• 한국컴퓨터정보학회논문지
• /
• 제15권2호
• /
• pp.47-53
• /
• 2010

본 논문은 동영상에서 실시간 얼굴검출을 위하여 Residual Image 검출과 색상정보를 이용한 얼굴검출 기법을 제안하였다. 제안된 기법은 동영상에서 빠른 처리 속도와 높은 얼굴 검출율을 나타냈으며 기울어진 얼굴영상에 대한 보정작업을 통하여 검출 에러율을 줄였다. 실시간으로 전송된 동영상에서 검출의 대상이 되는 정지영상을 추출한다. 추출된 영상은 기울어진 얼굴검출을 위한 window회전 알고리즘을 사용하고 이렇게 보정된 영상은 얼굴 검출에 필요한 특징을 추출하기 위해 AdaBoost알고리즘을 사용하여 실시간으로 얼굴이 검출된 영상을 획득하게 된다.

• 한국인쇄학회지
• /
• 제26권2호
• /
• pp.1-13
• /
• 2008

Printed mottle of coated paper is one of the most common phenomenon and the most difficult problem in offset printing. Offset printing is processed mainly processed by the attractive properties between water and oil, so all inks for off-printing must work with dampening solution(water). It may cause the emulsion on the printing nip from the printing pressure. This study aimed to investigate the effect of emulsified inks on print mottle from emulsified cyan ink by force with each different IP A contents. We measured the print mottle by densitometer and image analysis method. The emulsified inks also give effect to now properties of inks and it caused more ink transfer rate, however, it caused low density of inks. Moreover the emulsified inks were spreaded to around of dots and cause the thinning density on the non-printing area like print mottle. The results showed that the emulsified inks also cause scumming on the printing result with little mistake of adjusting dampening solution and mostly decreasing dot reproduction. So we could find out the obvious effect of emulsified inks to print mottle.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2019년도 춘계학술발표대회
• /
• pp.431-434
• /
• 2019

In the case of blur processing, it is common to use a tool such as Photoshop to perform processing manually. However, it can be considered very efficient if the blur is processed at one time in the object detection process. Based on this point, we can use the object detection model to blur the objects during the process. The object detection is performed by using the YOLO [3] model. If such blur processing is used, it may be additionally applied to streaming data of video or image.

• 전자공학회논문지B
• /
• 제31B권8호
• /
• pp.160-171
• /
• 1994

The wide dynamic range and severely attenuated contrast in mediastinal area appearing in typical chest radiographs have often caused difficulties in effective visualization and diagnosis of lung diseases. This paper proposes a new adaptive image enhancement technique which potentially solves this problem and there by improves observer performance through image processing. In the proposed method image processing is applied to the chest radiograph with different processing parameters for the lung field and mediastinum adaptively since there are much differences in anatomical and imaging properties between these two regions. To achieve this the chest radiograph is divided into the lung and mediastinum by gray level thresholding using the cumulative histogram and the dynamic range compression and local contrast enhancement are carried out selectively in the mediastinal region. Thereafter a gray scale transformation is performed considering the JND(just noticeable difference) characteristic for effective image displa. The processed images showed apparenty improved contrast in mediastinum and maintained moderate brightness in the lung field. No artifact could be observed. In the visibility evaluation experiment with 5 radiologists the processed images with better visibility was observed for the 5 important anatomical structures in the thorax.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1990년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 26-27 Oct. 1990
• /
• pp.716-721
• /
• 1990

It is one of the essential task to determine the absolute location of mobile robot during its navigation. In this paper we propose an algorithm to calculate the distance and orientation of camera from landmark through the visual image of stripe typed landmark. Exact closed form solution of camera location is obtained with the correspondences from vertical line on mark plane to the intersection point of projected line with horizontal axis of image plane. It needs only one line image information, so that location determination can be processed in real time.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1281-1283
• /
• 2003

By use of RS and GIS, the QuickBird image and geographic map were used for the survey of the foreshore resources of Shanghai. The image was processed and interpreted. The distribution maps of sea dike, foreshore, vegetation, soil, hydraulic structures, landscape, topography, and so on were extracted in manual classification. These data have been integrated into the information management system for the shoreline and foreshore. It plays an important role in the evolvement analysis of the shoreline and foreshore.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.894-907
• /
• 2022

The features extracted by convolutional neural networks are more descriptive of images than traditional features, and their convolutional layers are more suitable for retrieving images than are fully connected layers. The convolutional layer features will consume considerable time and memory if used directly to match an image. Therefore, this paper proposes a feature weighting and region integration method for convolutional layer features to form global feature vectors and subsequently use them for image matching. First, the 3D feature of the last convolutional layer is extracted, and the convolutional feature is subsequently weighted again to highlight the edge information and position information of the image. Next, we integrate several regional eigenvectors that are processed by sliding windows into a global eigenvector. Finally, the initial ranking of the retrieval is obtained by measuring the similarity of the query image and the test image using the cosine distance, and the final mean Average Precision (mAP) is obtained by using the extended query method for rearrangement. We conduct experiments using the Oxford5k and Paris6k datasets and their extended datasets, Paris106k and Oxford105k. These experimental results indicate that the global feature extracted by the new method can better describe an image.

• 한국통신학회논문지
• /
• 제16권2호
• /
• pp.180-195
• /
• 1991

본 논문은 한글 문자 패턴을 인식하기 위하여 쉐이프 패턴을 대상으로 한글의 구조적 정보를 이용한 새로운인식 방법에 대해서 연구하였다. 먼저, 입력된 데이타에 대하여 문자의 위치를 알기 위하여 문자 영역의 블럭화를 행하였고, 둘째로 한글의 무게 중심을 이용한 종모음의 유무를 결정하고, 횡모음과 짧은 기둥의 위치와 길이 조사 및 종정의 존재 여부를 조사하여 한글이 가지는 6가지의 기본 구조로 형식 분류를 하였으며, 마지막으로 분류된 형식에 따라 각각의 자소에 대해 유크리드 기리(Uclid distance)에 의한 탬플레이트 매칭(template matching)을 실행하여 인식을 행하였다. 본 연구는 실험을 통하여 총 2350자의 문자에 대하여 98.3%의 형식 분류율과 95.2%의 한글 인식율을 얻었다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.129-131
• /
• 2003

The aim of this study is to evaluate the hazard of landslides at Penang, Malaysia, using a Geographic Information System (GIS) and remote sensing. Landslide locations were identified in the study area from interpretation of aerial photographs and field surveys. The topographic and geologic data and satellite image were collected, processed and constructed into a spatial database using GIS and image processing. The used factors that influence landslide occurrence are topographic slope, topographic aspect topographic curv ature and distance from drainage from topographic database, geology and distance from lineament from the geologic database, land use from TM satellite image and vegetation index value from SPOT satellite image. Landslide hazardous area were analysed and mapped using the landslide-occurrence factors by probability - likelihood ratio - method. The results of the analysis were verified using the landslide location data. The validation results showed satisfactory agreement between the hazard map and the existing data on landslide location.

• Journal of information and communication convergence engineering
• /
• 제9권3호
• /
• pp.331-335
• /
• 2011

Digital images are often corrupted by impulse noise, and it is very important to remove random-valued impulse noise. Cleaning such noise is far more difficult than cleaning salt and pepper impulse noise. In this paper, we proposed an efficient way to remove random-valued impulse noise from digital images. This novel method comprises two stages. The first stage is to detect the random-valued impulse noise in the image and the pixels are roughly divided into two classes, which are "noise-free pixel" and "noise pixel". Then, the second stage is to eliminate the random-valued impulse noise from the image. In this stage, only the "noise pixels" are processed. The "noise-free pixels" are copied directly to the output image. Simulation results indicated that our method provides a significant improvement over many other existing algorithms.