• Proceedings of the KSRS Conference
• /
• 2009.03a
• /
• pp.13-17
• /
• 2009

고해상도 위성영상의 분류 기술은 최근 가장 활발히 연구되고 있는 분야 중 하나로 텍스쳐(texture), NDVI, PCA 영상 등 다양한 전처리 정보들을 추출하고 이를 멀티스펙트럴 밴드와 조합하여 분류 정확도를 높이는 기술을 개발하는 연구들이 주를 이루고 있다. 고해상도 위성영상에서 건물의 그림자와 옆벽면의 폐색 지역은 개체 추출 및 분류를 방해하는 주된 요인이 되며, 다양한 형태와 분광특성을 갖는 개개의 건물은 자동 분류 과정을 통해 제대로 식별되지 않는다는 한계를 갖는다. 이에 본 연구에서는 KOMPSAT-2 단영상으로부터 효율적으로 건물 정보 및 토지피복을 분류하기 위하여, 추출된 건물 정보를 바탕으로 건물의 그림자와 폐색지역을 보정한 후 비건물 지역에 대한 분류를 수행하여 분류 정확도를 높이고자 하였다. 우선 삼각벡터구조 기반의 반자동 인터페이스를 이용하여 건물의 3차원 모델 및 그림자 영역을 추출하고 이로부터 추출된 그림자 영역을 효과적으로 보정하기 위해 반복 선형회귀 연산을 이용한 그림자 보정을 수행한 후 inpainting 기법을 건물 폐색영역 복원에 적용하여 영상의 품질을 향상시켰다. 이러한 과정을 통해 도심 지역의 영상 분석에 있어 가장 큰 오차를 일으키는 인공물의 그림자와 폐색에 의한 오차를 최소화한 후 분류에 적용하여 이를 보정 전 영상을 이용한 분류 결과와 비교하였다.

• Journal of IKEEE
• /
• v.18 no.4
• /
• pp.536-543
• /
• 2014

Terrain classification is still a challenging issue in image processing, especially with high resolution satellite images. The well-known obstacles include low accuracy in the detection of targets, especially for the case of man-made structures, such as buildings and roads. In this paper, we present an efficient approach to classify and detect building footprints, foliage, grass and road from high resolution grayscale satellite images. Our contribution is to build a strong classifier using AdaBoost based on a combination of co-occurrence and Haar-like features. We expect that the inclusion of Harr-like feature improves the classification performance of the man-made structures, since Haar-like feature is extracted from corner features and rectangle features. Also, the AdaBoost algorithm selects only critical features and generates an extremely efficient classifier. Experimental result indicates that the classification accuracy of AdaBoost classifier is much higher than that of the conventional classifier using back propagation algorithm. Also, the inclusion of Harr-like feature significantly improves the classification accuracy. The accuracy of the proposed method is 98.4% for the target detection and 92.8% for the classification on high resolution satellite images.

• Journal of Broadcast Engineering
• /
• v.25 no.1
• /
• pp.58-66
• /
• 2020

The blur effect, which is generated by various external factors such as out-of-focus and object movement, degrades high-frequency components in the original sharp image. Based on this observation, we propose a novel method for blur detection using textural features. Specifically, the proposed method simultaneously adopts learning-based and watershed-based textural features, which effectively detect the blur on various situations. Moreover, we employ the region-based refinement to improve the processing time while also increasing detection accuracy. Experimental results demonstrate that the proposed method provides the competitive performance compared to previous approaches in literature.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.6
• /
• pp.464-468
• /
• 2009

In this paper we propose an image-based approach, which is different from the traditional flow cytometric method to detect shape of apoptosis cells. This method can overcome the defects of cytometry and give precise recognition of apoptosis cells. In this work K-means clustering was used to do the rough segmentation and an active contour model, called 'snake' was used to do the precise edge detection. And then some features were extracted including physical feature, shape descriptor and texture features of the apoptosis cells. Finally a Mahalanobis distance classifier classifies the segmentation images as apoptosis and non-apoptosis cell.

• Tribology and Lubricants
• /
• v.24 no.6
• /
• pp.320-325
• /
• 2008

The recent industrial application requires technical methods to get the cutting fluid droplet surfaces in particular from the viewpoint of topography and micro texture. To characterize the surface topography of droplet, the combination of the confocal laser scanning microscope (CLSM) and wavelet filtering is well suited for obtaining the droplet geometry encountered in tribological research. This technique indicates a better agreement in obtaining an appropriate droplet surface obtained by the CLSM over a detail range of surface accuracy (resolution: $2{\mu}m$). And the results allow an excellent accuracy in a measurement of a droplet surface. The combination of extended focal depth measurement configured and multi-scale wavelet filtering has proven that it can construct a droplet surface in a successive and accurate way. A multi-scale approach of wavelet filtering was developed based on the decomposition and reconstruction of droplet surface by 2D wavelet transform using db9 (a mother wavelet of daubechies). Also this technique can be extended to characterize the quantification of droplet properties and other field in a wide range of scales. Finally this method is verified to be a better droplet surface modeling in a micro scale arising in a mist machining.

• Journal of Fashion Business
• /
• v.12 no.2
• /
• pp.42-58
• /
• 2008

The purpose of this study is to examine actual design cases of decorative detail in the Art Nouveau style from the end of 19th century to the beginning of 20th century, and create designs and fashion works to meet our contemporary fashion trends by means of over-decorative style, a characteristic of decorative detail. The characteristics of decorative detail in the Art Nouveau style can be outlined as follows: First, pleats appear with two major feels of solidity, undulated and curvilinear solidity based on gather(ruffle, frill/ flare and flounce) and regular and linear solidity based on linear pleats or tucks. Second, embroidery appears in various patterns developed with stitch of solid feel as well as a variety of coloration effects. Third, attachments are expressed by means of independent motif(applique, gloss effects(beads, sequins), affluent texture and mobility(fur, feather). Moreover, according to technical characteristics and expressive aspects of pleats, embroidery and attachments, it is found that decoration detail in the era of Art Nouveau is over-decoration style. Indeed, it appears in major expressive aspects such as rhythmical solid type, detailed prominence type, superficial touch type and profound volume type.

• Journal of Fashion Business
• /
• v.3 no.4
• /
• pp.113-129
• /
• 1999

The purpose of this study is to discover the changes and characteristis of modern knitwears from the 1920's to the 1990's. The result of this study is as follows: The popular knitwears in the 1920's had a simple boxy-line and modern unisex image with a sporty look. The knitwears in the 1930's-1950's had seen more short, feminine detail and texture, fit silhouette with syntheyic fibers. In the 1960's, the knitwears of sporty look and unisex style was popularized by young peaples, and crochet with handkniting by the fiber artists was popularized. In the 1970's-80's, the layered looks and unisex styles of knitwears were popularized by influence of a ecology mood and a woman movemant. And various patterns was developed with the computer machine. The items of outer knitwear was increased by the use of fancy yarns and the knitwears as the total fashion was popularized. In the 1990s, the knitwears had a very forceful characteristics by the mixed style and the technique of design developed into the post-modernism. The key words of the character of the modern knitwears are funtional pursuit, unisex, high value, hightechnique, art. By the change of the life style and the develope of technical innovation, the knitwears will be the key item to leading the fashion in the 21th.

• Journal of the Semiconductor & Display Technology
• /
• v.15 no.2
• /
• pp.61-65
• /
• 2016

Facial feature detection is a fundamental function in the field of computer vision such as security, bio-metrics, 3D modeling, and face recognition. There are many algorithms for the function, active shape model is one of the most popular local texture models. This paper addresses issues related to face detection, and implements an efficient extraction algorithm for extracting the facial feature points to use on iOS platform. In this paper, we extend the original ASM algorithm to improve its performance by four modifications. First, to detect a face and to initialize the shape model, we apply a face detection API provided from iOS CoreImage framework. Second, we construct a weighted local structure model for landmarks to utilize the edge points of the face contour. Third, we build a modified model definition and fitting more landmarks than the classical ASM. And last, we extend and build two-dimensional profile model for detecting faces within input images. The proposed algorithm is evaluated on experimental test set containing over 500 face images, and found to successfully extract facial feature points, clearly outperforming the original ASM.

• Korean Journal of Human Ecology
• /
• v.2 no.1
• /
• pp.33-44
• /
• 1993

It is interesting that the costume in the period of romanticism was very fantastic and peculiar in its aspects. The romanticism in the fashion theme of these days' mode represents the image of this France romanticism. Costume has unseparable relations with the style of art in the same period. Especially, plastic art has logical connection with costume because it is an art through silhouette, line, color and texture felt by visional and solid feelings. This kind of study is important in order to understand the fashion of today, to anticipate the fashion in future and to get recognition of costume as a genre of arts. This study is to analyse and compare the general features in the grown-ups' everyday clothes of France from 1815 to 1850 when costume in the period of romanticism reached its peaks with the art of architecture, paintings, sculpture and technology, with the aid of documentary recordings. The above study explain that costume is expressed by the same plastic art of the period if it coexists in the same cultural background. Finally, we can plan the costume in future on an artistic dimension by understanding correctly the characteristics of plastic art which modern costume pursue from an artistic point of view.

• The Research Journal of the Costume Culture
• /
• v.20 no.2
• /
• pp.129-143
• /
• 2012

This study focuses on the application of collage techniques to contemporary fashion and intends to show that collage techniques have a significant influence on contemporary fashion, leading to a more creative design aesthetic through the combination of fashion and art. The author carried out an empirical analysis focusing on domestic and global fashion collections from 2000S/S to 2010F/W, fashion publications, and internet data, along with a literature review. As a result, the papier-colle approach, as represented by cubism, showed a creative surface effect through the texture of the paper itself by applying real paper and other materials directly to the clothing items. Second, Dadaist ready-made expressed a distortion of the material and freedom of expression by creating a collage with ready-made fashion items and daily necessities. Third, a photomontage expressed unique images by printing various images of photos that contrasted in perspective. In addition to this, beauty in dissonance and a new sense of space by a collage of disparate material. Fourth, decalcomanie was expressed by printing methods, giving a stable image of the symmetry of the perfect landscape as well as the unintended effect of coincidence in abstract images and particular textures. Fifth, assemblage as the representative collage technique of pop art introduced the overall object itself or modified form by combining it with fashion to express three-dimensional aggregate structures.