• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.25-36
• /
• 2008

In this paper, we present a robust hand recognition approach to sudden illumination changes. The proposed approach constructs a background model with respect to hue and hue gradient in HSI color space and extracts a foreground hand region from an input image using the background subtraction method. Eighteen features are defined for a hand pose and multi-class SVM(Support Vector Machine) approach is applied to learn and classify hand poses based on eighteen features. The proposed approach robustly extracts the contour of a hand with variations in illumination by applying the hue gradient into the background subtraction. A hand pose is defined by two Eigen values which are normalized by the size of OBB(Object-Oriented Bounding Box), and sixteen feature values which represent the number of hand contour points included in each subrange of OBB. We compared the RGB-based background subtraction, hue-based background subtraction and the proposed approach with sudden illumination changes and proved the robustness of the proposed approach. In the experiment, we built a hand pose training model from 2,700 sample hand images of six subjects which represent nine numerical numbers from one to nine. Our implementation result shows 92.6% of successful recognition rate for 1,620 hand images with various lighting condition using the training model.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2005.11a
• /
• pp.500-506
• /
• 2005

본 논문에서는 자가 생성 지도 학습 알고리즘을 이용한 운송 컨테이너 식별자 인식 시스템을 제안한다. 일반적으로 운송 컨테이너의 식별자들은 글자의 색이 검정색 또는 흰색으로 이루어져 있는 특정이 있다. 이러한 특성을 고려하여 원 컨테이너 영상에 대해 검은색과 흰색을 제외하고는 모든 부분을 잡음으로 처리하기 위해 퍼지 추론 방법을 이용하여 식별자 영역과 바탕영역을 구별한다. 식별자 영역으로 구분 된 영역은 그대로 두고, 바탕 영역으로 구분된 영역 은 전체 영상의 평균 픽셀 값으로 대체시킨다. 그리고 Sobel 마스크를 이용하여 에지를 검출하고, 추출된 에지를 이용하여 수직 블록과 수평 블록을 검출 하여 컨테이너의 식별자 영역을 추출하고 이진화한다. 이진화 된 식별자 영역에 대해 검정색의 빈도수를 이용하여 흰바탕과 민바탕을 구분하고 4 방향 윤곽선 추적 알고리즘을 적용하여 개별 식별자를 추출 한다. 개별 식별자 인식을 위해 자가 생성 지도 학습 알고리즘을 제안하여 개별 식별자 인식에 적용한다. 제안된 자가 생성 지도 학습 알고리즘은 입력층과 은닉층 사이의 구조를 ART-l을 개선하여 적용하고 은닉층과 출력층 사이에는 일반화된 델타 학습 방법과 Delta-bar-Delta 알고리즘을 적용하여 학습 및 인식 성능을 개선한다. 실제 80 개의 컨테이너 영상을 대상으로 실험한 결과, 제안된 식별자 추출 방법이 이전의 개별 추출 방법보다 추출률이 개선되었고 FCM 기반 자가 생성 지도 학습 알고리즘보다 제안된 자가 생성 지도 학습 알고리즘이 컨테이너 식별자의 학습 및 인식에 있어서 개선된 것을 확인하였다.색 문제를 해결하고자 하는 것이 연구의 목적이다. 정보추출은 사용자의 관심사에 적합한 문서들로부터 어떤 구체적인 사실이나 관계를 정확히 추출하는 작업을 가리킨다.앞으로 e-메일, 매신저, 전자결재, 지식관리시스템, 인터넷 방송 시스템의 기반 구조 역할을 할 수 있다. 현재 오픈웨어에 적용하기 위한 P2P 기반의 지능형 BPM(Business Process Management)에 관한 연구와 X인터넷 기술을 이용한 RIA (Rich Internet Application) 기반 웹인터페이스 연구를 진행하고 있다.태도와 유아의 창의성간에는 상관이 없는 것으로 나타났고, 일반 유아의 아버지 양육태도와 유아의 창의성간의 상관에서는 아버지 양육태도의 성취-비성취 요인에서와 창의성제목의 추상성요인에서 상관이 있는 것으로 나타났다. 따라서 창의성이 높은 아동의 아버지의 양육태도는 일반 유아의 아버지와 보다 더 애정적이며 자율성이 높지만 창의성이 높은 아동의 집단내에서 창의성에 특별한 영향을 더 미치는 아버지의 양육방식은 발견되지 않았다. 반면 일반 유아의 경우 아버지의 성취지향성이 낮을 때 자녀의 창의성을 향상시킬 수 있는 것으로 나타났다. 이상에서 자녀의 창의성을 향상시키는 중요한 양육차원은 애정성이나 비성취지향성으로 나타나고 있어 정서적인 측면의 지원인 것으로 밝혀졌다.징에서 나타나는 AD-SR맥락의 반성적 탐구가 자주 나타났다. 반성적 탐구 척도 두 그룹을 비교 했을 때 CON 상호작용의 특징이 낮게 나타나는 N그룹이 양적으로 그리고 내용적으로 더 의미 있는 반성적 탐구를 했다용을 지원하는 홈페이지를 만들어 자료

• Korean Journal of Remote Sensing
• /
• v.35 no.6_2
• /
• pp.1107-1115
• /
• 2019

Satellite data play a major role in supporting knowledge about forest fire by delivering rapid information to map areas damaged. This study, we used 7 Sentinel-2A images to detect change area in forests of Sokcho on April 4, 2019. The process of classify forest fire severity used 7 levels from Sentinel-2A dNBR(differenced Normalized Burn Ratio). In the process of classifying forest fire damage areas, the study selected three areas with high regrowth of vegetation level and conducted a detailed spatial analysis of the areas concerned. The results of dNBR analysis, regrowth of coniferous forest was greater than broad-leaf forest, but NDVI showed the lowest level of vegetation. This is the error of dNBR classification of dNBR. The results of dNBR time series, an area of forest fire damage decreased to a large extent between April 20th and May 3rd. This is an example of the regrowth by developing rare-plants and recovering broad-leaf plants vegetation. The results showed that change area was detected through the change detection of danage area by forest category and the classification errors of the coniferous forest were reached through the comparison of NDVI and dNBR. Therefore, the need to improve the precision Korean forest fire damage rating table accompanied by field investigations was suggested during the image classification process through dNBR.

• Journal of the Korean Society of Radiology
• /
• v.10 no.3
• /
• pp.215-222
• /
• 2016

X-ray mammography is the most effective method for the diagnosis of calcified lesions of various breast diseases. To reduce patient dose and to obtain optimal image required for diagnosis, the performance of the mammography system should be maintained continuously. Because the target (anode) angle of the X-ray tube is measured from the central X-ray, the effective angle can be slightly different in view of the position on the detector, which can result in degrading spatial resolution of the imaging within the field of view. In this study, we measured the MTF to examine spatial resolution for positions on the detector in the digital mammography system. For a tungsten wire of $50{\mu}m$ diameter, the highest spatial frequency was obtained. It meant that a wire diameter for measuring MTF through LSF should be small compared to the pixel size of the detector used in the mammography system. The spatial resolution showed slightly different performance according to positions on the detector. The center position gave the best spatial resolution and positions away from the center showed the degraded performance although the difference of the spatial resolution was small. The effective focal spot size of the full width at half maximum also showed similar result. It concluded that the slightly increase of the effective focal spot size gave the degradation of the spatial resolution for positions on the detector.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.295-302
• /
• 2018

Face recognition (FR) has been widely used in various applications, such as smart surveillance systems, immigration control in airports, user authentication in smart devices, and so on. FR in well-controlled conditions has been extensively studied and is relatively mature. However, in unconstrained conditions, FR performance could degrade due to undesired characteristics of the input face image (such as irregular facial pose variations). To overcome this problem, this paper proposes a new method for determining if an input image is suitable for FR. In the proposed method, for an input face image, reconstruction error is computed by using a predefined set of reference face images. Then, suitability can be determined by comparing the reconstruction error with a threshold value. In order to reduce the effect of illumination changes on the determination of suitability, a preprocessing algorithm is applied to the input and reference face images before the reconstruction. Experimental results show that the proposed method is able to accurately discriminate non-frontal and/or incorrectly aligned face images from correctly aligned frontal face images. In addition, only 3 ms is required to process a face image of $64{\times}64$ pixels, which further demonstrates the efficiency of the proposed method.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.2
• /
• pp.61-66
• /
• 2019

Augmented reality is a technology that makes a virtual object appear as if it exists in reality by composing a virtual object in real time with the image captured by the camera. In order to augment the virtual object on the object existing in reality, the homography of images utilized to estimate the position and orientation of the object. The homography can be estimated by applying the RANSAC algorithm to the feature points of the images. But the homography estimation method using the RANSAC algorithm has a problem that accurate homography can not be estimated when there are many feature points in the background. In this paper, we propose a method to filter feature points of a background when the object is near and the background is relatively far away. First, we classified the depth image into relatively near region and a distant region using the Otsu's method and improve homography estimation performance by filtering feature points on the relatively distant area. As a result of experiment, processing time is shortened 71.7% compared to a conventional homography estimation method, and the number of iterations of the RANSAC algorithm was reduced 69.4%, and Inlier rate was increased 16.9%.

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.273-282
• /
• 2022

MPEG-VCM(Video Coding for Machine) aims to standardize video codec for machines. VCM provides data sets and anchors, which provide reference data for comparison, for several machine vision tasks including object detection, object segmentation, and object tracking. The evaluation template can be used to compare compression and machine vision task performance between anchor data and various proposed video codecs. However, performance comparison is carried out separately for each machine vision task, and information related to performance evaluation of multiple machine vision tasks on a single bitstream is not provided currently. In this paper, we propose a performance evaluation method of a video codec for AI-based multi-tasks. Based on bits per pixel (BPP), which is the measure of a single bitstream size, and mean average precision(mAP), which is the accuracy measure of each task, we define three criteria for multi-task performance evaluation such as arithmetic average, weighted average, and harmonic average, and to calculate the multi-tasks performance results based on the mAP values. In addition, as the dynamic range of mAP may very different from task to task, performance results for multi-tasks are calculated and evaluated based on the normalized mAP in order to prevent a problem that would be happened because of the dynamic range.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.51-58
• /
• 2023

In this paper, we propose an organ segmentation technique for the automatic extraction of medical diagnostic indicators from X-ray images. In order to calculate diagnostic indicators of heart disease and spinal disease such as VHS(vertebral heart scale) and Cobb angle, it is necessary to accurately segment the thoracic spine, carina, and heart in a chest X-ray image. A deep neural network model in which the high-resolution representation of the image for each layer and the structure converted into a low-resolution feature map are connected in parallel was adopted. This structure enables the relative position information in the image to be effectively reflected in the segmentation process. It is shown that learning performance can be improved by combining the OCR module, in which pixel information and object information are mutually interacted in a multi-step process, and the channel attention module, which allows each channel of the network to be reflected as different weight values. In addition, a method of augmenting learning data is presented in order to provide robust performance against changes in the position, shape, and size of the subject in the X-ray image. The effectiveness of the proposed theory was evaluated through an experiment using 145 human chest X-ray images and 118 animal X-ray images.

• Journal of Digital Convergence
• /
• v.20 no.3
• /
• pp.407-413
• /
• 2022

Existing clothing recommendation systems remain at the level of showing appropriate photos when a user selects a type of clothing he or she likes after entering his or her own body size or body size. When a user purchases clothing using such recommendation systems, there are many cases in which it does not fit or does not fit the user's body size. In this study, to solve these problems of existing clothing recommendation systems, a system was implemented in which the user receives not only size but also skin tone and recommends clothing suitable for the user's body size as well as skin tone. In this system, clothing size information obtained through web crawling was periodically stored in a database for eight male tops to recommend clothing, and the entire pixel of the clothing image was analyzed to extract color text values. In order to confirm the performance of this system, a survey was conducted on 100 male college students, and the satisfaction level was 70%. Most of the reasons for not being satisfied are that the recommended clothing is limited, so it is judged that it is necessary to expand the target clothing in the future.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_3
• /
• pp.1693-1705
• /
• 2023

Rural areas, which account for about 90% of the country's land area, are increasing in importance and value as a space that performs various public functions. However, facilities that adversely affect residents' lives, such as livestock facilities, factories, and solar panels, are being built indiscriminately near residential areas, damaging the rural environment and landscape and lowering the quality of residents' lives. In order to prevent disorderly development in rural areas and manage rural space in a planned manner, detection and monitoring of hazardous facilities in rural areas is necessary. Data can be acquired through satellite imagery, which can be acquired periodically and provide information on the entire region. Effective detection is possible by utilizing image-based deep learning techniques using convolutional neural networks. Therefore, U-Net model, which shows high performance in semantic segmentation, was used to classify potentially hazardous facilities in rural areas. In this study, KOMPSAT ortho-mosaic optical imagery provided by the Korea Aerospace Research Institute in 2020 with a spatial resolution of 0.7 meters was used, and AI training data for livestock facilities, factories, and solar panels were produced by hand for training and inference. After training with U-Net, pixel accuracy of 0.9739 and mean Intersection over Union (mIoU) of 0.7025 were achieved. The results of this study can be used for monitoring hazardous facilities in rural areas and are expected to be used as basis for rural planning.