• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권9호
• /
• pp.3672-3684
• /
• 2015

Recently, the standardization of backward compatible JPEG image coding for high dynamic range (HDR) image has been undertaken to establish an international standard called "JPEG XT." The JPEG XT consists of two layers: the base layer and the residual layer. The base layer contains tone mapped low dynamic range (LDR) image data and the residual layer contains the error signal used to reconstruct the HDR image. This paper gives the result of a study to evaluate the overall performance of tone mapping operators (TMOs) for this standard. The evaluation is performed using five HDR image datasets and six TMOs for profiles A, B, and C of the proposed JPEG XT standard. The Tone Mapped image Quality Index (TMQI) and no reference image quality assessment (NR IQA) are used for measuring the LDR image quality. The peak signal to noise ratio (PSNR) is used to evaluate the overall compression performance of JPEG XT profiles A, B, and C. In TMQI and NR IQA measurements, TMOs using display adaptive tone mapping and adaptive logarithmic mapping each gave good results. A TMO using adaptive logarithmic mapping gave good PSNRs.

• 대한원격탐사학회지
• /
• 제23권5호
• /
• pp.431-437
• /
• 2007

Multi-Spectral Camera(MSC) on the KOMPSAT-2 satellite was developed and launched as a main payload to provide 1m of GSD(Ground Sampling Distance) for one(1) channel panchromatic imaging and 4m of GSD for four(4) channel multi-spectral imaging at 685km altitude covering l5km of swath width. Since the compression on MSC image chain was required to overcome the mismatch between input data rate and output date rate JPEG-like method was selected and analyzed to check the influence on the performance. In normal operation the MSC data is being acquired and transmitted with lossy compression ratio to cover whole image channel and full swath width in real-time. In the other hand the MSC performance have carefully been handled to avoid or minimize any degradation so that it was analyzed and restored in KGS(KOMPSAT Ground Station) during LEOP(Launch and Early Operation Phase). While KOMPSAT-2 had been developed, new compression method based upon wavelet for space application was introduced and available for next satellite. The study on improvement of image chain including new compression method is asked for next KOMPSAT which requires better GSD and larger swath width In this paper, satellite image chain which consists of on-board image chain and on-ground image chain including general MSC description is briefly described. The performance influences on the image chain between two on-board compression methods which are or will be used for KOMPSAT are analyzed. The differences on performance between two methods are compared and the better solution for the performance improvement of image chain on KOMPSAT is suggested.

• Journal of Information Processing Systems
• /
• 제19권3호
• /
• pp.289-301
• /
• 2023

Due to the development and dissemination of modern technology, anyone can easily communicate using services such as social network service (SNS) through a personal computer (PC) or smartphone. The development of these technologies has caused many beneficial effects. At the same time, bad effects also occurred, one of which was the spam problem. Spam refers to unwanted or rejected information received by unspecified users. The continuous exposure of such information to service users creates inconvenience in the user's use of the service, and if filtering is not performed correctly, the quality of service deteriorates. Recently, spammers are creating more malicious spam by distorting the image of spam text so that optical character recognition (OCR)-based spam filters cannot easily detect it. Fortunately, the level of transformation of image spam circulated on social media is not serious yet. However, in the mail system, spammers (the person who sends spam) showed various modifications to the spam image for neutralizing OCR, and therefore, the same situation can happen with spam images on social media. Spammers have been shown to interfere with OCR reading through geometric transformations such as image distortion, noise addition, and blurring. Various techniques have been studied to filter image spam, but at the same time, methods of interfering with image spam identification using obfuscated images are also continuously developing. In this paper, we propose a deep learning-based spam image detection model to improve the existing OCR-based spam image detection performance and compensate for vulnerabilities. The proposed model extracts text features and image features from the image using four sub-models. First, the OCR-based text model extracts the text-related features, whether the image contains spam words, and the word embedding vector from the input image. Then, the convolution neural network-based image model extracts image obfuscation and image feature vectors from the input image. The extracted feature is determined whether it is a spam image by the final spam image classifier. As a result of evaluating the F1-score of the proposed model, the performance was about 14 points higher than the OCR-based spam image detection performance.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.530-532
• /
• 2007

Multi-Spectral Camera(MSC) is a main payload on the KOMPSAT-2 satellite to perform the earth remote sensing. The MSC instrument has one(1) channel for panchromatic imaging and four(4) channel for multi-spectral imaging covering the spectral range from 450nm to 900nm using TDI CCD Focal Plane Array (FPA). The compression method on KOMPSAT-2 MSC was selected and used to match EOS input rate and PDTS output data rate on MSC image data chain. At once the MSC performance was carefully handled to minimize any degradation so that it was analyzed and restored in KGS(KOMPSAT Ground Station) during LEOP and Cal./Val.(Calibration and Validation) phase. In this paper, on-orbit image data chain in MSC and image data processing on KGS including general MSC description is briefly described. The influences on image performance between on-board compression algorithms and between performance restoration methods in ground station are analyzed and discussed.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제4권12호
• /
• pp.571-576
• /
• 2015

다양한 안개 제거 기술이 개발되어왔으나 이들의 성능을 정량 정성적으로 평가하는 방식에 대한 연구는 다소 부족하다. 본 논문에서는 안개 제거 기술의 성능을 평가하기 위하여 사용할 수 있는 다양한 척도를 살펴본다. 성능 척도의 신뢰도 검증을 위하여, 고화질 칼라 깊이 영상을 이용하여 안개 영상을 합성하고 안개 제거 영상과 원 영상을 비교하는 방식을 택한다. 한편 안개 제거 기술을 화질을 기준으로 평가하는 방식이 아닌, 안개 제거 전 후 영상에 대한 컴퓨터 비전 기법의 성능을 비교하는 방식을 검토한다. 다양한 안개 제거 기술 성능 척도에 대한 비교 분석 및 문제점에 대한 해결 방안을 토의한다.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.207-220
• /
• 2022

Structural health monitoring (SHM) plays a vital role in the maintenance and operation of constructions. In recent years, autonomous inspection has received considerable attention because conventional monitoring methods are inefficient and expensive to some extent. To develop autonomous inspection, a potential approach of crack identification is needed to locate defects. Therefore, this study exploits two deep learning-based segmentation models, DeepLabv3+ and Mask R-CNN, for crack segmentation because these two segmentation models can outperform other similar models on public datasets. Additionally, impacts of label quality on model performance are explored to obtain an empirical guideline on the preparation of image datasets. The influence of image cropping and label refining are also investigated, and different strategies are applied to the dataset, resulting in six alternated datasets. By conducting experiments with these datasets, the highest mean Intersection-over-Union (mIoU), 75%, is achieved by Mask R-CNN. The rise in the percentage of annotations by image cropping improves model performance while the label refining has opposite effects on the two models. As the label refining results in fewer error annotations of cracks, this modification enhances the performance of DeepLabv3+. Instead, the performance of Mask R-CNN decreases because fragmented annotations may mistake an instance as multiple instances. To sum up, both DeepLabv3+ and Mask R-CNN are capable of crack identification, and an empirical guideline on the data preparation is presented to strengthen identification successfulness via image cropping and label refining.

• 한국측량학회지
• /
• 제29권1호
• /
• pp.101-109
• /
• 2011

본 논문에서는 다중 항공영상을 이용한 영상정합기법과, 그 성능을 향상시키기 위한 시도들에 대해 기술한다. 일반적으로 영상간의 정합은 하나의 기준영상을 기준으로 다른 영상과의 밝기값 상관계수를 이용한 유사도 분석으로 진행된다. 제안된 다중 영상 정합기법 알고리즘은 처리할 지역을 일정크기의 구역으로 나누고 각 구역에서 가장 정사영상에 가까운 영상을 기준으로 하여 Object space상에서 처리할 수 있는 방식이다. 이 방식을 통해 영상의 위치에 상관없이 균등한 품질의 DEM이 생성 가능함을 확인할 수 있었다. 또한 차폐탐지 및 생성된 차폐지도를 통한 성능 향상 실험을 하였으며 그 결과 더욱 정확한 3차원 정보의 표현이 가능함을 확인할 수 있었다.

• 한국측량학회지
• /
• 제29권5호
• /
• pp.449-457
• /
• 2011

As automated image processing techniques have been required in multi-temporal/multi-sensor geospatial image applications, use of automated but highly invariant image matching technique has been a critical ingredient. Note that there is high possibility of geometric and spectral differences between multi-temporal/multi-sensor geospatial images due to differences in sensor, acquisition geometry, season, and weather, etc. Among many image matching techniques, the SIFT (Scale Invariant Feature Transform) is a popular method since it has been recognized to be very robust to diverse imaging conditions. Therefore, the SIFT has high potential for the geospatial image processing. This paper presents a performance test results of the SIFT on geospatial imagery by simulating various image differences such as shear, scale, rotation, intensity, noise, and spectral differences. Since a geospatial image application often requires a number of good matching points over the images, the number of matching points was analyzed with its matching positional accuracy. The test results show that the SIFT is highly invariant but could not overcome significant image differences. In addition, it guarantees no outlier-free matching such that it is highly recommended to use outlier removal techniques such as RANSAC (RANdom SAmple Consensus).

• 한국측량학회지
• /
• 제30권6_2호
• /
• pp.665-672
• /
• 2012

Amid rapidly increasing imagery inputs and their volume in a remote sensing imagery database, Content-Based Image Retrieval (CBIR) is an effective tool to search for an image feature or image content of interest a user wants to retrieve. It seeks to capture salient features from a 'query' image, and then to locate other instances of image region having similar features elsewhere in the image database. For a CBIR approach that uses texture as a primary feature primitive, designing a texture descriptor to better represent image contents is a key to improve CBIR results. For this purpose, an extended feature vector combining the Gabor filter and co-occurrence histogram method is suggested and evaluated for quantitywise and qualitywise retrieval performance criterion. For the better CBIR performance, assessing similarity between high dimensional feature vectors is also a challenging issue. Therefore a number of distance metrics (i.e. L1 and L2 norm) is tried to measure closeness between two feature vectors, and its impact on retrieval result is analyzed. In this paper, experimental results are presented with several CBIR samples. The current results show that 1) the overall retrieval quantity and quality is improved by combining two types of feature vectors, 2) some feature is better retrieved by a specific feature vector, and 3) retrieval result quality (i.e. ranking of retrieved image tiles) is sensitive to an adopted similarity metric when the extended feature vector is employed.

• Journal of information and communication convergence engineering
• /
• 제9권6호
• /
• pp.747-752
• /
• 2011

The position detection of overlapping area in the interframe for image stitching using auto and cross correlation function (ACCF) and compounding one image with the stitching algorithm is presented in this paper. ACCF is used by autocorrelation to the featured area to extract the filter mask in the reference (previous) image and the comparing (current) image is used by crosscorrelation. The stitching is detected by the position of high correlation, and aligns and stitches the image in shifting the current image based on the moving vector. The ACCF technique results in a few computations and simplicity because the filter mask is given by the featuring block, and the position is enabled to detect a bit movement. Input image captured from CMOS is used to be compared with the performance between the ACCF and the window correlation. The results of ACCF show that there is no seam and distortion at the joint parts in the stitched image, and the detection performance of the moving vector is improved to 12% in comparison with the window correlation method.