• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권6호
• /
• pp.296-301
• /
• 2006

Even though the emergency telecommunication make possible that specialist offers medical care over emergency cases in moving vehicle, we still have many problems in transmitting the image or video of patient over several wireless networks. To alleviate the effect of channel errors on compressed video bit-stream, this paper analyzed the error resilient features of JPEG2000 standard and measured the quality of transmission over noisy wireless channel, CDMA2000 1xEV-DO networks, compared to the features of error resilient tool of MPEG-4. We also proposed the optimum solution of transmitting images over real 3G network using JPEG2000 error resilient tool.

• 정보처리학회논문지B
• /
• 제15B권2호
• /
• pp.123-130
• /
• 2008

자동 독순(automatic lipreading)은 화자의 입술 움직임을 통해 음성을 인식하는 기술이다. 이 기술은 잡음이 존재하는 환경에서 말소리를 이용한 음성인식의 성능 저하를 보완하는 수단으로 최근 주목받고 있다. 자동 독순에서 중요한 문제 중 하나는 기록된 영상으로부터 인식에 적합한 특징을 정의하고 추출하는 것이다. 본 논문에서는 독순 성능의 향상을 위해 새로운 필터링 기법을 이용한 특징추출 기법을 제안한다. 제안하는 기법에서는 입술영역 영상에서 각 픽셀값의 시간 궤적에 대역통과필터를 적용하여 음성 정보와 관련이 없는 성분, 즉 지나치게 높거나 낮은 주파수 성분을 제거한 후 주성분분석으로 특징을 추출한다. 화자독립 인식 실험을 통해 영상에 잡음이 존재하는 환경이나 존재하지 않는 환경에서 모두 향상된 인식 성능을 얻음을 보인다.

• 한국산업정보학회논문지
• /
• 제18권2호
• /
• pp.19-25
• /
• 2013

본 논문에서는 실 도로 환경에서 획득한 영상으로부터 도로 영역을 추적하는 방법을 제안한다. 제안된 방법은 이전 처리 결과로부터 미리 알려진 정보를 이용하여 현재 영상에서 도로를 검출하고 추적하는 방법이다. 제안된 방법은 시스템의 효율을 위해 연속적인 입력 영상에서 하위 60%이내에 도로가 있다고 가정하여 관심의 대상이 되는 영역(Region of Interest, ROI)을 설정하고 이 영역에서만 도로를 검출하고 추적한다. 최초 분할은 플러드필 알고리즘(Flood-fill algorithm)을 수행한 결과로부터 주위 영역과의 유사성을 평가한 후 병합하여 분할한다. 사전 정보로 사용되는 이전 영상에서 분할 결과에서 시드점(Seed Point)을 추출하고 이 시드점을 기준으로 현재 영상을 분할한다. 이전 영상에서 분할된 도로 영역과 현재 영상에서 분할된 결과를 변형된 자카드 계수(Jaccard coefficient)를 이용한 유사도 측정 결과에 따라 다음 영상에서 도로영역을 정제하고 추적한다. 연속적인 입력 영상을 대상으로 실험한 결과는 잡음이 존재하는 영상에서도 도로를 추적하는데 효과적임을 보여준다.

• 한국의학물리학회지:의학물리
• /
• 제29권4호
• /
• pp.150-156
• /
• 2018

This study aims to develop an improved Feldkamp-Davis-Kress (FDK) reconstruction algorithm using anisotropic total variation (ATV) minimization to enhance the image quality of low-dose cone-beam computed tomography (CBCT). The algorithm first applies a filter that integrates the Shepp-Logan filter into a cosine window function on all projections for impulse noise removal. A total variation objective function with anisotropic penalty is then minimized to enhance the difference between the real structure and noise using the steepest gradient descent optimization with adaptive step sizes. The preserving parameter to adjust the separation between the noise-free and noisy areas is determined by calculating the cumulative distribution function of the gradient magnitude of the filtered image obtained by the application of the filtering operation on each projection. With these minimized ATV projections, voxel-driven backprojection is finally performed to generate the reconstructed images. The performance of the proposed algorithm was evaluated with the catphan503 phantom dataset acquired with the use of a low-dose protocol. Qualitative and quantitative analyses showed that the proposed ATV minimization provides enhanced CBCT reconstruction images compared with those generated by the conventional FDK algorithm, with a higher contrast-to-noise ratio (CNR), lower root-mean-square-error, and higher correlation. The proposed algorithm not only leads to a potential imaging dose reduction in repeated CBCT scans via lower mA levels, but also elicits high CNR values by removing noisy corrupted areas and by avoiding the heavy penalization of striking features.

• 방송공학회논문지
• /
• 제13권5호
• /
• pp.760-770
• /
• 2008

플래쉬 영상은 비-플래쉬 영상에 비해 잡음이 적고 디테일을 잘 표현하지만, 강한 플래쉬 빛으로 인하여, 종종 부자연스럽게 회백색으로 포화되고 전면 물체 주위에는 비정상적으로 강한 그림자가 나타나는 등의 색상 열화를 겪는다. 본 논문에서는 동일 장면을 찍은 비-플래쉬 영상의 색상 정보를 전달함으로써 플래쉬 영상의 색상 화질을 개선하는 새로운 알고리즘을 제안한다. 제안하는 알고리즘은 플래쉬 영상의 선명한 에지와 섬세한 디테일을 더욱 잘 보존하면서도 자연스러운 색상의 영상을 구성함으로써 우수한 주관적 화질을 보여준다. 잡음 특성이 다른 두 가지 영상에 대한 실험을 통하여 성능을 검증하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 제14회 신호처리 합동 학술대회 논문집
• /
• pp.283-286
• /
• 2001

In this paper, we present a robust region segmentation method based on the watershed transformation of a pseudo-distance map (PDM). A usual approach for the segmentation of a gray-scale image with the watershed algorithm is to apply it to a gradient magnitude image or the Euclidean distance map (EDM) of an edge image. However, it is well known that this approach suffers from the oversegmentation of the given image due to noisy gradients or spurious edges caused by a thresholding operation. In this paper we show thor applying the watershed algorithm to the EDM, which is a regularized version of the EDM and is directly computed form the edgestrength function (ESF) of the input image, significantly reduces the oversegmentation, and the final segmentation results obtained by a simple region-merging process are more reliable and less noisy than those of the gradient-or EDM-based methods. We also propose a simple and efficient region-merging criterion considering both boundary strengths and inner intensities of regions to be merged. The robustness of our method is proven by testing it with a variety of synthetic and real images.

• Journal of Computational Design and Engineering
• /
• 제2권2호
• /
• pp.113-118
• /
• 2015

An important problem in low-dose CT is the image quality degradation caused by photon starvation. There are a lot of algorithms in sinogram domain or image domain to solve this problem. In view of strong self-similarity contained in the special sinusoid-like strip data in the sinogram space, we propose a novel non-local filtering, whose average weights are related to both the image FBP (filtered backprojection) reconstructed from restored sinogram data and the image directly FBP reconstructed from noisy sinogram data. In the process of sinogram restoration, we apply a non-local method with smoothness parameters adjusted adaptively to the variance of noisy sinogram data, which makes the method much effective for noise reduction in sinogram domain. Simulation experiments show that our proposed method by filtering in both image and projection domains has a better performance in noise reduction and details preservation in reconstructed images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권12호
• /
• pp.4776-4794
• /
• 2020

We propose a rapid adaptive learning framework for streaming object detection, called EER-ASSL. The method combines the expected error reduction (EER) dependent rollback learning and the active semi-supervised learning (ASSL) for a rapid adaptive CNN detector. Most CNN object detectors are built on the assumption of static data distribution. However, images are often noisy and biased, and the data distribution is imbalanced in a real world environment. The proposed method consists of collaborative sampling and EER-ASSL. The EER-ASSL utilizes the active learning (AL) and rollback based semi-supervised learning (SSL). The AL allows us to select more informative and representative samples measuring uncertainty and diversity. The SSL divides the selected streaming image samples into the bins and each bin repeatedly transfers the discriminative knowledge of the EER and CNN models to the next bin until convergence and incorporation with the EER rollback learning algorithm is achieved. The EER models provide a rapid short-term myopic adaptation and the CNN models an incremental long-term performance improvement. EER-ASSL can overcome noisy and biased labels in varying data distribution. Extensive experiments shows that EER-ASSL obtained 70.9 mAP compared to state-of-the-art technology such as Faster RCNN, SSD300, and YOLOv2.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권3호
• /
• pp.670-684
• /
• 2024

3D Cross-Modal Retrieval (3DCMR) is a task that retrieves 3D objects regardless of modalities, such as images, meshes, and point clouds. One of the most prominent methods used for 3DCMR is the Cross-Modal Center Loss Function (CLF) which applies the conventional center loss strategy for 3D cross-modal search and retrieval. Since CLF is based on center loss, the center features in CLF are also susceptible to subtle changes in hyperparameters and external inferences. For instance, performance degradation is observed when the batch size is too small. Furthermore, the Mean Squared Error (MSE) used in CLF is unable to adapt to changes in batch size and is vulnerable to data variations that occur during actual inference due to the use of simple Euclidean distance between multi-modal features. To address the problems that arise from small batch training, we propose a Noisy Center Loss (NCL) method to estimate the optimal center features. In addition, we apply the simple Siamese representation learning method (SimSiam) during optimal center feature estimation to compare projected features, making the proposed method robust to changes in batch size and variations in data. As a result, the proposed approach demonstrates improved performance in ModelNet40 dataset compared to the conventional methods.

• 한국측량학회지
• /
• 제36권3호
• /
• pp.127-134
• /
• 2018

Electric transmission towers are facilities to transport electrical power from a plant to an electrical substation. The towers are connected using power lines that are installed with a proper sag by loosening the cable to lower the tension and to secure the sufficient clearance from the ground or nearby objects. The power line sag may extend over the tolerance due to the weather such as strong winds, temperature changes, and a heavy snowfall. Therefore the periodical mapping of the power lines is required but the poor accessibility to the power lines limit the work because most power lines are placed at the mountain area. In addition, the manual mapping of the power lines is also time-consuming either using the terrestrial surveying or the aerial surveying. Therefore we utilized multiple overlapping images acquired from a low-cost drone to automatically reconstruct the power lines in the object space. Two overlapping images are selected for epipolar image resampling, followed by the line extraction for the resampled images and the redundant images. The extracted lines from the epipolar images are matched together and reconstructed for the power lines primitive that are noisy because of the multiple line matches. They are filtered using the extracted line information from the redundant images for final power lines points. The experiment result showed that the proposed method successfully generated parabolic curves of power lines by interpolating the power lines points though the line extraction and reconstruction were not complete in some part due to the lack of the image contrast.