• Korean Journal of Remote Sensing
• /
• v.21 no.2
• /
• pp.121-133
• /
• 2005

Texture imaging, which means texture image creation by co-occurrence relation, has been known as one of the useful image analysis methodologies. For this purpose, most commercial remote sensing software provides texture analysis function named GLCM (Grey Level Co-occurrence Matrix). In this study, texture-imaging program based on GLCM algorithm is newly implemented. As well, texture imaging modules for GLDV (Grey Level Difference Vector) are contained in this program. As for GLCM/GLDV Texture imaging parameters, it composed of six types of second order texture functions such as Homogeneity, Dissimilarity, Energy, Entropy, Angular Second Moment, and Contrast. As for co-occurrence directionality in GLCM/GLDV, two direction modes such as Omni-mode and Circular mode newly implemented in this program are provided with basic eight-direction mode. Omni-mode is to compute all direction to avoid directionality complexity in the practical level, and circular direction is to compute texture parameters by circular direction surrounding a target pixel in a kernel. At the second phase of this study, some case studies with artificial image and actual satellite imagery are carried out to analyze texture images in different parameters and modes by correlation matrix analysis. It is concluded that selection of texture parameters and modes is the critical issues in an application based on texture image fusion.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.1
• /
• pp.44-49
• /
• 2022

Abstract Recently, with the development of IoT technology and communication media, various video equipment is being used in industrial fields. Image data acquired from cameras and sensors are easily affected by noise during transmission and reception, and noise removal is essential as it greatly affects system reliability. In this paper, we propose a weight filter algorithm based on the pixel value distribution pattern to preserve details in the process of restoring images damaged in AWGN. The proposed algorithm calculates weights according to the pixel value distribution pattern of the image and restores the image by applying a filtering mask. In order to analyze the noise removal performance of the proposed algorithm, it was simulated using enlarged image and PSNR compared to the existing method. The proposed algorithm preserves important characteristics of the image and shows the performance of efficiently removing noise compared to the existing method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.5 no.6
• /
• pp.504-510
• /
• 2004

The objective of this paper is to propose the image interpolation method with pseudomedian filter for Field warping and morphing, and to evaluate and analyze its subjective image quality. The Field warping relatively gives rise to more computing overhead, but it can use the control line to control the warping result with more elaboration. Due to the working characteristics of the image warping and morphing process, various complex geometrical transformations occur and a image interpolation technique is needed to effectively process them. Of the various interpolation techniques, bilinear interpolation which shows above average performance is the most widely used. However, this technology has its limits in the reconstructivity of diagonal edges. The proposed interpolation method is to efficiently combine the bilinear interpolation and the pseudomedian filter-based interpolation which shows good performance in the reconstructivity of diagonal edges. According to the proposed interpolation method, we could get more natural warping and morphing results than other interpolation methods.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.4
• /
• pp.327-343
• /
• 2020

This study proposes a method to improve the geometric quality of KOMPSAT (Korea Multi-Purpose Satellite)-3/3A Level 1R imagery, particularly for efficient disaster damage analysis. The proposed method applies a novel grid-based SIFT (Scale Invariant Feature Transform) method to the Planetscope ortho-imagery, which solves the inherent limitations in acquiring appropriate optical satellite imagery over disaster areas, and the KOMPSAT-3/3A imagery to extract GCPs (Ground Control Points) required for the RPC (Rational Polynomial Coefficient) bias compensation. In order to validate its effectiveness, the proposed method was applied to the KOMPSAT-3 multispectral image of Gangnueng which includes the April 2019 wildfire, and the KOMPSAT-3A image of Daejeon, which was additionally selected in consideration of the diverse land cover types. The proposed method improved the geometric quality of KOMPSAT-3/3A images by reducing the positioning errors(RMSE: Root Mean Square Error) of the two images from 6.62 pixels to 1.25 pixels for KOMPSAT-3, and from 7.03 pixels to 1.66 pixels for KOMPSAT-3A. Through a visual comparison of the post-disaster KOMPSAT-3 ortho-image of Gangneung and the pre-disaster Planetscope ortho-image, the result showed appropriate geometric quality for wildfire damage analysis. This paper demonstrated the possibility of using Planetscope ortho-images as an alternative to obtain the GCPs for geometric calibration. Furthermore, the proposed method can be applied to various KOMPSAT-3/3A research studies where Planetscope ortho-images can be provided.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2003.06a
• /
• pp.1-5
• /
• 2003

의료영상의 분할은 의료영상을 컴퓨터 진단 및 가시화에 필요한 같은 성질을 가진 여러 조직으로 나누어주는 방법이다. 즉 입력되어진 영상을 처리하여 유사한 화소들의 집합인 영역들로 화소들을 구분하는 작업이며 영상분할의 결과는 영상인식의 정확성에 큰 영향을 미친다. MRI(Magnetic Resonance Imaging)으로부터 정상적인 세포조직 또는 뇌종양과 같은 비정상적인 세포조직의 가시화와 분석을 위해서는 대상 세포조직의 적절한 분류를 필요로 한다. 하지만 기존의 영역 검출 방법으로는 잡음이 섞여 있는 영상에서 여러 가지의 처리과정(주로 잡음 제거)이 필수적이고 그런 과정으로 인해 정확한 영역 검출이 힘들게 된다. 이에 잡음이 있더라도 이를 제거하기 위한 처리가 필요 없이 영역기반으로 필요한 파라미터의 추정을 통한 MRF(Markov Random Field)를 이용하여 보다 효율적이고 정확하게 MRI에서 질환 영역을 검출할 수 있다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.2
• /
• pp.214-220
• /
• 2021

In modern society, various digital communication equipments are being used due to the influence of the 4th industrial revolution, and accordingly, interest in removing noise generated in the data transmission process is increasing. In this paper, we propose a filtering algorithm to remove AWGN generated during digital image transmission. The proposed algorithm removes noise based on mask matching to preserve information such as the boundary of an image, and uses pixel values with similar patterns according to the pattern of the input pixel value and the surrounding pixels for output calculation. To evaluate the proposed algorithm, we simulated with existing AWGN removal algorithms, and analyzed using enlarged image and PSNR comparison. The proposed algorithm has superior AWGN removal performance compared to the existing method, and is particularly effective in images with strong noise intensity of AWGN.

• Investigative Magnetic Resonance Imaging
• /
• v.16 no.2
• /
• pp.115-123
• /
• 2012

Purpose : To evaluate white matter abnormalities on diffusion tensor imaging (DTI) in patients with mild Alzheimer disease (AD) and mild cognitive impairment (MCI), using tract-based spatial statistics (TBSS) and voxel-based morphometry (VBM). Materials and Methods: DTI was performed in 21 patients with mild AD, in 13 with MCI and in 16 old healthy subjects. A fractional anisotropy (FA) map was generated for each participant and processed for voxel-based comparisons among the three groups using TBSS. For comparison, DTI data was processed using the VBM method, also. Results: TBSS showed that FA was significantly lower in the AD than in the old healthy group in the bilateral anterior and right posterior corona radiata, the posterior thalamic radiation, the right superior longitudinal fasciculus, the body of the corpus callosum, and the right precuneus gyrus. VBM identified additional areas of reduced FA, including both uncinates, the left parahippocampal white matter, and the right cingulum. There were no significant differences in FA between the AD and MCI groups, or between the MCI and old healthy groups. Conclusion: TBSS showed multifocal abnormalities in white matter integrity in patients with AD compared with old healthy group. VBM could detect more white matter lesions than TBSS, but with increased artifacts.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2004.03a
• /
• pp.273-278
• /
• 2004

Feature identification is one of the largest issue in high spatial resolution satellite imagery. A popular method associated with this feature identification is image segmentation to produce image segments that are more likely to features interested. Here, it is, proposed that combination of edge extraction and region growing methods for image segments were used to improve the result of image segmentation. At the intial step, an image was segmented by edge detection method. The segments were assigned IDs, and polygon topology of segments were built. Based on the topology, the segments were tested their similarities with adjacent segments using multivariate analysis. The segments that have similar spectral characteristics were merged into a region. The test application shows that the segments composed of individual large, spectrally homogeneous structures, such as buildings and roads, were merged into more similar shape of structures.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.614-617
• /
• 2022

인공지능의 발전으로 의료영상 분야에서 딥러닝 기반 질병 진단 연구가 활발하다. 그러나 모델 개발 시 학습 데이터의 개수와 품질은 매우 중요한데, 의료 분야 특성상 접근 가능한 데이터셋이 적으며 오픈 데이터셋은 서로 다른 기관에서 배포되거나 웹상에서 수집된 것으로 진단에 적합한 품질을 기대하기 어렵다. 또한, 기존 연구는 데이터셋이 학습에 적합한지에 대한 품질검증 없이 사용한다. 따라서 본 논문에서는 임상에서 사용하는 화질 평가 요소에 근거를 두고 영역별 화소값 분석을 통한 흉부 X선 영상 품질 평가 기법을 제안한다. 오픈 데이터셋 JSRT, Chest14와 국내 A 병원 데이터셋 AUH에 제안한 기법을 적용한 결과 민감도 91.5%, 특이도 96.1%의 우수한 성능을 확인하였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.251-258
• /
• 2004

This paper proposes a method for estimating the illuminant chromaticity using the distributions of the camera responses obtained by a CCD camera in a real-world scene. Illuminant estimation using a highlight method is based on the geometric relation between a body and its surface reflection. In general, the pixels in a highlight region are affected by an illuminant geometric difference, camera quantization errors, and the non-uniformity of the CCD sensor. As such, this leads to inaccurate results if an illuminant is estimated using the pixels of a CCD camera without any preprocessing. Accordingly, to solve this problem the proposed method analyzes the distribution of the CCD camera responses and selects pixels using the Mahalanobis distance in highlight regions. The use of the Mahalanobis distance based on the camera responses enables the adaptive selection of valid pixels among the pixels distributed in the highlight regions. Lines are then determined based on the selected pixels with r-g chromaticity coordinates using a principal component analysis(PCA). Thereafter, the illuminant chromaticity is estimated based on the intersection points of the lines. Experimental results using the proposed method demonstrated a reduced estimation error compared with the conventional method.