• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.113-127
• /
• 2012

Face detection methods using image processing have been proposed in many different ways. Generally, the most widely used method for face detection is an Adaboost that is proposed by Viola and Jones. This method uses Haar-like feature for image learning, and the detection performance depends on the learned images. It is well performed to detect face images within a certain distance range, but if the image is far away from the camera, face images become so small that may not detect them with the pre-learned Haar-like feature of the face image. In this paper, we propose the far distance face detection method that combine the Aadaboost of Viola-Jones with a saliency map and user's attention information. Saliency Map is used to select the candidate face images in the input image, face images are finally detected among the candidated regions using the Adaboost with Haar-like feature learned in advance. And the user's eye-tracking information is used to select the interest regions. When a subject is so far away from the camera that it is difficult to detect the face image, we expand the small eye gaze spot region using linear interpolation method and reuse that as input image and can increase the face image detection performance. We confirmed the proposed model has better results than the conventional Adaboost in terms of face image detection performance and computational time.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.4 s.310
• /
• pp.46-54
• /
• 2006

Recently, the important of a personal identification is increasing according to expansion using each on-line commercial transaction and personal ID-card. Although a personal ID-card embedded RFID(Radio Frequency Identification) tag is gradually increased, the way for a person's identification is deficiency. So we need automatic methods. Because RFID tag is vary small storage capacity of memory, it needs effective feature extraction method to store personal biometrics information. We need new recognition method to compare each feature. In this paper, we studied the face verification system using Hippocampal neuron modeling algorithm which can remodel the hippocampal neuron as a principle of a man's brain in engineering, then it can learn the feature vector of the face images very fast. and construct the optimized feature each image. The system is composed of two parts mainly. One is feature extraction using NMF(Non-negative Matrix Factorization) and LDA(Linear Discriminants Analysis) mixture algorithm and the other is hippocampal neuron modeling and recognition simulation experiments confirm the each recognition rate, that are face changes, pose changes and low-level quality image. The results of experiments, we can compare a feature extraction and learning method proposed in this paper of any other methods, and we can confirm that the proposed method is superior to the existing method.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.3
• /
• pp.241-246
• /
• 2018

Because of the mechanical problems of input camera equipment, image restoration process is performed in order to minimize recognition errors due to the noise problem generated in test data image. The image restoration method resolves the noise problem by examining the numbers and positions of the Direct neighbors and the Indirect neighbors for each pixel constituting the test data. As a result, satisfactory recognition result can be obtained by eliminating the noise problem generated in the test data through the image restoration process as much as possible and also by calculating the differences between the learning data and the test data in the area unit, thereby reducing the possibility of recognition error by the noise problem.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.881-884
• /
• 2017

좋은 특징을 도출할 수 있는 신경망은 곧 대상을 잘 이해하고 있는 신경망을 의미한다. 그러나 얼굴과 같이 유사한 이미지를 분류하기 위해서는 신경망이 좀 더 구분되는 특징을 도출해야한다. 본 논문에서는 얼굴과 같이 유사도한 이미지를 분류하기 위해 오차함수에 중심확장(Center Expansion)이라는 오차를 추가한다. 중심확장은 도출된 특징이 밀집되면 클래스를 분류하는 매니폴드를 구하기 어려워져 분류 성능이 하락되는 문제를 해결하기 위해 제안한 것으로 특징이 밀집될 가능성이 높은 부분에 특징이 도출되지 않도록 강제하는 방식이다. 학습 시 활용하는 오차는 일반적으로 분류 문제를 위해 사용되는 softmax cross-entropy 오차와 각 클래스의 분산을 줄이는 오차 그리고 제안한 중심확장 오차를 조합해 구할 것이다. 본 논문에서는 제안한 중심확장 오차를 조합한 모델과 조합되지 않은 모델이 결과적으로 특징 도출과 분류에 어떠한 영향을 주었는지 알아볼 것이다. 중심확장을 조합해 학습한 모델이 어떤 영향을 주었는지 알기 위해 본 논문에서는 Labeled Faces in the Wild를 활용해 분류 실험을 진행할 것이다. Labeled Faces in the Wild을 활용해 실험한 결과 중심확장을 활용한 모델과 활용하지 않은 모델간의 성능을 차이를 확인할 수 있었다.

• Animal cells and systems
• /
• v.7 no.3
• /
• pp.197-205
• /
• 2003

White snakeroot (Ageratina altissima (L.) R. King & H. Robinson) as an invasive alien plant appeared more abundantly at lower elevations where frequent artificial interferences prevailed than at higher elevations where such impacts were less. They appeared abundantly in introduced forests such as black locust plantation but they did not appear or were rare in natural forests such as oak forest. But an exceptional phenomenon where white snakeroot did not appear was found in a Korean pine stand with dense cover afforested recently. Appearance status of white snakeroot in each section of trampling path depended on breadth of the path and relative light intensity. Growth of white snakeroot measured as the number of ramet per genet, height, and biomass was better near the trampling path and was reduced toward the forest interior. The growth was proportionate to the relative light intensity measured according to distance from the trampling path. Such results support the fact generally known in relation invasion and expansion of the invasive alien plants. From this viewpoint, we suggest a management plan that applies ecological restoration principles to address ecosystems infected with white snakeroot by restoring the integral feature of the degraded nature and more thoroughly conserving the remaining nature.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.16 no.2
• /
• pp.17-28
• /
• 2010

The considerable increase of the elderly with dementia is expected annually and when we think about the family members' and the patients' suffering, it could be painful. Above all things, it imposes heavy economic burdens on the family members that have patients who suffer from diseases of age like dementia or paralysis that caring them at home and also, it is not desirable for those old people in point of physical or environmental circumstances for medical care. Thus, it is needed urgently that the expansion of specified facilities and improvement of services for these old people. Under this present condition, it is the special feature that the subject of research is people/facilities that offer services, not the elderly with dementia-the main user of those facilities. This proposal aims to make a study of expansion and improvement the old people's welfare facilities by using remodeled closed Small and Midium Hospitals which are the bad effect of economic growth. Also, it can save money with re-using abolished buildings which is property of the nation and protect environment too. In this study, We examine the present conditions of old people's welfare institution, and research a factor of remodeling for welfare facilities. Then we will verify remodeling-possibility which is concrete and working by using the product of this study.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.56.2-56.2
• /
• 2019

Measurement of the location of the baryon acoustic oscillation (BAO) feature in the clustering of galaxies has proven to be a robust and precise method to measure the expansion of the Universe. The best constraints so far have been provided from spectroscopic surveys because the errors on the redshift obtained from spectroscopy are minimal. This in turn means that the errors along the line-of-sight are reduced and so one can expect constraints on both angular diameter distance $D_A$ and expansion rate $H^{-1}$. But, future surveys will probe a larger part of the sky and go to deeper redshifts, which correspond to more number of galaxies. Analysing each galaxy using spectroscopy, which is a time consuming task, will not be practically possible. So, photometry will be the most convenient way to measure redshifts for future surveys such as LSST, Euclid, etc. The advantage of photometry is measuring the redshift of vast number of galaxies in a single exposure, but the disadvantage are the errors associated with the measured redshifts. Using a wedge approach, wherein the clustering is split into different wedges along the line-of-sight ${\pi}$ and across the line-of-sight ${\sigma}$, we show that the BAO information can be recovered even for photometric catalogues with errors along the line-of-sight. This means that we can get cosmological distance constraints even if we don't have spectroscopic information.

• Biomedical Science Letters
• /
• v.28 no.3
• /
• pp.157-169
• /
• 2022

DNA typing is the typical technology in the forensic science and plays a significant role in the personal identification of victims and suspects. Short tandem repeat (STR) is the short tandemly repeated DNA sequence consisting of 2~7 bp DNA units in specific loci. It is disseminated across the human genome and represents polymorphism among individuals. Because polymorphism is a key feature of the application of DNA typing STR analysis, STR analysis becomes the standard technology in forensics. Therefore, the DNA database (DNA-DB) was first introduced with 4 essential STR markers for the application of forensic science; however, the number of STR markers was expanded from 4 to 13 and 13 to 20 later to counteract the continuously increased DNA profile and other needed situations. After applying expanded STR markers to the South Korean DNA-DB system, it positively affected to low copy number analysis that had a high possibility of partial DNA profiles, and especially contributed to the theft cases due to the high portion of touch DNA evidence in the theft case. Furthermore, STR marker expansion not only contributed to the resolution of cold cases but also increased kinship index indicating the potential for improved kinship test accuracy using extended STR markers. Collectively, the expansion of the STR locus was considered to be necessary to keep pace with the continuously increasing DNA profile, and to improve the data integrity of the DNA-DB.

• The Bulletin of The Korean Astronomical Society
• /
• v.45 no.1
• /
• pp.50.4-51
• /
• 2020

We report our discovery of Raman-scattered He II λ6545 feature in young planetary nebulae NGC 6886 and NGC 6881 which indicates the existence of atomic hydrogen components. Considering sharply increasing cross-section of hydrogen atom near the resonance, Raman-scattered He II features are a useful diagnostic tool to investigate the distribution and kinematics of H I region in planetary nebulae. The high-resolution spectroscopic observation was carried out using BOES installed on the 1.8 m telescope of BOAO. We estimate the column density of H I region and its expansion velocity using our grid-based Monte-Carlo radiative transfer code. We assume that the H I region is uniformly distributed in spherical shell geometry with an opening angle and expands with constant speed. Our best-fit model is shown with the column density NHI = 3 × 1020 cm-2 and expansion speed vexp = 25 km s-1 with the opening angle ~ 25° for NGC 6886, and NHI = 4 × 1020 cm-2 and vexp = 30 km s-1 with the opening angle ~ 35° for NGC 6881. We present brief discussions on the late-stage of evolution of stars with mass > 3 M⊙.

• Journal of the Korean Society of Food Culture
• /
• v.26 no.3
• /
• pp.211-219
• /
• 2011

To examine the key success factors for long-lasting restaurants, we visited 10 restaurants with 30 or more than 30 years of tradition, located in Seoul and Gyeonggi-do districts, to research these restaurant menus and customer characteristics by observation and interview. The results were analyzed using descriptive statistics. The outstanding feature noted was that each and every restaurant had its own simple and specialized menu. We found that this feature created a virtuous circle that reinforced itself through a positive feedback loop. The simple and specialized menu increased both the cooking efficiency and food quality while it reduced both food and labor costs, this enabled the customers to eat at an affordable price and have generous servings. This lead to customer satisfaction and revisits to the restaurant, which triggered word-of-mouth referral and expansion of their customer base. This in turn created higher operating profit margins that could be reinvested in the business. The secret recipes for cooking, invented by their founders, were passed on from generation to generation. Their customer base included customers of all ages from children to senior people. And their regular customers consisted of neighboring office workers and families traveling from a long distance. We hope that our findings on long-lasting restaurants, especially of the virtuous cycle created due to the simple and specialized menus with secret recipes, will contribute to the development of Korean style long-lasting restaurant model.