• 인지과학
• /
• 제9권1호
• /
• pp.1-11
• /
• 1998

본 논문에서는 인간의 정보처리 과정에 관한 심리학적 실험에 바탕을 두고 인간이 사용하고 있는 것으로 생각되는 특징을 이용하여 이를 문자 인식에 적용하였다. 인간의 경우 화소단위의 정보뿐만 아니라 일정지역의 정보를 함께 처리하는 경향이 있다. 그러므로 일정지역에 대한 정보를 표시하는 영역 특징을 정의하고 정의된 이 영역 특징과 기존의 화소단위 특징들을 결합하였다. 사용한 특징으로는 영역 특징에 기반 한 초등 적 분석결과, 영역특징을 포함한 망 특징, 교차거리와 특징 그리고 기울기 특징들이다. 성능 평가 실험은 필기 한글자모, 숫자 그리고 대소영문자를 대상으로 하였으며, 인식기는 역전과 학습 방법을 이용한 신경망 인식기를 사용하였다. 각각의 인식 결과는 90.27∼93.25%, 98.00% 그리고 79.73∼85.75였다. 영역 특징과 유사한 UDLRH 특징을 대상으로 비교한 결과 전체적으로 1∼2% 정도 인식률 향상이 있었으며 인간이 판단하기에 보다 납득하기 쉬운 오 인식 성향을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권8호
• /
• pp.1976-1995
• /
• 2023

The anchor-free object detector CenterNet regards the object as a center point and predicts it based on the Gaussian circle region. For each object's center point, CenterNet directly regresses the width and height of the objects and finally gets the boundary range of the objects. However, the critical range of the object's center point can not be accurately limited by using the Gaussian circle region to constrain the prediction region, resulting in many low-quality centers' predicted values. In addition, because of the large difference between the width and height of different objects, directly regressing the width and height will make the model difficult to converge and lose the intrinsic relationship between them, thereby reducing the stability and consistency of accuracy. For these problems, we proposed a center point prediction method based on the Gaussian elliptic region and a size component regression method based on the small solution space. First, we constructed a Gaussian ellipse region that can accurately predict the object's center point. Second, we recode the width and height of the objects, which significantly reduces the regression solution space and improves the convergence speed of the model. Finally, we jointly decode the predicted components, enhancing the internal relationship between the size components and improving the accuracy consistency. Experiments show that when using CenterNet as the improved baseline and Hourglass-104 as the backbone, on the MS COCO dataset, our improved model achieved 44.7%, which is 2.6% higher than the baseline.

• 디지털융복합연구
• /
• 제15권12호
• /
• pp.13-23
• /
• 2017

오늘날 '정보화사회' 구축은 국가경쟁력 획득에 중요한 수단이 된다. 특히, 우리나라는 전 세계적으로 성공적인 정보화 구축 대표 사례로 평가 받고 있다. 이와는 반대로 북한은 심각한 '정보격차' 문제로 인해 그렇지 못한 실정이다. 이러한 정보격차의 발생원인으로는 세 가지 측면이 있다. 첫째, 매체접근성, 둘째, 정보동원력, 셋째, 정보의식이다. 이러한 세가지 측면을 바탕으로 통일 이후 북한지역의 정보화 구축 과정에 대해 설계 제안한다. 본 연구의 목적은 통일시대를 대비해 어떻게 북한 지역의 정보화 구축을 할 것인가에 대해 단계별 실행 전략을 도출하고자 한다. 이를 위해 우리나라와 북한의 정보화 구축 단계들을 각각 살펴보고 추진과정을 분석하였다. 본 연구에서 제시한 실행전략이 향후 연구에 있어서 거대한 담론을 일으키는 초석이 될 수 있을 것으로 기대한다.

• 한국통신학회논문지
• /
• 제25권3A호
• /
• pp.334-341
• /
• 2000

This paper presents an analysis of the capacity, the interference of adjacent cells of a CDMA cellular system, depending on the soft handoff region and log-normal shadowing. The optimum soft handoff region is chosen by using Erlang capacity. It is shown that when the soft handoff region increases, the Erlang capacity increase due to a reduction of the interference power of adjacent cells. But if the region is increased above a certain value, there is no improvement in the system’s capacity. Furthermore as the standard deviation of the log-normal shadowing's normal distribution factor increases, the soft handoff region has to be increased linearly to achieve the same Erlang capacity.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2003년도 춘계종합학술대회
• /
• pp.334-337
• /
• 2003

장마포기에는 적도에서 동지나 지역은 주로 대류에 의한 강수가 우세했으며, 대다수의 수증기는 인도 몬순지역에서 이류되어 온 수증기임을 안 수 있었다. 장마기에는 한반도 지역은 convection에 의한 강수는 미소하나 microphysics에 의한 강수가 지배적이었다. 이 때 수증기의 근원(강수량)은 인도 몬순지역에서 이류되어 온 수증기이다. 비장마기에 우리나라 및 대다수의 지역은 microphysics에 의한 강수가 지배적이었다. 또한 태풍의 북상으로 인한 대량의 수증기의 이류이다. 수증기의 대부분은 Rossby wave의 복동방향 전파에 기인한다.

• 한국멀티미디어학회논문지
• /
• 제17권7호
• /
• pp.806-817
• /
• 2014

The extraction of lip region is essential to Lip Reading, which is a field of image processing to get some meaningful information by the analysis of lip movement from human face image. Many conventional methods to extract lip region are proposed. One is getting the position of lip by using geometric face structure. The other discriminates lip and skin regions by using color information only. The former is more complex than the latter, however it can analyze black and white image also. The latter is very simple compared to the former, however it is very difficult to discriminate lip and skin regions because of close similarity between these two regions. And also, the accuracy is relatively low compared to the former. Conventional analysis of color coordinate systems are mostly based on specific extraction scheme for lip regions rather than coordinate system itself. In this paper, the method for selection of effective color coordinate system and chromaticity transformation to discriminate these two lip and skin region are proposed.

• 산업경영시스템학회지
• /
• 제19권38호
• /
• pp.199-205
• /
• 1996

The purpose of this study, therefore, was to construct the region statistical information to present methods of the data. The results of this paper are as follows: First, the construction of region statistical data is much in need of utilizing the server of regional information center, or the database to the server of public institutions, Second, there are some difficulties to receive the region statistical data because of only depending on the main source of KOSIS provided by national units from National Statistical Office. Third, as there is another problem which is text searching system served by KOSIS, GU system should be established for the user's satisfaction served by easier accessing screen. Fourth, there should be a standard software production to suit for the accessing software of the region statistical data.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2331-2334
• /
• 2003

Generally, skin color information has been widely used at the face region extraction step of the face region recognition process. But many experimental results show that they are very sensitive to the given threshold range which is used to extract the face regions at the input image. In this paper, we propose a face region extraction algorithm based on an adaptive range decision for skin color. First we extract the pixels which are regarded as the candidate skin color pixels by using the given range for skin color extraction. Then, the ratio between the total pixels and the extracted pixels is calculated. According to the ratio, we adaptively decide the range of the skin color and extract face region. From the experiment results for the various images, the proposed algorithm shows more accurate results than the conventional algorithm.

• 한국통신학회논문지
• /
• 제21권8호
• /
• pp.1874-1884
• /
• 1996

In this paper, we proposed automatic searching algorithm of thresholding value using multilevel thresholding for face segmentation from input bust image effectively. The proposed algorithm extracted the thresholding value of brightness that is formed background region, face region and hair region without illumination, background and face size from input image. The statistical projection analysis project the brightness of multilevel thresholding image into horizontal and vertical direction and decide the thresholding value of face. And the algorithm extracted elliptical type block of face from input image in order to reduce the back ground region and hair region efficiently. The proposed algorithm can reduce searching area of feature extraction and processing time for face recognication.

• 한국통신학회논문지
• /
• 제23권9A호
• /
• pp.2333-2344
• /
• 1998

We present a two step approach for estimating the motionand sturcture parameters from region orrespondences in two frames. Given four or more region corresondences on the same planar surface, the motion and planar orientation parameters are first linearly estimated based on second-order approximation of the displacement field of the image plane. Then, using this linear estimate as an initial guess, a nonlinear estimate is obtained by iteratively minimizing an objective function using the exact experession of the displacement field. The objective function involves the centroids of corresponding regions and relationships among low-order moments. Through simulations, we show that the two-step region-based approach gives robust estimates. The performance of nonlinear region-based estimation is compared with that of linear region-based and point-based methods. Experimental results for two image pairs, on esynthetic and one real, ar epresented to show the practical applicability of our approach.