• The Journal of the Korea Contents Association
• /
• v.1 no.1
• /
• pp.24-31
• /
• 2001

In The AV system, to produce a realistic sound effect is very difficult because the distance between stereo speakers is very narrow. Many signal processing method of widening the sound image for spatial impression have been studied. Most of the typical methods of widening the sound image are related to the phase shifting. but this method was not effective in the concrete wall structure with high reflectivity. In this paper, we proposed an effective method of extending stereo sound image using Precedence Effect and reflected sound. In experiments we confirmed the usefulness of the method for extending stereo sound image of a conventional AV system in wider listening area of a room.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.1029-1032
• /
• 1999

Muscle based face image synthesis is one of the most realistic approach to realize life-like agent in computer. Facial muscle model is composed of facial tissue elements and muscles. In this model, forces are calculated effecting facial tissue element by contraction of each muscle strength, so the combination of each muscle parameter decide a specific facial expression. Now each muscle parameter is decided on trial and error procedure comparing the sample photograph and generated image using our Muscle-Editor to generate a specific face image. In this paper, we propose the strategy of automatic estimation of facial muscle parameters from 2D marker movement using neural network. This also 3D motion estimation from 2D point or flow information in captered image under restriction of physics based face model.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.8
• /
• pp.640-646
• /
• 2003

We presents an edge-based point correlation algorithm for fast and stable visual inspection system. Conventional algorithms based on NGC(normalized gray-level correlation) have to overcome some difficulties in applying automated inspection systems to real factory environment. First of all, NGC algorithms involve highly complex computation and thus require high performance hardware for realtime process. In addition, lighting condition in realistic factory environments is not stable and therefore intensity variation from uncontrolled lights gives many troubles for applying NGC directly as pattern matching algorithm. We propose an algorithm to solve these problems, using thinned and binarized edge data, which are obtained from the original image. A point correlation algorithm with the thinned edges is introduced with image pyramid technique to reduce the computational complexity. Matching edges instead of using original gray-level image pixels overcomes problems in NGC method and pyramid of edges also provides fast and stable processing. All proposed methods are proved by the experiments using real images.

• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.1088-1091
• /
• 2000

Superquadrics can represent various and complex 3D objects with only some parameters(size, position, deformation etc.). So if we use both superquadrics and deformed superquadrics, we can also represent more realistic 3D objects which are existed in real world. In this paper we use the z-buffer algorithm and stencil buffer together because this is very useful when the superquadric primitives are combined. The fundamental ideas are illustrated with a number of tables and figures.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.525-528
• /
• 2019

Atmospheric particle removal is a challenging task and attacks wide interests in computer vision filed. In this paper, we proposed a single image snow removal framework based on deep residual networks. According to the fact that there are various snow sizes in a snow image, the inception module which consists of different filter kernels was adopted to extract multiple resolution features of the input snow image. Except the traditional mean square error loss, the perceptual loss and total variation loss were employed to generate more clean images. Experimental results on synthetic and realistic snow images indicated that the proposed method achieves superior performance in respect of visual perception and objective evaluation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.415-418
• /
• 2019

본 논문에서 grayscale 이미지를 그럴듯한 컬러 이미지로의 전환을 다루고자 한다. 기존의 CNN Network 를 통해 실제 Image 를 만들어내려는 기법들은 모든 Pixel 의 Error 를 Loss 로 사용한다. 각 픽셀별로 가장 완벽한 답을 찾으려고 하기보다는, 전체 픽셀의 관점에서의 Loss 를 줄이려고 하기 때문에, 픽셀 값이 정확한 값대신 안전한 값으로 넘어간다는 단점이 있다. 이 문제를 해결하기 위해 본 논문에서 GAN 기반의 Image-to-Image Translation 기법에 NIN(Network in Network) 적용해 이 문제를 해결할 수 있음을 보인다. 전통 CNN 기법보다 더 Photo-realistic 한 이미지를 생성할 수 있게 된다.

• Korean Journal of Remote Sensing
• /
• v.22 no.5
• /
• pp.351-356
• /
• 2006

Based on current practical needs for geo-spatial information on mobile platform, the main theme of this study is a design and implementation of dynamic 3D terrain rendering system using spaceborne imagery, as a kind of texture image for photo-realistic 3D scene generation on mobile environment. Image processing and 3D graphic techniques and algorithms, such as TIN-based vertex generation with regular spacing elevation data for generating 3D terrain surface, image tiling and image-vertex texturing in order to resolve limited resource of mobile devices, were applied and implemented by using graphic pipeline of OpenGL|ES (Embedded System) API. Through this implementation and its tested results with actual data sets of DEM and satellite imagery, we demonstrated the realizable possibility and adaptation of complex typed and large sized 3D geo-spatial information in mobile devices. This prototype system can be used to mobile 3D applications with DEM and satellite imagery in near future.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.1
• /
• pp.7-13
• /
• 2009

This paper presents a circularly symmetric point spread function (PSF) estimation technique for a fully digital auto-focusing system. The proposed algorithm provides realistic, unsupervised PSF estimation by establishing the relationship between one-dimensional ideal step response and two-dimensional circularly symmetric PSF.

• Journal of Internet Computing and Services
• /
• v.5 no.5
• /
• pp.79-91
• /
• 2004

This paper proposes avatar face generation system that uses shading mechanism and facial features extraction method of facial recognition. Proposed system generates avatar face similar to human face automatically using facial features that extracted from a photo. And proposed system is an approach which compose shade and facial features. Thus, it has advantages that can make more realistic avatar face similar to human face. This paper proposes new eye localization method, facial features extraction method, classification method for minimizing retrieval time, image retrieval method by similarity measure, and realistic avatar face generation method by mapping facial features with shaded face pane.

• Journal of the Korean Society of Costume
• /
• v.33
• /
• pp.41-54
• /
• 1997

The objectives of this study were to find out the relationships between clothing style pre-ferences and self-image and to examine the differences in clothing style preferences ac-cording to marital status educational level and social stratification of women. The drawings of clothing style were designed referring to the catalogues for spring/summer of 1996 and printed by computer 6 styles of suit corresponding to clothing image were selected. Style A is a brown suit decorated with scarf style B a grey suit with stripes C a yellow suit with printed pattern D a grey and beige suit E a chanel suit decorated with corsage and F a blue suit with pleated skirt. The self-image was separated to the actual self-image and the ideal self-image. Samples were 226 women(ages 18 to 37) in Seoul Korea. The results of the study were the followings. 1. Clothing images of 6 styles were estimated; Style A was plain conservative formal and gentle image ; B masculine solid actual dark and plain image; C feminine romantic bright and splendid image; D actual ordinary un-fashionable and plain image; E feminine ten-der romantic and non-active image ; F indi-vidual fshionable open casual sprightly and active image. 2. There were significant relationships be-tween clothing style preferences and realistic self-image. The women who considered them-selves as masculine preferred style B mascu-line and plain image. The women feminine and conservative preferred style E feminine and tender image. The women not to follow the fshion preferred style D ordinary and plain image. The women informal and open pre-ferred the style F casual and active image. 3. There were significant relationships be-tween clothing style preferences and ideal self-image. The women who wanted to be-tween clothing style preferences and ideal self-image. The women who wanted to be con-sidered themselves as feminine and conserva-tive preferred style E feminine and tender im-age. The women who wanted gentle and con-servative preferred style D ordinary and plain image. The women who wanted sprightly pre-ferred the style F casual and active image. 4. There were significant differences in clothing style preferences according to marital status educational level and social stratifi-cation. The women with more eduacation pre-ferred the splendid and the plain image at the same time. The upper class preferred feminine image and lower class casual and active image.