• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.6 no.6
• /
• pp.980-985
• /
• 2002

In this paper, we analyzed satellite image with a high resolution compression performance. We need much time in a fast processing on vast satellite image pixel data. On compressing and decompressing, we should keep the information about road, building, forest, etc. In conclusion, we did analyze and compare the performance of compression and decompression for JPEG and WSQ(wavelet scalar quantization) method. As a result, we knew that WSQ was more efficient than JPEG.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.6
• /
• pp.628-630
• /
• 2016

Compressive sensing can recover an original sparse signal from a few measurements. Its performance is affected by the number of non-zero elements in the signal. The knowledge of partial locations of non-zero elements can improve the recovery performance. In this paper, we apply the partial location knowledge to the multipath matching pursuit. The numerical results show it improves the signal recovery performance and the channel estimation performance in the ITU-VB channel.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.475-477
• /
• 2005

본 연구는 신문기사나 백과사전 등의 문서에서 빈번히 발생하는 동사 파생 접미사와 어미가 생략된 형태의 서술성 명사를 동사로 복원하는 방법에 대한 것으로 이러한 복원은 문장구조 분석에 영향을 미친다. 기존 연구는 간단한 규칙만을 사용하지만 규칙을 사용하는 방법은 재현률에서 성능 저하를 보이기 때문에 본 연구에서는 이러한 생략 형태를 구분하여 규칙과 통계 방법을 사용하여 각각 적합한 형태에 적용하였다. 본 연구의 접근 방법은 규칙 기반에 비해 약 $30\%$, 통계 기반에 비해 약 $8\%$의 성능 향상을 보여서 문장 구조 분석에서는 $3.6\%$의 성능 향상을 보였다.

• Journal of the Korea Computer Graphics Society
• /
• v.25 no.5
• /
• pp.1-9
• /
• 2019

In this paper, we propose a video enhancement method using generative adversarial networks to remove raindrops and restore the background information on the removed region in the coastal wave video imagery distorted by raindrops during rainfall. Two experimental models are implemented: Pix2Pix network widely used for image-to-image translation and Attentive GAN, which is currently performing well for raindrop removal on a single images. The models are trained with a public dataset of paired natural images with and without raindrops and the trained models are evaluated their performance of raindrop removal and background information recovery of rainwater distortion of coastal wave video imagery. In order to improve the performance, we have acquired paired video dataset with and without raindrops at the real coast and conducted transfer learning to the pre-trained models with those new dataset. The performance of fine-tuned models is improved by comparing the results from pre-trained models. The performance is evaluated using the peak signal-to-noise ratio and structural similarity index and the fine-tuned Pix2Pix network by transfer learning shows the best performance to reconstruct distorted coastal wave video imagery by raindrops.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06b
• /
• pp.309-311
• /
• 2012

형태소 복원은 형태소 분석의 한 단계로 문장에 나타난 형태소의 변형 현상을 분석하여 규칙화하고 이를 이용하여 형태소 원형을 복원하는 것이다. 본 논문에서는 형태소 품사 부착 말뭉치로부터 다양한 형태소 변화 규칙을 학습하여 효과적으로 형태소 원형을 복원하기 위한 계산 방법을 비교한다. 이를 위해 계산 모델, 한글 코드, 학습 자료를 다르게 하여 학습하고 그에 따른 성능을 비교 분석한다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.102-105
• /
• 2000

본 논문에서는 잡음환경에서의 음성신호복원(Speech Enhancement) 시스템 구현을 목적으로 한다 이를 위한 적응필터로서 LMS(Least Mean Square)알고리즘 FIR필터를 제안한다. 또 정밀 필터로서 신경망 필터를 제안한다. 잡음환경에서의 음성신호 복원 시스템은 잡음에 의해 왜곡된 음성신호에서 잡음성분만을 제거함으로써 음성신호를 복원하는 시스템이다. 일반적으로 잡음은 시변특성과, 비선형적인 전달특성을 갖는다. 그러므로 파라미터가 고정된 필터로는 제어하기가 힘들다. 이러한 이유로 본 논문에서는 LMS알고리즘 적응필터를 적용한다. 신경망 필터는 오차 역전파 학습 알고리즘에 의해 오차를 최소화하는 방향으로 필터의 파라미터를 수정한다. 제안한 필터로 잡음환경에서의 음성신호복원 시스템을 구성하고, 실험을 통해 필터의 성능을 확인한다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.215-218
• /
• 2003

JPEG2000은 ISO/ITU-T에 의해 개발된 가장 최근의 영상 압축 표준으로 기존의 JPEG 표준이 제공하는 압축 성능을 개선하고 새로운 기능을 제공해준다. 이러한 기능 중 하나는 관심영역(Region of Interest) 부호화이다. JPEG2000 표준에서는 이러한 관심영역 부호화를 위해 Part 1에서는 Maxshift 방법을 정의하고 있다. Maxshift 방법은 관심영역을 완전히 복원하기 전까지 배경이 복원되지 않는다. 또한 영상전체를 웨이블릿 변환을 함으로써 메모리와 계산량이 상당히 많아진다. 본 논문에서는 JPEG 2000에서 사용되는 Maxshift 방법에서 관심영역이 완전복원되기 전에는 배경영역이 복원되지 않는 단점을 보완하고 부호화효율과 메모리 사용을 줄일 수 있는 영상 타일링에 기반한 관심영역 부호화 방법을 제안한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.1C
• /
• pp.72-80
• /
• 2009

Look-up table based inverse halftoning from the digital color halftone image is proposed in this paper, which uses vector adaptive filter for the nonexisting patterns in the table. Halftone image is obtained from a continuous -tone image, which can be restored into continuous one from the digital binary image by way of inverse halftoning method. Look-up table based method usually processes fast and has even performances over the various halftoning. The numbers of pixels in the pattern of table and the method how to define the table elements for each R, G, B channels can effect largely for its performance. The proposed method uses 16 pixels in the table considering the diversity of the expressions from their patterns and with memory size as well. This also proposed how to combine R, G, B channels into one. Experimental results showed the better performance in the expression of colors, better color restoration and the short processing time compared with the conventional ones.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.33 no.1
• /
• pp.63-74
• /
• 2023

In order to ensure safety to invasion of privacy, Federated Learning(FL) that learns using parameters is emerging. However a paper that leaks training data using gradients was recently published. Our paper implements an experiment to leak training data using gradients in a federated learning environment, and proposes a method to improve reconstruction performance by improving existing attacks that leak training data. Experiments using Yale face database B, MNIST dataset on the proposed method show that federated learning is not safe from invasion of privacy by reconstructing up to 100 data out of 100 training data when performance of federated learning is high at accuracy=99~100%. In addition, by comparing the performance (MSE, PSNR, SSIM) of pixels and the performance of identification by Human Test, we want to emphasize the importance of the performance of identification rather than the performance of pixels.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.18 no.5
• /
• pp.439-445
• /
• 2012

Only the sand carriers fitted with hopper doors can remove their hatch covers in current regulations. However, there is no sand carriers fitted with hopper doors in korea. Through the analysis of accidents, inspection of equipment installed on ships, and evaluation of stability and seakeeping performance concerning the sand carriers, it is expected that the current exemption requirement is modified for hatch covers for sand carriers. As the result, this paper proposed the removal of hatch covers and be fitted by tarpaulin instead to protect water ingress into the holds. This can be done by making the holds smaller designed to be filled full until the top of the hold without exceeding loadline. Also, the bilge pumps should have the sufficient capacity of pumping water out in the early stage of sand-water mixture to wetted condition in approximately 1 hour and be operationally ready in every voyage conditions.