• Journal of the Korea Society of Computer and Information
• /
• v.17 no.7
• /
• pp.45-52
• /
• 2012

In this paper, an crowd density in elevator estimation method based on multi-class Adaboost classifier is proposed. The SOM (Self-Organizing Map) based conventional methods have shown insufficient performance in practical scenarios and have weakness for low reproducibility. The proposed method estimates the crowd density using multi-class Adaboost classifier with texture features, namely, GLDM(Grey-Level Dependency Matrix) or GGDM(Grey-Gradient Dependency Matrix). In order to classify into multi-label, weak classifier which have better performance is generated by modifying a weight update equation of general Adaboost algorithm. The crowd density is classified into four categories depending on the number of persons in the crowd, which can be 0 person, 1-2 people, 3-4 people, and 5 or more people. The experimental results under indoor environment show the proposed method improves detection rate by about 20% compared to that of the conventional method.

• Journal of Broadcast Engineering
• /
• v.8 no.1
• /
• pp.91-100
• /
• 2003

In this paper, to improve the retrieval Performance, an efficient combination of the MPEG-7 visual descriptors, such as the edge histogram descriptor (EHD), the color layout descriptor (CLD), and the homogeneous texture descriptor (HTD), is proposed in the framework of the relevance feedback approach. The EHD represents spatial distribution of edges in local image regions and it is considered as an important feature to represent the content of the image. The CLD specifies spatial distribution of colors and is widely used in image retrieval due to its simplicity and fast operation speed. The HTD describes precise statistical distribution of the image texture. Both the feature vector for the query image and the weighting factors among the combined descriptors are adaptively determined during the relevance feedback. Experimental results show that the proposed method improves the retrieval performance significantly tot natural images.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.2D
• /
• pp.311-316
• /
• 2006

Despite geospatial information systems are widely used in many different fields as a powerful tool for spatial analysis and decision-making, their capabilities to handle realistic 3-D urban environment are very limited. The objective of this work is to integrate the recent developments in 3-D modeling and visualization into GIS to enhance its 3-D capabilities. To achieve a photorealistic view, building models are collected from a pair of aerial stereo images. Roof and wall textures are respectively obtained from ortho-rectified aerial image and ground photography. This study is implemented by using ArcGIS as the work platform and ArcObjects and Visual Basic as development tools. Presented in this paper are 3-D geometric modeling and its data structure, texture creation and its association with the geometric model. As the results, photorealistic views of Purdue University campus are created and rendered with ArcScene.

• Journal of Korean Society of Rural Planning
• /
• v.24 no.4
• /
• pp.135-146
• /
• 2018

A Visual landscape planning and management system has been introduced and implemented by each ministry so as to solve the problems of visual landscape destruction due to recognition on the value of natural landscape of beautiful territory and various development projects. At present, this system emphasizes the importance of the visual and perceptual aspect of the landscape however, there is a lack of techniques required for comprehensively predicting, evaluating, and managing it. Furthermore, sustainable landscape management after the completion of development projects has been inadequately carried out, as the focus has been only on consultation in the planning process of the development project in institutional performance. To this end, we presented objective and standardized criteria to predict and judge the effects of development projects on landscapes before project implementation. During the implementation of the development project, the influence of the visual landscape becomes accumulated in the construction progress stage. There is a need to identify the main viewpoints and to examine the continuous changes in the landscape-influencing factors, owing to the remarkable influences on the landscape, such as the change in the topography and the change caused by the artificial structure. During the stage of managing the influence on the visual landscape after the completion of the project, the influence on landscape should be monitored by measuring the change in the continuous landscape-influencing factors and determining the extent to which the actual reduction plan has been implemented. These processes should be performed continuously to maintain the quality of the visual landscape. The change in the landscape caused by the development project is shown to cause relatively greater visual damage than other factors composing the landscape owing to the influence of the artificial factors including the structure or the building. This shows that not only detailed examination of the visual impact before the development project but also continuous management is required during and after the development project. For this purpose, we derived eight landscape-influencing factors including form/shape, line, color, texture, scale/volume, height, skyline, and landscape control point. The proposed considering to be of high utilization in that it has a clear target of the landscape influencing factors.

• Science of Emotion and Sensibility
• /
• v.23 no.4
• /
• pp.21-32
• /
• 2020

The perception of a fashion product may vary depending on the texture and color of its material. Additionally, the product may appear differently in person versus on a digital screen. Therefore, in the present study, we sought to investigate the differences in visual sensibility evaluation between materials in person and on digital screens. In this study, three pairs of visual sensibility adjectives were tested for 60 samples selected as fashion materials. Fashion materials were divided into colors, embossings, and visual clarity categories. Results showed that each color had the same sense during in-person and digital evaluation. In terms of visual sensibility according to embossing, both in-person and digital evaluations of materials with embossings were found to have the same visual sense, whereas those without embossings looked different between in-person and digital evaluations. Assessments based on visual classification showed that both in-person and digital evaluations had the same sensibility. This study is meaningful in suggesting that when evaluating the visual sense of fashion material, the sensation for the digital screen versus in person may be different in some cases.

• The International Journal of Costume Culture
• /
• v.7 no.2
• /
• pp.87-102
• /
• 2004

By introducing Mondrian's creative world into the field of fashion design, I examined how its application can satisfy not only visual expressions but also the desire of fashion design for its simplicity, individuality, and sensitivity. As a program developing designs and guiding how to produce, the textile CAD system helps to develop a variety of textile systems. In case of dying or textile printing, a variety of free expressions of print patterns and functional color simulations are possible by the configuration of colors or enlargement of design. It can also confirm the flexible simulation with a variety of color changes through the monitor by treating the knit design with dots. Especially in case of consulting for the design with ordering customers, the system is very speedy and effective, because it is possible to correct on the spot those complicated elements of designs and color sensation and see the prints in the light of marketing, processing and artistic value. Mondrian's Art, beauty of balance and proportion in the Mondrian's plastic forms, the changes of coloring and texture were added into vertical and horizontal lines and the divisions of faces for the dressmaking. Whether they were the reciprocal action of human body, texture and color or the reciprocal action of human body and colors, these changes will be interpreted differently, depending on the individuals' experiences and psychological moods of situations. The emphases of the sense are also different, depending on the activity and functionality.

• The Research Journal of the Costume Culture
• /
• v.15 no.5
• /
• pp.749-759
• /
• 2007

As the traditional style is treated as one of the important themes in fashion recently, how to apply the formative character in Korean and Japanese traditional dress to modern fashion is searched through actual analysis of photograph material, Both design formative elements were confirmed by clothing and fashion department majors through visual data so that 20 pieces of them were selected as final analysis object. Korean traditional dress form in modern fashion emphasizes curvaceousness as plane division. On the other hand, that of Japanese shows straight line, layered, belt, big look through up & down connection style. Color in Korean traditional dress prefers white and original color and modern fashion displays the natural beauty through harmony of similar colors ; that of Japanese based on natural color such as persimmon color cherishes natural beauty and implicit moderation showing harmony of various original color with brilliance and neutral color. While texture in Korean traditional dress was fine and exquisite, that of Japanese preferred coarse and tactile ones. In motif, Korea was natural and geometric but Japanese variously used complex and geometric ones. Likewise, the result suggests that the formative character in Korean and Japanese modern fashion affects the modern dress format as new aesthetic sense and takes on more complicated and subtle aspect in basic form, not just use so far.

• Journal of Korea Multimedia Society
• /
• v.8 no.4
• /
• pp.516-524
• /
• 2005

In this paper, a new watermarking scheme based on the POCS theory and human visual system is proposed. Using the POCS theory, watermarks are embedded into imperceptible image regions such as edge and strong texture area in the spatial domain. Also it is inserted into middle frequency band in the transform domain to achieve the robustness against compression and filtering, etc. In addition, different gain factors are employed into blocks classified by considering texture masking effect. By doing so, the proposed method has a novel property of having both the imperceptibility and the robustness simultaneously. Simulation results show that the proposed method has an excellent performance better than conventional approaches.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.268-269
• /
• 2008

Moving object detection is a fundamental technique in visual surveillance. Robust technique to enhance performance of moving object detection is required for several bad conditions in real external circumtance. In case of sudden illumination change in outdoor condition, many objects are determined as moving object though they are not really moving, but just their illumination changes. This makes the detection result untrustworthy. In this paper, robust moving object detection to sudden illumination change using gaussian mixture background model and new texture information using background from the weighted sum of recent images is proposed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.3
• /
• pp.1761-1784
• /
• 2017

In order to improve the embedding rate of reversible watermarking algorithm for digital image and enhance the imperceptibility of the watermarked image, an adaptive reversible image watermarking algorithm based on DE is proposed. By analyzing the traditional DE algorithm and the generalized DE algorithm, an improved difference expansion algorithm is proposed. Through the analysis of image texture features, the improved algorithm is used for embedding and extracting the watermark. At the same time, in order to improve the embedding capacity and visual quality, the improved algorithm is optimized in this paper. Simulation results show that the proposed algorithm can not only achieve the blind extraction, but also significantly heighten the embedded capacity and non-perception. Moreover, compared with similar algorithms, it is easy to implement, and the quality of the watermarked images is high.