• 한국지능시스템학회논문지
• /
• 제23권2호
• /
• pp.139-143
• /
• 2013

기존의 영상 이진화에 대한 알고리즘의 기본 아이디어는 영상이 회색 수준의 차이에 의하여 물체와 배경으로 구분된다는 가정에서 이루어지고 있다. 본 논문에서는 이러한 가정을 확장하여 영상은 물체와 배경뿐만 아니라 하나를 더 추가하여 그 테두리로 이루어진다고 가정하고 테두리 검출에 기반한 이진화 기법을 제안한다. 제안한 방법의 타당성을 보이기 위하여 6개의 잘 알려진 영상에 대하여 모의실험을 수행하고, 그 결과로부터 기존의 방법들과의 성능을 비교 검토한다.

• 전자공학회논문지B
• /
• 제28B권10호
• /
• pp.842-913
• /
• 1991

The automatic target detection which automatically identifies the location of the target with its input image is one of the significant subjects of image processing field. Then, there are some problems that should be solved to detect the target automatically from the input image. First of all, the ambiguity of the boundary between targets or between a target and background should be solved and the target should be searched adaptively. In other words, the target should be identified by the relative brightness to the background, not by the absolute brightness. In this paper, to solve these problems, a new algorithm which can identify the target automatically is proposed. This algorithm uses the set of fuzzy for solving the ambiguity between the boundaries, and using the weight according to the brightness of data in the input image, the target is identified adaptively by the relative brightness to the background. Applying this algorithm to real images, it is experimentally proved that it is can be effectively applied to the automatic target detection.

• Journal of Information Processing Systems
• /
• 제16권6호
• /
• pp.1424-1436
• /
• 2020

Although huge progress has been made in current image segmentation work, there are still no efficient segmentation strategies for tree image which is taken from natural environment and contains complex background. To improve those problems, we propose a method for tree image segmentation combining adaptive mean shifting with image abstraction. Our approach perform better than others because it focuses mainly on the background of image and characteristics of the tree itself. First, we abstract the original tree image using bilateral filtering and image pyramid from multiple perspectives, which can reduce the influence of the background and tree canopy gaps on clustering. Spatial location and gray scale features are obtained by step detection and the insertion rule method, respectively. Bandwidths calculated by spatial location and gray scale features are then used to determine the size of the Gaussian kernel function and in the mean shift clustering. Furthermore, the flood fill method is employed to fill the results of clustering and highlight the region of interest. To prove the effectiveness of tree image abstractions on image clustering, we compared different abstraction levels and achieved the optimal clustering results. For our algorithm, the average segmentation accuracy (SA), over-segmentation rate (OR), and under-segmentation rate (UR) of the crown are 91.21%, 3.54%, and 9.85%, respectively. The average values of the trunk are 92.78%, 8.16%, and 7.93%, respectively. Comparing the results of our method experimentally with other popular tree image segmentation methods, our segmentation method get rid of human interaction and shows higher SA. Meanwhile, this work shows a promising application prospect on visual reconstruction and factors measurement of tree.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2407-2410
• /
• 2003

In this paper, we propose a new stereoscopic video conversion methodology that converts two-dimensional (2-D) MPEG-4 video to stereoscopic video. In MPEG-4, each Image is composed of background object and primary object. In the first step of the conversion methodology, the camera motion type is determined for stereo Image generation. In the second step, the object-based stereo image generation is carried out. The background object makes use of a current image and a delayed image for its stereo image generation. On the other hand, the primary object uses a current image and its horizontally-shifted version to avoid the possible vertical parallax that could happen. Furthermore, URFA(Uncovered Region Filling Algorithm) is applied in the uncovered region which might be created after the stereo image generation of a primary object. In our experiment, show MPEG-4 test video and its stereoscopic video based upon out proposed methodology and analyze Its results.

• 한국컴퓨터그래픽스학회논문지
• /
• 제20권3호
• /
• pp.1-8
• /
• 2014

스마트폰의 전면 및 후면 카메라를 이용하여 동시에 획득한 전경 이미지와 배경 이미지에서, 전경 이미지의 일부분인 전경 물체를 추출하여 배경 이미지에 합성하는 방법을 제시한다. 최근의 고사양 스마트폰은 대개 두 개의 카메라를 가지고 있고, 사진을 촬영하는 과정에서 미리보기 화면을 제공한다. 전면 카메라로부터 전경 이미지를 획득하는 과정에서 미리보기 화면의 비디오에 대한 옵티컬 플로우를 이용하여 전경 물체를 추출한다. 추출된 전경 물체와 배경 화면을 단순히 합성한 후, 전경 물체와 배경화면의 경계에서 가중치 경계 블렌딩을 이용하여 시각적으로 부드러운 경계를 갖는 합성을 수행한다. 화소 수준의 조밀한 옵티컬 플로우의 계산은 고사양의 스마트폰에서도 상당히 느리기 때문에, 전경 물체 추출을 위한 마스크의 계산을 저해상도에서 수행하여 계산시간을 크게 절약할 수 있다. 실험적 결과에 의하면 제안하는 방법은 더 적은 계산 시간을 사용하며, 널리 사용되는 Poisson 이미지 합성 방법에 비하여 시각적으로 더 우수한 결과를 얻을 수 있다. 제안하는 방법은 Poisson 이미지 합성 방법에서 자주 관찰되는 색 번짐 결점을 가중치 경계 블렌딩을 이용하여 제한적인 수준에서 극복할 수 있다.

• 한국컴퓨터정보학회논문지
• /
• 제20권7호
• /
• pp.17-24
• /
• 2015

In this paper, we propose a method to solve ghosting problem. To generate adaptive background, using an exponentially decreasing number of frames, may improve object detection performance. To extract moving objects from the background by using a differential image, detection error may be caused by object rotations or environmental changes. A ghosting problem can be issue-driven when there are outdoor environmental changes and moving objects. We studied that a differential image by adaptive background may reduce the ghosting problem. In experimental results, we test that our method can solve the ghosting problem.

• 디지털산업정보학회논문지
• /
• 제13권4호
• /
• pp.71-79
• /
• 2017

Recently, Fire watching and dangerous substances monitoring system has been being developed to enhance various fire related security. It is generally assumed that fire flame extraction plays a very important role on this monitoring system. In this study, we propose the fire flame extraction method of Non-Residential Facilities based on core object extraction in image. A core object is defined as a comparatively large object at center of the image. First of all, an input image and its decreased resolution image are segmented. Segmented regions are classified as the outer or the inner region. The outer region is adjacent to boundaries of the image and the rest is not. Then core object regions and core background regions are selected from the inner region and the outer region, respectively. Core object regions are the representative regions for the object and are selected by using the information about the region size and location. Each inner region is classified into foreground or background region by comparing its values of a color histogram intersection of the inner region against the core object region and the core background region. Finally, the extracted core object region is determined as fire flame object in the image. Through experiments, we find that to provide a basic measures can respond effectively and quickly to fire in non-residential facilities.

• 한국의류학회지
• /
• 제27권7호
• /
• pp.851-861
• /
• 2003

The objectives of this study were to investigate the effect of perceiver's fashion involvement, clothing color, and background of object person on image perceptions of clothing, and to examine how clothing color preference vary according to perceiver's fashion involvement. Subjects were 273 college women in the metropolitan area of Seoul. The T-shirt was changed into 11 colors by using the CAD system. Five factors were derived to account for the dimensions of image perception. These were individuality, elegance, femininity, activity, and neatness. Perceiver's fashion involvement gave a significant influence on perception of individuality. Clothing color gave significant influences on 5 image dimensions. White and beige were evaluated neat image. Neatness factor had an interaction effect by fashion involvement and clothing color. The high involvement group evaluated white and beige shirt more neatly, and orange and yellow less neatly than the low involvement group. Individuality and elegance had an interaction effect by fashion involvement and background of object person. The high involvement group liked red, violet, and black shirt more than the low involvement. Refined and becomingness image gave significant influences on clothing color preference in both high and low involvement groups.

• 복식문화연구
• /
• 제22권3호
• /
• pp.399-410
• /
• 2014

The purpose of this study was to investigate emotional images and preference of knitwear by tone on tone combination. The subjects were 357 university students in Daejeon and Chungnam province, and the measuring instruments were 6 stimuli manipulated by color and tone combination type of background and pattern in the tone and tone combination, and self-administrated questionnaires consisted of emotional images items, preference items, and subjects' demographics attributions. The data were analyzed by Cronbach's ${\alpha}$, factor analysis, t-test, MANOVA and Duncan's multiple range test, using SPSS program. The results were as follows. First, four factors (attractiveness, conspicuity, mildness, and activity) are emerged on emotional images of knitwear. Second, color had main effects on emotional images and preference. Gray color was perceived as most attractive image and more preferred than others. Third, tone combination type had some effects on emotional images. Vivid tone background/light tone pattern was perceived more attractive image but less conspicuous and mild than light tone background/vivid tone pattern. Forth, subjects' gender had an effects on conspicuous image. Male was perceived more conspicuous image on knitwear stimuli than female. Fifth, color and subjects' gender had interaction effects on attractiveness image and preference. Male perceived that blue is more attractive and preferred than female.

• 산업경영시스템학회지
• /
• 제43권1호
• /
• pp.16-25
• /
• 2020

Vegetation segmentation in a field color image is a process of distinguishing vegetation objects of interests like crops and weeds from a background of soil and/or other residues. The performance of the process is crucial in automatic precision agriculture which includes weed control and crop status monitoring. To facilitate the segmentation, color indices have predominantly been used to transform the color image into its gray-scale image. A thresholding technique like the Otsu method is then applied to distinguish vegetation parts from the background. An obvious demerit of the thresholding based segmentation will be that classification of each pixel into vegetation or background is carried out solely by using the color feature of the pixel itself without taking into account color features of its neighboring pixels. This paper presents a new pixel-based segmentation method which employs a multi-layer perceptron neural network to classify the gray-scale image into vegetation and nonvegetation pixels. The input data of the neural network for each pixel are 2-dimensional gray-level values surrounding the pixel. To generate a gray-scale image from a raw RGB color image, a well-known color index called Excess Green minus Excess Red Index was used. Experimental results using 80 field images of 4 vegetation species demonstrate the superiority of the neural network to existing threshold-based segmentation methods in terms of accuracy, precision, recall, and harmonic mean.