• Journal of Satellite, Information and Communications
• /
• v.8 no.4
• /
• pp.26-29
• /
• 2013

In order to estimate people crowdedness in public area, the texture based method or motion based method can be used. In this paper we have proposed a mixed method. By designating the region of interest, we made the degree of crowdedness more accurate. The feature normalization also reduced the image distortion which results from difference of camera angle. The proposed system was optimized to real time embedded hardware system.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.128-131
• /
• 2004

In this paper, we describe reconstructed 3D-urban modeling techniques for laser scanner and CCD camera system, which are loading on the vehicle. We use two laser scanners, the one is horizon scanner and the other is vertical scanner. Horizon scanner acquires the horizon data of building for localization. Vertical scan data are main information for constructing a building. We compared extraction of edge aerial image with laser scan data. This method is able to correct the cumulative error of self-localization. Then we remove obstacles of 3D-reconstructed building. Real-texture information that is acquired with CCD camera is mapped by 3D-depth information. 3D building of urban is reconstructed to 3D-virtual world. These techniques apply to city plan. 3D-environment game. movie background. unmanned-patrol etc.

• Journal of the Korean Society of Costume
• /
• v.56 no.8 s.108
• /
• pp.138-147
• /
• 2006

This study tried to research on clothing styles of show hostess in the cable television home-shopping network program. Especially, show hostess's clothing styles were classified into 5 sections according to selling products, that is baby goods, insured goods, underwear, bedclothes and beauty goods. item is examined 7 levels by texture, color, clothing item, fashion image, fashion trend, fashion type, and fashion silhouette. The results showed that significant correlations between show host's clothing and selling products. The another findings of this study is that show hostess's clothing is aimed at the taste of main consumer such as housewife. Conseguently this study reaffirms the importance of the shopping hostess's clothing influnce according to selling products's characteristics.

• Annual Conference on Human and Language Technology
• /
• 2001.10d
• /
• pp.48-53
• /
• 2001

인터넷 환경의 급속한 성장과 더불어 기존의 텍스트 정보들이 다양한 형태의 멀티미디어 정보(소리, 이미지, 동영상 등)로 대체되었다. 이로 인해 멀티미디어 정보검색의 필요성이 대두되기 시작했다. 멀티미디어 정보검색 중 이미지검색은 크게 주석기반과 특징기반 (color, shape, texture 등) 검색으로 나눌 수 있다. 본 고는 이미지 검색 중 전처리에 해당하는 색상어 질의처리의 한 방법을 제안한다. 즉, 사용자에게 익숙한 자연어 질의로부터 이미지의 특징에 해당하는 색상 정보와 주석에 해당하는 키워드 정보를 중심어 후위원칙기반으로 파싱트리를 구성한 후, 후위순회방식에 의해 불리언 검색을 수행하는 방법을 제안한다.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.13 no.2
• /
• pp.161-167
• /
• 2009

An animated ink diffusion on paper is simulated through making a multiple sessions of random walks. The simulated random walk is built and validated against the diffusion model, then animated by varying the intensity thresholds of the accumulated visit counts on each pixels on an image. Two different random walk models are built one of which is a free random walk in that the walker has exactly same probability to move in any four or eight directions in each step. The other is a biased random walk that has a higher chance to go to a pixel that has more similar intensity value. The latter can be used to simulate an ink diffusion radiating through different texture of paper.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.22 no.2
• /
• pp.91-100
• /
• 2018

In this paper, we propose a new method for template matching, patch ratio, to inpaint unknown pixels. Before this paper, many inpainting methods used sum of squared differences(SSD) or sum of absolute differences(SAD) to calculate distance between patches and it was very useful for closest patches for the template that we want to fill in. However, those methods don't consider about geometric similarity and that causes unnatural inpainting results for human visuality. Patch ratio can cover the geometric problem and moreover computational cost is less than using SSD or SAD. It is guaranteed about finding the most similar patches by Cauchy-Schwarz inequality. For ignoring unnecessary process, we compare only selected candidates by priority calculations. Exeperimental results show that the proposed algorithm is more efficent than Criminisi's one.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.7
• /
• pp.2480-2495
• /
• 2014

This paper describes a hierarchical method for image-based age estimation that combines age group classification and age value estimation. The proposed method uses a coarse-to-fine strategy with different appearance features to describe facial shape and texture. Considering the damage to continuity between neighboring groups caused by fixed divisions during age group classification, a dynamic grouping technique is employed to allow non-fixed groups. Based on the given group, an ordinal hyperplane ranking (OHRank) model is employed to transform age estimation into a series of binary enquiry problems that can take advantage of the intrinsic correlation and ordinal information of age. A set of experiments on FG-NET are presented and the results demonstrate the validity of our solution.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2327-2330
• /
• 2003

This paper deals with face detection and recognition using ellipsodal information and wavelet packet analysis. We proposed two methods. First, Face detection method uses general ellipsodal information of human face contour and we find eye position on wavelet transformed face images A novel method for recognition of views of human faces under roughly constant illumination is presented. Second, The proposed Face recognition scheme is based on the analysis of a wavelet packet decomposition of the face images. Each face image is first located and then, described by a subset of band filtered images containing wavelet coefficients. From these wavelet coefficients, which characterize the face texture, the Euclidian distance can be used in order to classify the face feature vectors into person classes. Experimental results are presented using images from the FERET and the MIT FACES databases. The efficiency of the proposed approach is analyzed according to the FERET evaluation procedure and by comparing our results with those obtained using the well-known Eigenfaces method. The proposed system achieved an rate of 97％(MIT data), 95.8％(FERET databace)

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.1909-1910
• /
• 2008

본 논문에서는 실린더 모델을 이용하여 머리의 다양한 포즈 변화와 조명 변화에 대해 강인한 얼굴 인식을 제안하고자 한다. 실린더 모델은 사람의 머리가 실린더 모양과 유사하고 그 표면은 얼굴에 해당된다고 가정한다. 실린더 모델은 6가지의 모션 파라메터를 따라 움직이며 Lucas-Kanade 알고리즘에 의해 모션 파라메터의 양을 결정한다. 강인한 동작을 위해 템플릿을 지속적으로 바꿔주는 동적 템플릿(dynamic template)방법과 그에 따른 에러가 누적되는 것을 막기 위해 re-registration방법을 사용한다. 조명 문제를 해결하기 위해 템플릿에서 조명 주성분 벡터를 추출하여 제거하는 방법으로 조명 효과를 제거한다. 실험에서는 다양한 포즈 변화와 조명 변화가 반영된 얼굴 데이터베이스를 구축하고 추출한 텍스쳐 맵(texture map image)을 SVM에 적용함으로서 포즈, 조명 변화에 강인한 얼굴인식을 보인다.

• Journal of Advanced Navigation Technology
• /
• v.9 no.2
• /
• pp.170-176
• /
• 2005

In this paper, we proposed watermarking algorithm based on wavelet transform. Discrete wavelet transform is involved to calculate additive energy strength. Considering imperceptibility, after computing contrast and texture sensitivity in gray-level image, we inserted watermark with variable weight due to the feature of coefficient block. Consequently, applying human visual system, the experimental results showed that the proposed algorithm satisfied the properties of robustness and imperceptibility that are the major conditions of watermarking.