• 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.

• 자연과학논문집
• /
• 제7권
• /
• pp.67-73
• /
• 1995

본 논문에서는 인간시각 시스템의 특성을 이용하여 세그멘테이션을 행하는 새로운 텍스처 세그멘테이션 영상코딩 기술을 제안한다. 제안된 방법은 영상을 HVS가 인지한 러프니스 정도에 관하여 영상을 텍스처와 같은 성질의 영역으로 세그멘테이션하는 방법론을 제안하여 상 세그멘트를 갖는 세그멘테이션 영상코딩기술의 문제점을 해결한다. 세그멘테이션은 텍스처 영역을 3 가지의 다른 텍스처 크래스(인간이 인지한 상 인테셔티, 부드러운 텍스처 및 거칠은 텍스처)로 구분하기 위해서 프락탈 디멘션을 임계하여 얻는다. 프락탈 디멘션을 근사하기 위한 적당한 브락 크기를 결정하는 것이 중요하다. 좋은 화질을 갖는 재생 영상은 여러 종류의 영상에 대해서 약 0.1에서 0.25 비트/픽셀에서 얻는다.

• Design & Manufacturing
• /
• 제15권3호
• /
• pp.1-6
• /
• 2021

An artificial neural network model based on a deep learning algorithm is known to be more accurate than humans in image classification, but there is still a limit in the sense that there needs to be a lot of training data that can be called big data. Therefore, various techniques are being studied to build an artificial neural network model with high precision, even with small data. The transfer learning technique is assessed as an excellent alternative. As a result, the purpose of this study is to develop an artificial neural network system that can classify burr images of light guide plate products with 99% accuracy using transfer learning technique. Specifically, for the light guide plate product, 150 images of the normal product and the burr were taken at various angles, heights, positions, etc., respectively. Then, after the preprocessing of images such as thresholding and image augmentation, for a total of 3,300 images were generated. 2,970 images were separated for training, while the remaining 330 images were separated for model accuracy testing. For the transfer learning, a base model was developed using the NASNet-Large model that pre-trained 14 million ImageNet data. According to the final model accuracy test, the 99% accuracy in the image classification for training and test images was confirmed. Consequently, based on the results of this study, it is expected to help develop an integrated AI production management system by training not only the burr but also various defective images.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1999년도 가을 학술발표논문집 Vol.26 No.2 (2)
• /
• pp.533-535
• /
• 1999

자궁경부진 세포인식 시스템에 있어서 가장 중요한 것이 영상처리를 이용하여 세포핵과 세포질을 추출하여 세포의 형태적인 정보를 알아내는 과정이다. 기존의 전역 thresholding 기법이나 region growing의 경우는 pap smear 검사를 통해 얻어진 세포 영상을 분할할 수 있는 region growing 기법을 제안한다. 제안된 region growing 기법은 초기에 seed를 검출할 때 local threshold growing 기법을 제안한다. 제안된 region growing 기법은 초기에 seed를 검출할 때 local threshold 개념을 도입하여 seed의 검출을 고르게 하고, 2가지 확장 조건을 사용하여 영역을 확장한다. 첫 번째 확장 조건은 비정상 세포나 artifact가 많아서 어둡게 나타나는 영상이나 세포질과 배경의 경계가 뚜렷하지 않아서 세포질의 구별이 어려운 영상의 영역 분할이 가능하도록 그 특성을 반영하고, 두 번째 조건은 세포가 흡수하는 빛의 양이 일정하다는 가정으로 영상에서의 지역 특성(gray level, color 등을 반영한다. 제안된 기법은 정상세포 영상뿐만 아니라 비정상 세포 영상에 대하여 over-segment나 under-segment하는 경우를 줄여서 영역 분할에 좋은 결과를 보인다.

• 한국멀티미디어학회논문지
• /
• 제15권12호
• /
• pp.1442-1448
• /
• 2012

The problem of Metal Area Segmentation (MAS) in X-ray CT images is a very hard task because of metal artifacts. This research features a practical yet effective method for MAS in X-ray CT images that exploits both projection image and reconstructed image spaces. We employ the Relevant Neighbor Area (RNA) idea [1] originally developed for projection image inpainting in order to create a novel feature in the projection image space that distinctively represents metal and near-metal pixels with opposite signs. In the reconstructed result of the feature image, application of a simple thresholding technique provides accurate segmentation of metal areas due to nice separation of near-metal areas from metal areas in its histogram.

• The Journal of the Acoustical Society of Korea
• /
• 제15권2E호
• /
• pp.85-91
• /
• 1996

New very low bit rate segmentation video image coding technique is proposed by segmenting image into textually homogeneous regions. Regions are classified into one of three perceptually distinct texture classes(perceived constant intensity, smooth texture, and rough texture) using the Human Visual System(HVS) and the fractals. To design very low bit rate video image coder, it is very important to determine the best block size for estimation the fractal dimension and the thresholding of the fractal dimension for each texture class. Good quality reconstructed images are obtained with about 0.10 to 0.21 bit per pixel(bpp) for many different types of imagery.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2007년도 춘계학술대회 학술발표 논문집 제17권 제1호
• /
• pp.315-319
• /
• 2007

This paper presents a algorithm, what is able to recognize 4 different continuous human motion using a single stationary camera as input. For the first step, we acquire images from a camera. To enhance the image, we perform preprocessing which deals with removing noise using median filter, thresholding. And then morphological operations are performed to remove which small blobs and eliminates small holes. At the forth step, blobs are analysed to extracts for foreground region. Then, motions are predicted from these images by using optical flow technique, and the predicted motion data are refined by comparing our cardboard models so as to judge behavior pattern.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1987년도 전기.전자공학 학술대회 논문집(II)
• /
• pp.1394-1397
• /
• 1987

It is difficult to detect edge segments from a noisy image since the image have a noise in piratical applications which utilize some type of visual input capability. Hence, the proposed algorithm consists of the modality tests based on parallel statistical tests without a noise removal preprocessing or postprocessing, and the edge detection technique With one-Pixel edge segments in this paper. The algorithm is very reliable and effective in the case of those situations where the Picture is poor quality and low resolution. And it does'nt require thinning operation and thresholding in hand. Experimental comparision With the more conventional techniques when applied to typical low-quality Pictures confirms good capabilities of the algorithm.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.134.1-134
• /
• 2001

The paper presents a sonar based map building method. The environment is a room or area inside a building, which is composed of four types of geometric primitives(corners, edges, cylinders, and walls). We also assume the environment can be modeled into two dimensional map in terms of planes(walls), points(corner and edge), and circle(cylinder). In a real world where most of the object surfaces are specular ones, a sonar sensor suffers from a multipath effect which results in a wrong interpretation of the location of an object. To reduce the effect and uncertainty, the method employs a simple thresholding technique for extracting circular arc features called regions of constant depth(RCD) from scanning sonar data. The usefulness of the approach is illustrated with the results produced by sets of experiments.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1998년도 추계학술대회
• /
• pp.189-190
• /
• 1998

In this paper, we show the realtime 3D reconstruction algorithm with the sliced CT images. The preprocessing is thresholding, labeling, contouring, and extracting dominant point. we reconstruct 3D image with dominant points using dynamic matching technique. The software implemented in Visualc++ 5.0 as a window-based application program.