• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.187-190
• /
• 2007

This study is for analyzing best band in image matching using correlation coefficient of left and right images of stereo image pair, lot red, green, blue band images separated from color aerial photo and gray image converted from the same color aerial photo image. The image matching is applied to construct Digital Elevation Model(DEM) or terrain data. The correlation coefficients and variation by change of pixel patch size are computed from pixel patches of which sizes are $11{\times}11{\sim}101{\times}101$. Consequently, the correlation coefficient in red band image is highest. The lowest is in blue band. Therefore, to construct terrain data using image matching, the red band image is preferable. As the size of pixel patch is growing, the correlation coefficient is increasing. But increasing rate declines from $51{\times}51$ image patch size and above. It is proved that the smaller pixel patch size than $51{\times}51$ is applied to construct terrain data using image matching.

• ETRI Journal
• /
• v.35 no.3
• /
• pp.512-522
• /
• 2013

In this paper, the radius weight mean (RWM) and the feature-embedding technique are used to present a novel watermarking scheme for color images. Simulations validate that the stego-images generated by the proposed scheme are robust against most common image-processing operations, such as compression, color quantization, bit truncation, noise addition, cropping, blurring, mosaicking, zigzagging, inversion, (edge) sharpening, and so on. The proposed method possesses outstanding performance in resisting high compression ratio attacks: JPEG2000 and JPEG. Further, to provide extra hiding storage, a steganographic method using the RWM with the least significant bit substitution technique is suggested. Experiment results indicate that the resulting perceived quality is desirable, whereas the peak signal-to-noise ratio is high. The payload generated using the proposed method is also superior to that generated by existing approaches.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.185-189
• /
• 2004

For face recognition system, a face detector which can find exact face region from complex image is needed. Many face detection algorithms have been developed under the assumption that background of the source image is quite simple . this means that face region occupy more than a quarter of the area of the source image or the background is one-colored. Color-based face detection is fast but can't be applicable to the images of which the background color is similar to face color. And the algorithm using neural network needs so many non-face data for training and doesn't guarantee general performance. In this paper, A multi-scale, multi-face detection algorithm using PCA is suggested. This algorithm can find most multi-scaled faces contained in static images with small number of training data in reasonable time.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.987-990
• /
• 2005

An important issue in the field of face recognitions and man-machine interfaces is an automatic detection of faces in visual scenes. it should be computationally fast enough to allow an online detection. In this paper we describe our ongoing work on face detection that models the face appearance by edge orientation and color distribution. We show that edge orientation is a powerful feature to describe objects like faces. We present a method for face region detection using edge orientation and a method for face feature detection using local color information. We demonstrate the capability of our detection method on an image database of 1877 images taken from more than 700 people. The variations in head size, lighting and background are considerable, and all images are taken using low-end cameras. Experimental results show that the proposed scheme achieves 94% detection rate with a resonable amount of computation time.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.265-267
• /
• 2003

해부학적 구조의 변형이 존재하는 신체 부위를 정합하기 위하여 연구되는 non-rigid 정합 방법은 현재 의료 영상 분야에서 매우 중요한 주제이고 많은 연구가 이루어지고 있다. 본 논문에서는 Visible Human Color 단면 영상과 CT영상 사이에 존재하는 다리 모양의 변형을 정합 하기 위하여 계층적인 non-rigid 정합 방법을 제안하였다. 제안한 계층적 정합 방법은 영역 경계를 이용한 global rigid 정합으로 초기 변형 벡터를 찾고. 정합 할 영역을 sampling하여 local non-rigid 정합을 수행 한 후 결과를 interpolation하여 전체 영역에 대한 최종 정합 벡터를 계산하였다. 결과적으로 더욱 효율적이고 강력한 non-rigid 정합 결과를 얻을 수 있었다.

• The International Journal of Costume Culture
• /
• v.9 no.1
• /
• pp.77-81
• /
• 2006

From the viewpoint of color perspective, black has more obvious effects to impart images than dress itself This study aims to examine black dress through the fashion history to highlight the aesthetic value of black and to make better use of black in designing. Black in fashion, particularly in the guise of the little black dress, became an indispensable feature of cosmpolitan style after World War I. Designers harnessed the power of black, drawn irresistibly to its innate qualities of drama and strength of line. For the past five hundred years, aside from the use of black for mourning as well as for religious, academic, legal and ceremonial dress, black with a greater or lesser dominance has been a fashion constant. Since then black has been an important color in fashion. How to use black in formative designs should be studied continuously.

• The Journal of Korea Robotics Society
• /
• v.8 no.2
• /
• pp.82-91
• /
• 2013

This paper proposes a building recognition algorithm using watershed image segmentation algorithm and integrated region matching (IRM). To recognize a building, a preprocessing algorithm which is using Gaussian filter to remove noise and using canny edge extraction algorithm to extract edges is applied to input building image. First, images are segmented by watershed algorithm. Next, a region adjacency graph (RAG) based on the information of segmented regions is created. And then similar and small regions are merged. Second, a color distribution feature of each region is extracted. Finally, similar building images are obtained and ranked. The building recognition algorithm was evaluated by experiment. It is verified that the result from the proposed method is superior to color histogram matching based results.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.28 no.910
• /
• pp.1320-1328
• /
• 2004

Purposes of the study were to find out the joint effects of two salient appearance cues-hair colors and hair lengths on males fashion images, using 729 university students in Daejon city and a Chungnam province. The study was a quasi experiment; the dependent variables were hair lengths(4 levels) and hair colors(4 levels)and the dependent variable was a set of semantic different of scales which was consisted of 40 hi-polar adjectives, The data were analyzed by a factor analysis, 3-way ANOVA, and the results were as follows. Hair lengths effected on the image of five dimensions, salient, social, potency, evaluate and dynamics while hair colors effected on salients, social and potency dimensions. The most significant interaction effect between hair color and lengths were existed on the salient image: For the longer haired males, the color effects became less evident then normal to shorten haired males and it can be concluded that when two salient cues were combined one cue's effect became discounted.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.3
• /
• pp.40-46
• /
• 2006

Automatic recognition of container identifier is one of key factor to implement port automation and increase distribution throughput. In this paper, I propose a method of container identifier recognition on various input images using color based edge detection and character verification algorithm, I tested the proposed method on 350 container images and it showed good results.

• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.894-897
• /
• 2000

In this paper, we present a content-based image retrieval method that is less sensitive to some rotations and translations of an image by using the fuzzy region segmentation. The algorithm retrieves similar images from a database using the two features of color and color spatial information. To index images, we use the average coordinates of color distribution to obtain the spatial information of each segmented region. Furthermore, we also propose the alternative to the ripple phenomenon, which is occurred in the conventional fuzzy region segmentation algorithm.