• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.9
• /
• pp.930-935
• /
• 2014

A Gabor filter is a linear filter used for edge detectionas frequency and orientation representations of Gabor filters are similar to those of the human visual system. In this thesis, we propose a pedestrian detection algorithm using a Gabor filter bank. In order to extract the features of the pedestrian, we use various image processing algorithms and data structure algorithms. First, color image segmentation is performed to consider the information of the RGB color space. Second, histogram equalization is performed to enhance the brightness of the input images. Third, convolution is performed between a Gabor filter bank and the enhanced images. Fourth, statistical values are calculated by using the integral image (summed area table) method. The calculated statistical values are used for the feature matrix of the pedestrian area. To evaluate the proposed algorithm, the INRIA pedestrian database and SVM (Support Vector Machine) are used, and we compare the proposed algorithm and the HOG (Histogram of Oriented Gradient) pedestrian detector, presentlyreferred to as the methodology of pedestrian detection algorithm. The experimental results show that the proposed algorithm is more accurate compared to the HOG pedestrian detector.

• The Research Journal of the Costume Culture
• /
• v.23 no.6
• /
• pp.987-1003
• /
• 2015

The purpose of this study is to supply available data for men's fashion design planning by analyzing the trend and design tendency of the preppy look in the domestic men's collection. In the men's collection of Seoul fashion week from 2011 S/S to 2015 S/S, 494 photos judged to be the preppy look by three design specialists were chosen in Seoul fashion week and style.com's web-site. Design analyses were compiled based on year, season, brands, item, color, material, and silhouette. The preppy look was found often in S/S season, three piece combinations were the most common, and "H", "I" silhouettes were also popular. Refined black and refreshing orange were used with traditional preppy colors like navy, beige, gray, and white. Contrast color arrangement and neutral, moderate tones were seen repeatedly. Two-thirds of fabrics were pattern-less with clean, bulky, and soft textures. Coordinating accessories like hats, backpacks, books, headsets were used frequently. Among the various preppy fashion types, there were 'traditional preppy' faithful to tradition, 'sophisticated preppy' with refined semi-formal look, 'sportive preppy' with active sports sense, and 'natural preppy' with natural and comfortable senses. In a contemporary preppy look, traditional and practical senses are combined with casual and sportive pieces. This study can provide the data for design planning, interpreting, and applying the fashion themes along with contemporary sensibilities since the preppy look is based on cultural history.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.1
• /
• pp.79-88
• /
• 2001

The target such as aircraft operates flares to protect itself from the missile. In general, Infra-red(IR) flares that are hot bodies radiating energy considerably greater than it does, so cause the missile to guide the flare instead of the target. For a precise target tracking in spite of a presence of flares, therefore, the seeker should discriminate the target signal from various clutters including the flare and the background. In this paper, we simulated 2-color rosette scan seeker using IR and UV(UltraViolet) bands. In each wave band, we analyzed the radiant distributions of the target, the flare, and background. These results showed that a simultaneous process in two bands can detect precisely the target.

• Journal of Korea Multimedia Society
• /
• v.6 no.6
• /
• pp.953-961
• /
• 2003

This paper suggests an efficient method to extract face regions from the com]]lex background. Input image is transformed to color space, where the data is independent of the brightness and several regions are extracted by skin color information. Each extracted region is processed as an object. Noise and overlapped objects ate removed. The candidate objects, faces are likely to be included in, are selected by checking the sizes of extracted objects, the XY ratio, and the distribution ratio of skin colors. In this processing, the objects without face are excluded out of candidate regions. The proposed method can be applied for successful extraction of face regions under various conditions such as face extraction with complex background, slanted faces, and face with accessories, etc.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2003.04a
• /
• pp.171-180
• /
• 2003

The merging of different scales or multi-sensor image data is becoming a widely used procedure of the complementary nature of various data sets. Ideally, the merging method should not distort the characteristics of the high-spatial and high-spectral resolution data used. To present an effective merging method for survey of reclaimed land, this paper compares the results of Intensity Hue Saturation (IHS), Principal Component Analysis (PCA), Color Normalized(CN) and High Pass Filter(HPF) methods used to merge the information contents of the high-resolution (6.6 m) Electro-Optical Camera (EOC) panchromatic image of the first Korea Multi-Purpose Satellite 1 (KOMPSAT-1) and the multi-spectral Moderate Resolution Imaging Spectroradiometer (MODIS) image data. The comparison is made by visual evaluation of three-color combination images of IHS, PCA, CN and HPF results based on spatial and spectral characteristics. The use of a contrasted EOC panchromatic image as a substitute for intensity in merged images with MODIS bands 1, 2 and 3 was found to be particularly effective in this study.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.11a
• /
• pp.143-152
• /
• 2004

Researchers seeking geological and environmental information, depend on remote sensing and aerial photographic datum from various commercial satellites and aircraft. However, adverse weather conditions as well as equipment expense limit the ability to collect data anywhere and anytime. To allow for better flexibility in geological and environmental data collection, we have developed a compact, multi-spectral automatic Aerial Photographic system (PKNU2). This system's Multi-spectral camera can record visible (RGB) and infrared (NIR) band (3032＊2008 Pixels) images Visible and infrared band images were obtained from each camera respectively and produced color-infrared composite images to be analyzed for the purpose of the environmental monitoring. However this did not provide quality data. Furthermore, it has the disadvantage of having the stereoscopic overlap area being 60% unsatisfied due to the 12 seconds of storage time of each data The PKNU2 system in contrast, photographed photos of great capacity Thus, with such results, we have been proceeding to develop the advanced PKNU2 (PKNU3) system that consists of a color-infrared spectral camera that can photograph in the visible and near-infrared bands simultaneously using a single sensor, a thermal infrared camera, two 40G computers to store images, and an MPEG board that can compress and transfer data to the computer in real time as well as be able to be mounted onto a helicopter platform.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.95-102
• /
• 2021

The urinalysis, which is universally accessible to the general public, has disadvantages of being less objective using sight and purchasing a separate portable urinalysis machine. However, due to the high penetration rate and performance improvement of smartphone created by the development of mobile communication technology, research on urinalysis services using smartphone has been conducted. In this paper, a new urinalysis screening application based on smartphone was developed by supplementing the limitations of the previously studied urinalysis services. The key technology of the application is urinalysis recognition algorithm and urinalysis pad color determination algorithm through image-processing and contour detection. In order to confirm the performance of the developed application, urinalysis strip was photographed and analyzed from various backgrounds and angles.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.21 no.2
• /
• pp.109-122
• /
• 2019

The purpose of this study is to examine the clothing component information and attributes as the control parameters for the 3D modeling process of the biomorphic clothing sculpture using a parametric methodology. The 3D modeling parameters of biomorphic clothing sculpture were identified as exaggerated silhouette, surface texture, and digital color. The types of exaggerated silhouettes were shoulder and hip exaggeration, shoulder exaggeration, hip exaggeration, vertical exaggeration, and horizontal exaggeration. The types of surface texture were embossed, lacy, furry, and complex textures. The types of digital color were chrome, blur, blend, and acid colors. The characteristics of morphological representation due to the attributes of these control variables were identified as morphological variation, organic morphology, organizational morphology, and realistic morphology. As a result, it was found that the parameter attributes were applied to the biomorphic clothing sculpture parametric design process and developed into various shapes.

• Journal of Broadcast Engineering
• /
• v.13 no.4
• /
• pp.544-553
• /
• 2008

With the development of video editing technology, there are growing uses of overlay text inserted into video contents to provide viewers with better visual understanding. Since the content of the scene or the editor's intention can be well represented by using inserted text, it is useful for video information retrieval and indexing. Most of the previous approaches are based on low-level features, such as edge, color, and texture information. However, existing methods experience difficulties in handling texts with various contrasts or inserted in a complex background. In this paper, we propose a novel framework to localize the overlay text in a video scene. Based on our observation that there exist transient colors between inserted text and its adjacent background a transition map is generated. Then candidate regions are extracted by using the transition map and overlay text is finally determined based on the density of state in each candidate. The proposed method is robust to color, size, position, style, and contrast of overlay text. It is also language free. Text region update between frames is also exploited to reduce the processing time. Experiments are performed on diverse videos to confirm the efficiency of the proposed method.

• Archives of design research
• /
• v.12 no.2
• /
• pp.133-144
• /
• 1999

Considering product as mass of information, it is very critical for designers to have good means of accessing to and organizing information on products. However, designers conventionally depend on their experience, bunch of catalogues, or short visit to some fairs for gathering information on products. There are no systematically organized information for designing new products. If any, those are ones developed by market researchers or engineers who speak fundamentally different language from designers. It is needed to develop the information system through which designer can get insights on the essence of product and communicate information with various persons involved in new product planning. At first, the design information in product planning is discussed and the necessity of development of new design information system is emphasized. Then, product is understood as a composite of various attributes and a set of fundamental attributes of product is defined by surveying and summarizing existing theories of product attributes: namely technological, human, and market attributes. The possibility of new design information system is explored by analyzing various relationships between attributes of different products. Computer program 'DISPP' displays various visual information of product itself, perceptual map, trend slope, profile chart and general information of manufacturer, style, color, price, size. Finally, findings of thesis are concluded and further prospects of the study are proposed.