposed face detection algorithm can provide robust detection performance even under variable conditions and complex background.

• Journal of Information Processing Systems
• /
• v.13 no.1
• /
• pp.114-127
• /
• 2017

This paper proposes a color image coding algorithm based on shape-adaptive all phase biorthogonal transform (SA-APBT). This algorithm is implemented through four procedures: color space conversion, image segmentation, shape coding, and texture coding. Region-of-interest (ROI) and background area are obtained by image segmentation. Shape coding uses chain code. The texture coding of the ROI is prior to the background area. SA-APBT and uniform quantization are adopted in texture coding. Compared with the color image coding algorithm based on shape-adaptive discrete cosine transform (SA-DCT) at the same bit rates, experimental results on test color images reveal that the objective quality and subjective effects of the reconstructed images using the proposed algorithm are better, especially at low bit rates. Moreover, the complexity of the proposed algorithm is reduced because of uniform quantization.