• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2009년도 9th International Meeting on Information Display
• /
• pp.1338-1340
• /
• 2009

High resolution three-dimensional integral imaging display is proposed. Each time-multiplexed image is projected with different incident angle on same array of elemental lenses. Those images are collected at different positions in focal plane of lens array, and thus the number of the point light sources increases and their spacing decreases. Therefore, proposed method can create high resolution 3D images.

• 대한방사선기술학회지:방사선기술과학
• /
• 제8권2호
• /
• pp.11-14
• /
• 1985

The author came to analize and get the following problems after researched radiographic quality in order to find out the necessary factors to improve in radiographs of frontal projection of the chest selected at random of the adult patients (1545 male, 1520 female) who had been examined in 4 departments of radiology of the general hospitals in Seoul and Kyungki area. 1. Problems of x-ray film or of radiographic cassette appeared in 2.97% radiographs on account of selection of the film size (except costophrenic sinus) (1.79%), poor screen-film contact (0.85%), light leakage of cassette (0,33%). 2. Problems of patients' positioning or breathing appeared in 16.57% radiographs of all because of overlapping of lung apex and clavicle (6.98%), overlapping of scapula and lung field (5.87%), asymmetrical projection of clavicles (1.76%), errors in positioning and breathing of the patient (1.96%). 3. Problems of x-ray exposure factors or film processing appeared in 22.25% radiographs because of over-density (2.64%), under-density (3.95%), fog (0.59%), demonstration density under clavicles or lung marking unsharply (3.82%), not clear of lung marking from breast region (0.94%), not clear the lung marking from the part overlapped of heart and lungs (3.92%), not clear the lung marking from the part overlapped of liver and lung (6.49%).

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1993년도 추계학술대회 논문집
• /
• pp.423-427
• /
• 1993

An efficient 3-axis NC milling simulator is presented. The geometric simulation of milling is based on z-map structure and voxels. For the graphic simulation,dimetric projection is adopted. As a result, two faces of a voxel are exposed and they are overlapped. Visible faces are determined by using z-butter method. The simulation system is developed in IBM-PC compatible with satisfactory result.

• International Journal of Contents
• /
• 제8권1호
• /
• pp.39-46
• /
• 2012

Character segmentation is a preprocessing step in many offline handwriting recognition systems. In this paper, Chinese characters are categorized into seven different structures. In each structure, the character size with the range of variations is estimated considering typical handwritten samples. The component removal and merge criteria are presented to remove punctuation symbols or to merge small components which are part of a character. Finally, the criteria for segmenting the adjacent characters concerning each other or overlapped are proposed.

• 한국지능시스템학회논문지
• /
• 제9권4호
• /
• pp.444-450
• /
• 1999

본 논문에서는 칼라로 입력된 문서 영상에서 문자 영역추출을 위하여 k-means을 이용한 클러스트링 알고리즘을 제안하였다. 칼라 영상의 클러스트링을 위해서 HIS 좌표계에 적합한 거리함수를 제안하였다. 이를 인식하기 위한 전처리 단계인 문자분리(segmentation)방법은 연결 화소를 이용한 개별문자 추출 알고리즘을 제안하였다. 본 알고리즘 에서는 문자분리방벙에서 접촉문자 (touching character)또는 겹친 문자(overlapped character)등과 같이 분리가 곤란한 문자를 개별문자로 분리하는 방법이다. 기존의 문자 분리방법에서는 투영(projection)dop 의한 방법과 외곽선(edge)추적에 의한 방법등을 사용하여 왔으나 제안된 방법은 문자열 추출후 한번의 투영으로 연결화소를 이용하여 개별문자를 추출한다. 문자 영역과 비 문자 영역을 구분하여 개발문자 추출을 한 결과 단순한 이진 영상이 아닌 칼라 영상에서의 문서 처리가 큰 의의가 있고 기존의 문서 처리기 보다 향상된 알고리즘인 것을 확인하였다.

• 한국정보처리학회논문지
• /
• 제4권5호
• /
• pp.1277-1288
• /
• 1997

본 논문에서는 인체 문서 인식을 위한 전처리 과정인 개별 문자 추출 방법과 인식 방법에 대하여 논한다. 전처리에서는 접촉 문자(touching charadcter) 또는 겹친 문자 (overlaapped character) 등과 같이 추출이 곤란한 문자를 개별 문자로 추출하는 것이다. 기존의 문자 분리 방법에서는 투영((projection)에 의한 방법과 외곽선(edge)추척에 의한 방법 등을 사용하여 왔으나, 제안된 방법은 문자열 추출 후 한번의 투영으로 연결 화소를 이용하여 개별 문자를 추출한다. 인식을 위해서는 최대불록화 방법(Maximum Block Mehtod:MBM)을 이용하여 특징 추출을 한다. 최대불록화는 문자를 투영 중 처음 찾아진 점에서부터 최대한 불록을 확정 시키는 방법이다. 문자를 이루는 최대불록들을 직선 불록과 사선 불록으로 분리후 골격화 시킨다. 특히 한자 인식에서 기존의 상용 문자 인식기와 비교하여 향상된 인식율을 얻을 수 있다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 제14회 신호처리 합동 학술대회 논문집
• /
• pp.755-758
• /
• 2001

In this paper. Ive propose a postprocessing technique based on the theory of projection on convex sets(POCS) to reduce the blocking artifacts in HDTV decoded images. In BDCT of HDTV. the image is divided into a grid of non-overlapped 8 ${\times}$ 8 blocks. and then each block is coded separately. A block which is located one pixel apart from the grid of BDCT will include the boundary of the original 8 ${\times}$ 8 block. If the blocking artifact is Introduced alone the block boundary. this block will have different frequency characteristic from that of the original block. Thus, a comparison of frequency characteristics of these two overlapping blocks can detect the undesired high-frequency components mainly caused by the blocking artifact. By eliminating these undesired high-frequency components adaptively, robust smoothing projection operator can be obtained. Simulation results with real image sequences indicate that the proposed method performs better than conventional algorithms.

• 동의생리병리학회지
• /
• 제25권2호
• /
• pp.217-226
• /
• 2011

The aim of this study is to identify central neural pathway of neurons following the projection to the large intestine and Hapgok(LI4) which is Won acupoint of the large intestine meridian of hand-yangmyeong. In this experiment, Bartha's strain of pseudorabies virus was used to trace central localization of neurons related with large intestine and acupoint(LI4) which has been known to be able to regulate intestinal function. The animals were divided into 3 groups: group 1, injected into the large intestine; group 2, injected into the acupoint(LI4); group 3, injected into the acupoint(LI4) after severing the radial, ulnar, median nerve. After four days survival of rats, PRV labeled neurons were identified in the spinal cord and brain by immunohistochemical method. First-order PRV labeled neurons following the projection to large intestine, acupoint(LI4) and acupoint(LI4) after cutting nerve were found in the cervical, thoracic, lumbar and sacral spinal cord. Commonly labeled neurons were labeled in the lumbosacral spinal cord and thoracic spinal cord. They were found in lamina V- X, intermediomedial nucleus and dorsal column area. The area of sensory neurons projecting was L5-S2 spinal ganglia and T12-L1 spinal ganglia, respectively. In the brainstem, the neurons were labeled most evidently and consistently in the nucleus tractus solitarius, area postrema, dorsal motor nucleus of vagus nerve, reticular nucleus, raphe nuclei(obscurus, magnus and pallidus), C3 adrenalin cells, parapyramidal area(lateral paragigantocellular nucleus), locus coeruleus, subcoeruleus nucleus, A5 cell group, periaqueductal gray matter. In the diencephalon, PRV labeled neurons were marked mostly in the arcuate nucleus and median eminence. These results suggest that overlapped CNS locations are related with autonomic nuclei which regulate the functions of large intestine-related organs and it was revealed by tracing PRV labeled neurons projecting large intestine and related acupoint(LI4).

• 대한전자공학회논문지TE
• /
• 제37권3호
• /
• pp.45-52
• /
• 2000

본 연구에서는 인체 상반신영상에서 얼굴부위를 분할하기 위한 영상분할 알고리즘을 제안하였다. 제안한 알고리즘은 HWT를 적용하여 영상의 경계를 이루는 차분영상인 고주파대역과 평균영상인 저주파대역으로 분리하고, 저주파대역에서 고립점과 돌출부위, 경계중복점을 제거하였다. 또한 제안한 경계검출 알고리즘으로 경계를 검출하고 단순화시켰으며, 1픽셀 단위의 세선화과정을 통하여 경계를 선명하게 하였다. 그리고 제안 한 폐곡선추적 알고리즘으로 얼굴부위 경계만을 추출한 뒤, 마스크를 구성하고 원영상과의 정합을 통하여 얼굴부위분할을 하였다. 제안한 알고리즘을 적용하여 얼굴부위 분할실험을 실행한 결과 95.88%의 분할값을 갖는 얼굴분할이 이루어졌다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권11호
• /
• pp.4502-4518
• /
• 2015

Fisher linear discriminant analysis (LDA) is one of the most popular projection techniques for feature extraction and has been widely applied in face recognition. However, it cannot be used when encountering the single sample per person problem (SSPP) because the intra-class variations cannot be evaluated. In this paper, we propose a novel method called local similarity based linear discriminant analysis (LS_LDA) to solve this problem. Motivated by the "divide-conquer" strategy, we first divide the face into local blocks, and classify each local block, and then integrate all the classification results to make final decision. To make LDA feasible for SSPP problem, we further divide each block into overlapped patches and assume that these patches are from the same class. To improve the robustness of LS_LDA to outliers, we further propose local similarity based median discriminant analysis (LS_MDA), which uses class median vector to estimate the class population mean in LDA modeling. Experimental results on three popular databases show that our methods not only generalize well SSPP problem but also have strong robustness to expression, illumination, occlusion and time variation.