• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.288-296
• /
• 2021

Automated face recognition in a runtime environment is gaining more and more important in the fields of surveillance and urban security. This is a difficult task keeping in mind the constantly volatile image landscape with varying features and attributes. For a system to be beneficial in industrial settings, it is pertinent that its efficiency isn't compromised when running on roads, intersections, and busy streets. However, recognition in such uncontrolled circumstances is a major problem in real-life applications. In this paper, the main problem of face recognition in which full face is not visible (Occlusion). This is a common occurrence as any person can change his features by wearing a scarf, sunglass or by merely growing a mustache or beard. Such types of discrepancies in facial appearance are frequently stumbled upon in an uncontrolled circumstance and possibly will be a reason to the security systems which are based upon face recognition. These types of variations are very common in a real-life environment. It has been analyzed that it has been studied less in literature but now researchers have a major focus on this type of variation. Existing state-of-the-art techniques suffer from several limitations. Most significant amongst them are low level of usability and poor response time in case of any calamity. In this paper, an improved face recognition system is developed to solve the problem of occlusion known as FRS-OCC. To build the FRS-OCC system, the color and texture features are used and then an incremental learning algorithm (Learn++) to select more informative features. Afterward, the trained stack-based autoencoder (SAE) deep learning algorithm is used to recognize a human face. Overall, the FRS-OCC system is used to introduce such algorithms which enhance the response time to guarantee a benchmark quality of service in any situation. To test and evaluate the performance of the proposed FRS-OCC system, the AR face dataset is utilized. On average, the FRS-OCC system is outperformed and achieved SE of 98.82%, SP of 98.49%, AC of 98.76% and AUC of 0.9995 compared to other state-of-the-art methods. The obtained results indicate that the FRS-OCC system can be used in any surveillance application.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.38 no.5_2
• /
• pp.186-193
• /
• 2010

The purpose of this study was to survey the citizens for their satisfaction with the outdoor landscape lighting in Gyeongju Historic Areas registered as UNESCO World Cultural Heritage in November 2000 and thereupon, provide for some basic data useful to the design of the outdoor landscape lighting for the cultural properties. As a result of examining the conditions of the outdoor landscape lighting in Wolseong Zone of Anapji, Banwolseong, Dongbu Sajeokji, Cheomseongdae and Gyerim, there were found 391 lighting fixtures of 12 types in Anapji, 138 lightings of 4 types in Banwolseong, 38 lightings of 6 types in Cheomseongdae, 28 lightings of 3 types in Dongbu Sajeokji and 54 lightings of 5 types in Gyerim. As a result of analyzing citizens' satisfaction with the outdoor landscape lighting, it was found that citizens were satisfied more or less with the nightscape image changed by the outdoor landscape lighting; their satisfaction scored 3.836 on average for Anapji on a 5-point Likert type scale, 3.516 for Banwolseong, 3.446 for Dongbu Sajeokji, 3.650 for Cheomseongdae and 3.479 for Gyerim. However, citizens' satisfaction with the originality of the nightscape was generally low: 3.055 for Anapji, 2.914 for Cheomseongdae, 2.877 for Banwolseong, 2.847 for Gyerim and 2.665 for Dongbu Sajeokji. On the other hand, since most of the lighting fixtures were installed as inserted lights or floodlights, the color tones of light source were relatively highly distinctive, but the peripheral spaces around the cultural properties were rather dark, which means that citizens were feeling inconvenient more or less for using the amenities such as bench or waste box. All in all, their satisfaction with the outdoor landscape at the sample zone at night scored 2.981, lower than the normal level.

• Journal of Intelligence and Information Systems
• /
• v.8 no.1
• /
• pp.15-25
• /
• 2002

This paper proposes a vehicle license plate recognition system, which has relatively a simple structure and is highly tolerant of noise, by using the DCT(Discrete Cosine Transform) coefficients extracted from the character region of a license plate and the LVQ(Learning Vector Quantization) neural network. The image of a license plate is taken from a captured vehicle image based on RGB color information, and the character region is derived by the histogram of the license plate and the relative position of individual characters in the plate. The feature vector obtained by the DCT of extracted character region is utilized as an input to the LVQ neural classifier fur the recognition process. In the experiment, 109 vehicle images captured under various types of circumstances were tested with the proposed method, and the relatively high extraction rate of license plates and recognition rate were achieved.

• Proceedings of the Korea Society of Costume Conference
• /
• 2001.08a
• /
• pp.34-36
• /
• 2001

Chirimen (silk crepe) has been one of Japan's most distinctive textiles since times and has gained a reputation worldwide as the supreme example of Japanese costume. It is because of its distinctive quality and features, transcending the history, lacation and lacal of the people who wear this form of clothing, that chirimen has continued to highly valued over a long historical period. There is a wide range of literature on the subject of chirimen written from the standpoints of introducing the various types of material, discussing its history, and looking at the origins of the textile unions. However, most such writings are little more than fragmentary attempts to describe these matters from an empirical and publicity-oriented position. Very little serious research has ever been published in this area. In the present study I examine the features of chirimen. I began by directly interviewing kimono wholesalers, kimono stores and Western-style clothing stores on the subject of chirimen in order to establish a clear image of this fabric. I then went on to examine the subject experimentally in terms of the physical properties of the fabric in connection with the features of this image. In the study of the physical properties of the material, I selected habutae as a silk fabric to offer comparisons with chirimen. Habutae is used frequently together with chirimen in garments such as semi-formal visiting kimono (homongi), kimono in non-color fabric (ironashiji), mouming kimono (mofuku), broad-sleeved kimono (tomesode and furisode), and undergarments such ad juban.

• Journal of the Korea Computer Graphics Society
• /
• v.24 no.2
• /
• pp.1-9
• /
• 2018

In this paper, we propose a method to restore corrupted black and white facial images to color. Previous studies have shown that when coloring damaged black and white photographs, such as old ID photographs, the area around the damaged area is often incorrectly colored. To solve this problem, this paper proposes a method of restoring the damaged area of input photo first and then performing colorization based on the result. The proposed method consists of two steps: BEGAN (Boundary Equivalent Generative Adversarial Networks) model based restoration and CNN (Convolutional Neural Network) based coloring. Our method uses the BEGAN model, which enables a clearer and higher resolution image restoration than the existing methods using the DCGAN (Deep Convolutional Generative Adversarial Networks) model for image restoration, and performs colorization based on the restored black and white image. Finally, we confirmed that the experimental results of various types of facial images and masks can show realistic color restoration results in many cases compared with the previous studies.

• The Research Journal of the Costume Culture
• /
• v.19 no.4
• /
• pp.661-673
• /
• 2011

This study aimed to identify the intrinsic characteristics of camouflage patterns by reviewing their origin, transitions and types from a theoretical background and analyzing their forms of expression in contemporary fashion. For a literature review and an empirical analysis of the camouflage patterns used in contemporary fashion, the study referred to domestic and foreign fashion magazines published between 2000 S/S and 2010 S/S, including Gap Press, Fashion News, Vogue and Harper's Bazaar, and other related data available on the internet. The findings of this study show that the forms of camouflage patterns used in contemporary fashion can be divided into four types: abstract patterns, plant patterns of flowers or leaves, animal patterns and dotted patterns. In terms of coloration, the camouflage patterns work to refresh the design, breaking from the image of military uniforms through the use of a wide range of color variation and combinations as well as the traditional camouflage colors based on khaki and beige. In terms of expression, most of them utilize printing. However, other techniques of expression, such as embroidery, beading, knitting, and collages are used to emphasize the beauty of handcrafted decorations along with the aesthetic value of reliefs. Through these tendencies of expression, the characteristics of contemporary fashion using camouflage are explained with an emphasis on feminine beauty, the expression of neutrality, and the use as decorative factors.

• Science of Emotion and Sensibility
• /
• v.2 no.2
• /
• pp.67-74
• /
• 1999

본 연구는 실제 현장에서 적용할 수 있는 보다 구체적인 감성 데이터를 제공하기 위한 시도로서, 메이크업의 주요한 색채특성을 평가변인으로 하여 칼라 시뮬레이션 실험 및 분석을 실시하여, 최종적으로 색채감성 분석기법에 의한 이미지 유형별 예측모델을 작성하였다. 그 결과, $\ulcorner$품위있는.귀족적인$\lrcorner$, $\ulcorner$깔끔한.여성스러운$\lrcorner$, $\ulcorner$강렬한.도발적인$\lrcorner$, $\ulcorner$캐주얼한.경쾌한$\lrcorner$, $\ulcorner$수수한.부드러운$\lrcorner$의 5가지 이미지유형이 추출되었고, 이미지유형별로 이미지와 색채특성간의 정량적 예측모델을 작성한 후, 그 결과를 토대로 이미지유형별 색채팔레트를 제시하였다.

• Korean Institute of Interior Design Journal
• /
• no.3
• /
• pp.64-70
• /
• 1994

The objective of this study is to provide recommendations for the interir design of motor showroom as a sales policy. ten cases of motor showrooms were selected from already observed 50 showrooms in Seoul area. findings revealed that the car industries of Korea should meet the strong needs of differentiated sales policy, and the showroom design was an important factor which influenced client's pruchasing power. From these findings and analyses, this study suggests that each brand has to represent the typical total image to appeal to the consumer strongly . Additionally each showroom should be flexible in modification to meet the diverse conditions such as the location, required function and the trend of consumers. In conclusion , researchers provided 6 types of recommendations in terms of floor plan and interior elements such as circulation path, moduled furniture and objects color and lighting variation . Hopely, this research provides more functional and comfortable environment of automobile showrooms for consumers and companies.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1999.11a
• /
• pp.324-329
• /
• 1999

본 연구는 실제 현장에서 적용할 수 있는 보다 구체적인 감성 데이터를 제공하기 위한 시도로서, 메이크업의 주요한 색채특성을 정가변인으로 하여 칼라 시뮬레이션 실험을 실시한 후, 색채감성 분석기법에 의한 이미지유형별 예측모델을 작성하였다. 그 결과, $\ulcorner$품위있는ㆍ귀족적인$\lrcorner$, $\ulcorner$깔끔한ㆍ여성스러운$\lrcorner$, $\ulcorner$강렬한ㆍ도발적인$\lrcorner$, $\ulcorner$캐주얼한ㆍ경쾌한$\lrcorner$, $\ulcorner$수수한ㆍ부드러운$\lrcorner$ 의 5가지 이미지유형이 추출되었고, 이미지유형별로 이미지와 색채특성간의 정량적 예측모델을 작성한 후, 그 결과를 토대로 이미지유형별 색채팔레트를 제시하였다.

• The KIPS Transactions:PartB
• /
• v.14B no.4
• /
• pp.249-254
• /
• 2007

A mobile robot with various types of sensors and wireless camera is introduced. We show this mobile robot can detect objects well by combining the results of active sensors and image processing algorithm. First, to detect objects, active sensors such as infrared rays sensors and supersonic waves sensors are employed together and calculates the distance in real time between the object and the robot using sensor's output. The difference between the measured value and calculated value is less than 5%. We focus on how to detect a object region well using image processing algorithm because it gives robots the ability of working for human. This paper suggests effective visual detecting system for moving objects with specified color and motion information. The proposed method includes the object extraction and definition process which uses color transformation and AWUPC computation to decide the existence of moving object. Shape information and signature algorithm are used to segment the objects from background regardless of shape changes. We add weighing values to each results from sensors and the camera. Final results are combined to only one value which represents the probability of an object in the limited distance. Sensor fusion technique improves the detection rate at least 7% higher than the technique using individual sensor.