• 한국지능시스템학회논문지
• /
• 제13권6호
• /
• pp.649-654
• /
• 2003

대부분의 영상 임계화 방법들은 그레이 레벨의 히스토그램 함수를 이용하여 임계값을 설정한다. 본 논문에서는 히스토그램을 이용하는 기존의 영상 임계화 방법들의 단점을 간단하면서 효율적으로 보여주는 예제를 제시한다. 이러한 기존의 임계화 방법들의 단점을 개선하기 위해 그레이 레벨의 분포를 기반으로 하는 새로운 그레이 레벨 임계값 설정방법을 제안한다. 마지막으로, 여러 가지 예제를 통해 제안된 임계값 설정 방법의 효율성을 보인다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.1811-1814
• /
• 2002

In this paper, we propose an improved contrast control method f9r image improvement of multi-gray scale image. The proposed contrast control method can improve contrast of image by changing gradient of weight as the type of input image. In addition, the proposed method does not require field and frame memory for large amount of computed data. And, the proposed method can be easily applied to the FPD fur real-time processing because of its less hardware complexity than that of the conventional methods. Also it can flexibly control the contrast of input gray level by varying the weight values that control the contrast range. The operation and performance of the proposed controller have been verified using computer simulation.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2003년도 춘계학술발표논문집 (상)
• /
• pp.631-634
• /
• 2003

오늘날 CT나 MR등을 통한 의학 영상 기술과 컴퓨터 성능의 향상으로 인체 내부 장기의 영상을 비교적 용이하게 얻을 수 있으며 얻어진 영상 정보는 컴퓨터로 수치화 되므로 데이터의 조작 및 가공이 용이하다. 그러나, 이렇게 얻어진 의학 영상들은 보통 2 차원적 슬라이스 image 형태로 얻어진다. 일반적으로 슬라이스 사이의 간격은 조사량 등 여러 문제 때문에, 항상 동일한 간격을 유지하고 있지 않은 경우가 많으며 슬라이스 사이 간격이 슬라이스 내의 픽셀 간격보다 큰 경우가 대부분이다. 이러한 image로부터 3 차원적 디스플레이나, 조작, 분석을 하기 위해서는 같은 간격의 image를 얻어야 한다. 이러한 이유로 인하여 보간(Interpolation) 기법이 의학 영상 분야에서 많이 사용된다. 본 논문은 형태-기반 보간 방법을 gray-scale image 에 적용이 가능하도록 확장한 그레이 수준 형태 기반 보간 알고리즘을 구현하였다. 그리하여, 본 논문이 제안한 알고리즘을 슬라이스 간격이 큰 2차원 복부 CT 영상에 적용시켜 다른 보간 법들보다 향상된 결과를 확인할 수 있었다.

• 한국정보통신학회논문지
• /
• 제8권3호
• /
• pp.708-713
• /
• 2004

그레이 스케일 이미지를 이용한 차량 감지 방법은 주차장에서 빈 공간으로 진입하는 차량의 안내나 기타 유사한 목적들을 위해 제안되고 있다. 본 논문은 그레이레벨 이미지를 이용하여 주차여부를 확인하고, 주차공간을 분석하는 방법을 제안한다. 실험결과로써 각기 2일 동안 새벽부터 해질녘까지 야외 주차장을 이용하여 획득한 129개의 영상을 이용하여 실험한 결과 98.7％의 성공률을 나타내었다.

• 한국시뮬레이션학회논문지
• /
• 제10권3호
• /
• pp.59-70
• /
• 2001

Typical low-level image processing tasks require thousands of operations per pixel for each input image. Traditional general-purpose computers are not capable of performing such tasks in real time. Yet important features of traditional computers are not exploited by low-level image processing tasks. Since storage requirements are limited to a small number of low-precision integer values per pixel, large hierarchical memory systems are not necessary. The mismatch between the demands of low-level image processing tasks and the characteristics of conventional computers motivates investigation of alternative architectures. The structure of the tasks suggests employing an array of processing elements, one per pixel, sharing instructions issued by a single controller. In this paper we implemented various image processing filtering using the format converter. Also, we realized from conventional gray image process to color image process. This design method is based on realized the large processor-per-pixel array by integrated circuit technology This format converter design has control path implementation efficiently, and can be utilize the high technology without complicated controller hardware.

• Journal of the Korean Wood Science and Technology
• /
• 제24권4호
• /
• pp.87-92
• /
• 1996

When cutting 2.0cm-thick red oak and hard maple with an air-jet-assisted carbon-dioxide laser of 2kW output power, maximum feed speed at the point of full penetration of the beam decreased with increasing the angle between grain and cutting direction. Feed speed averaged 3.75 and 3.38 meters per minute for red oak and hard maple, respectively. Gray-level of laser-cut surfaces were analyzed by image analysis system. The highest gray level of laser-cut surface was obtained when red oak was cut parallel to grain by laser. Surface profiler was used to scan the sawn and laser-cut surfaces. Center line average roughnesses of laser-cut surfaces were higher than those of sawn surfaces. Scanning electron micrographs showed the cell walls which were melted by laser.

• Journal of information and communication convergence engineering
• /
• 제20권1호
• /
• pp.58-64
• /
• 2022

Breast ultrasonic reading is critical as a primary screening test for the early diagnosis of breast cancer. However, breast ultrasound examinations show significant differences in diagnosis based on the difference in image quality according to the ultrasonic equipment, experience, and proficiency of the examiner. Accordingly, studies are being actively conducted to analyze the texture characteristics of normal breast tissue, positive tumors, and malignant tumors using breast ultrasonography and to use them for computer-assisted diagnosis. In this study, breast ultrasonography was conducted to select 247 ultrasound images of 71 normal breast tissues, 87 fibroadenomas among benign tumors, and 89 malignant tumors. The selected images were calculated using a statistical method with 21 feature parameters extracted using the gray level co-occurrence matrix algorithm, and classified as normal breast tissue, benign tumor, and malignancy. In addition, we proposed five feature parameters that are available for computer-aided diagnosis of breast cancer classification. The average classification rate for normal breast tissue, benign tumors, and malignant tumors, using this feature parameter, was 82.8%.

• 대한전자공학회논문지
• /
• 제24권4호
• /
• pp.713-718
• /
• 1987

In this paper, an iterative restoration algorithm from power spectral density with 1 bit sign information of real part of two dimensional Fourier transform of image corrupted by additive white Gaussian noise is proposed. This method is a modified version of image reconstruction algorithm from power spectral density. From the results of computer simulation with original 32 gray level imgae of 64x64 pixels, we can find that restorated image after each iteration converge to original image very fast, and SNR gain be at least 8[dB] after 10th iteration for corrupted image with additive white Gaussian noise.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.192-194
• /
• 2003

Since the details in quasi-homogeneous region will be destroyed from the conventional global image enhancement method such as histogram equalization. This defect is caused by the saturation of gray level in equalization process. So the local histogram equalization for each quasi-homogeneous region will be used in order to improve the details in the region itself. To obtain the quasi- homogeneous regions, the original image must be segmented. Here we applied the watershed transform to the interesting image. Since the watershed transform is based on mathematical morphology, therefore, the regions touch can be effectively separated. Hence two adjacent regions which have the similar gray pixels will be split off. The process will be independently applied to three different spectral images. Then three different colors are assigned to each processed image in order to produce a color composite image. By the proposed algorithm, the result image shows the better perception on image details. Therefore, the high efficiency of image classification can be obtained by using this color image.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.2059-2064
• /
• 2004

Texture analysis is an important role for automatic visual insfection. This paper presents an application of wavelet extension and Gray level co-occurrence matrix (GLCM) for detection of defect encountered in textured images. Texture characteristic in low quality images is not to easy task to perform caused by noise, low frequency and small dimension. In order to solve this problem, we have developed a procedure called wavelet image extension. Wavelet extension procedure is used to determine the frequency bands carrying the most information about the texture by decomposing images into multiple frequency bands and to form an image approximation with higher resolution. Thus, wavelet extension procedure offers the ability to robust feature extraction in images. Then the features are extracted from the co-occurrence matrices computed from the sub-bands which performed by partitioning the texture image into sub-window. In the detection part, Mahalanobis distance classifier is used to decide whether the test image is defective or non defective.