• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06b
• /
• pp.182-187
• /
• 2007

본 논문에서는 이미지 상에 나타난 색상 정보를 추출하기 위한 새로운 커널 메소드(Kernel method)인 Grid kernel을 제안한다. 제안한 Grid kernel은 Convolution kernel의 하나로 이미지 상에 나타나는 자질을 주변 픽셀에서 나타나는 자질로 정의 하고 이를 재귀적으로 적용함으로써 두 이미지를 비교한다. 본 논문에서는 제안한 커널을 차량 색상 인식 문제에 적용하여 차량 색상 인식 모델을 제안한다. 이미지 생성시 나타나는 주변 요인으로 인해 차량의 색상을 추출하는 것은 어려운 문제이다. 이미지가 야외에서 촬영되기 때문에 시간, 날씨 등의 주변 요인은 같은 차량이라 하더라도 다른 색상을 보이게 할 수 있다. 이를 해결하기 위해 Grid kernel이 적용된 차량 색상 인식 모델은 이미지를 HSV (Hue-Saturation-Value) 색상 공간으로 사상하여 명도를 배제하였다. 제안한 커널과 색상 인식 모델을 검증하기 위해 5가지 색상을 가진 차량 이미지를 이용하여 실험을 하였으며, 실험 결과 92.4%의 정확율과 92.0%의 재현율을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.2 no.6
• /
• pp.280-298
• /
• 2008

For efficient content-based image retrieval, diverse visual features such as color, texture, and shape have been widely used. In the case of leaf images, further improvement can be achieved based on the following observations. Most plants have unique shape of leaves that consist of one or more blades. Hence, blade-based matching can be more efficient than whole shape-based matching since the number and shape of blades are very effective to filtering out dissimilar leaves. Guaranteeing rotational invariance is critical for matching accuracy. In this paper, we propose a new shape representation, indexing and matching scheme for leaf image retrieval. For leaf shape representation, we generated a distance curve that is a sequence of distances between the leaf’s center and all the contour points. For matching, we developed a blade-based matching algorithm called rotation invariant - partial dynamic time warping (RI-PDTW). To speed up the matching, we suggest two additional techniques: i) priority queue-based pruning of unnecessary blade sequences for rotational invariance, and ii) lower bound-based pruning of unnecessary partial dynamic time warping (PDTW) calculations. We implemented a prototype system on the GEMINI framework [1][2]. Using experimental results, we showed that our scheme achieves excellent performance compared to competitive schemes.

• Journal of Korea Multimedia Society
• /
• v.11 no.12
• /
• pp.1676-1687
• /
• 2008

In this paper, we proposed a new multi-view human recognition method based on face and gait features detection algorithm. For getting the position of moving object, we used the different of two consecutive frames. And then, base on the extracted object, the first important characteristic, walking direction, will be determined by using the contour of head and shoulder region. If this individual appears in camera with frontal direction, we will use the face features for recognition. The face detection technique is based on the combination of skin color and Haar-like feature whereas eigen-images and PCA are used in the recognition stage. In the other case, if the walking direction is frontal view, gait features will be used. To evaluate the effect of this proposed and compare with another method, we also present some simulation results which are performed in indoor and outdoor environment. Experimental result shows that the proposed algorithm has better recognition efficiency than the conventional sing]e view recognition method.

• Journal of Korea Multimedia Society
• /
• v.10 no.2
• /
• pp.187-199
• /
• 2007

The purpose of painterly rendering is to express real painting work from input image. For expression of real pain ting impression, drawing condition is one of main element. In this paper, we propose new algorithm for using density of edges. Drawing condition of new algorithm uses color difference and density of edges. And for finding next position from current position, we used dynamic grid. We did direction interpolation for coherence direction. Also using various texture brush, we express the feel of a material effective. We show results of images rendered more realistic oil painting effect, and discuss long-term goals for more effective result.

• Journal of The Korean Astronomical Society
• /
• v.35 no.3
• /
• pp.131-141
• /
• 2002

We present Near-IR photometry of the Arches cluster, a young and massive stellar cluster near the Galactic center. We have analyzed the high resolution (FWHM $\~$ 0.2") Hand K' band images in the Galactic Center Demonstration Science Data Set, which were obtained with the Gemini/Hokupa's adaptive optics (AO) system. We present the color-magnitude diagram, the luminosity function and the initial mass function (IMF) of the stars in the Arches cluster in comparison with the HST/NICMOS data. The IMF slope for the range of 1.0 < log (M/M$\bigodot$) < 2.1 is estimated to be ${\Gamma} = -0.79 {\pm} 0.16$, in good agreements with the earlier result based on the HST/NICMOS data [Figer et al. 1999, ApJ, 525, 750]. These results strengthen the evidence that the IMF of the bright. stars close to the Galactic center is much flatter than that for the solar neighborhood. This is also consistent with a recent finding that the IMFs of the bright stars in young clusters in M33 get flatter as the galactocentric distance decreases [Lee et al. 2001, astro-ph 0109258]. It is found that the power of the Gemini/ AO system is comparable, with some limits, to that of the HST/NICMOS.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.11
• /
• pp.79-84
• /
• 2015

Steganography is to conceal the existence of secrete data itself. The Emulab is a framework to provide real systems and network topology that can set up at anytime by researchers. In this paper, we show that steganography techniques can be applied in the Emulab environment. Steganography methods are evaluated on a standalone and sharing environments using the color bitmap images. The cover image is divided into RGB channels and then embedded the secret data at each client. The experimental results demonstrate that execution time is better in client/server environment as cover image size is increasing.

• Proceedings of the Korea Technical Association of the Pulp and Paper Industry Conference
• /
• 2006.06b
• /
• pp.485-488
• /
• 2006

Surface roughening which is occurred by interaction between base paper and water in coating color deteriorates surface properties of coated paper. In this study, the effect of calendering variables on surface roughening and the relationship between hot calendering and water penetration depth were investigated. BCTMP handsheets were calendered at the various conditions of temperature and linear load, and its PPS roughness was measured before and after moistening to evaluate surface roughening. To determine water penetration depth, thickness was measured from the cross sectional images of sheet which were obtained using CLSM technique. High pressure calendering was beneficial to reduce surface roughness before coating but its smoothening effect was mostly lost by contact with water. On the contrary, sheet calendered at the highest temperature showed the lowest roughening. High temperature calendering allowed the smallest penetration of water into fiber network because of sufficient deformation and densification in top side of z-direction of sheet. Consequently, hot calendering could be the effective way to reduce surface roughening and unevenness of paper surface.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.12
• /
• pp.2398-2405
• /
• 2007

This paper proposes a contrast enhancement technique which stretches the intensity surfaces of image to improve the quality of the digital photos. The proposed method enhances the contrast of image by stretching the intensity surface of the original image to the maximum range of the output image in proportion to the distances between the original intensity surface and upper, lower intensity surface, respectively. The upper and lower intensity surfaces are generated from the original intensity surface by gaussian smoothing. In the experiments, digital color images in a variety of illumination conditions were used and the proposed method was compared with other several existed image enhancement algorithms, which are histogram stretching, surface stretching, histogram equalization, gamma correction and retinex. It was proved that the experimental results were more natural visually without deterioration of gradation.

• The Journal of Korea Robotics Society
• /
• v.14 no.4
• /
• pp.301-310
• /
• 2019

A new algorithm has been propose to detect the reflected light region as disturbances in a real-time vision system. There have been several attempts to detect existing reflected light region. The conventional mathematical approach requires a lot of complex processes so that it is not suitable for a real-time vision system. On the other hand, when a simple detection process has been applied, the reflected light region can not be detected accurately. Therefore, in order to detect reflected light region for a real-time vision system, the detection process requires a new algorithm that is as simple and accurate as possible. In order to extract the reflected light, the proposed algorithm has been adopted several filter equations and clustering processes in the HSI (Hue Saturation Intensity) color space. Also the proposed algorithm used the pre-defined reflected light data generated through the clustering processes to make the algorithm simple. To demonstrate the effectiveness of the proposed algorithm, several images with the reflected region have been used and the reflected regions are detected successfully.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.73-78
• /
• 2006

Conventional caption extraction methods use the difference between frames or color segmentation methods from the whole image. Because these methods depend heavily on heuristics, we should have a priori knowledge of the captions to be extracted. Also they are difficult to implement. In this paper, we propose a method that uses little heuristic and simplified algorithm. We use topographical features of characters to extract the character points and use MST(Minimum Spanning Tree) to extract the candidate regions for captions. Character regions are determined by testing several conditions and verifying those candidate regions. Experimental results show that the candidate region extraction rate is 100%, and the character region extraction rate is 98.2%. And then we can see the results that caption area in complex images is well extracted.