• Journal of Broadcast Engineering
• /
• v.23 no.4
• /
• pp.503-510
• /
• 2018

Restoring of damaged images is a fundamental problem that was attempted before digital image processing technology appeared. Various algorithms for reconstructing damaged images have been introduced. However, the results show inferior restoration results compared with manual restoration. Recent developments of DNN (Deep Neural Network) have introduced various studies that apply it to image restoration. However, if the wide area is damaged, it can not be solved by a general interpolation method. In this case, it is necessary to reconstruct the damaged area through contextual information of surrounding images. In this paper, we propose an image restoration network using a generative adversarial network (GAN). The proposed system consists of image generation network and discriminator network. The proposed network is verified through experiments that it is possible to recover not only the natural image but also the texture of the original image through the inference of the damaged area in restoring various types of images.

• Journal of the Korea Computer Industry Society
• /
• v.3 no.12
• /
• pp.1679-1690
• /
• 2002

This paper, describe about a generation of a syllable restoration regulation for a post processing of a speech recognition and a decrease of a restoration candidate. It created a syllable restoration regulation to create a restoration candidate pronounced with phonetic value recognized through a post processing of the formula system that was a tone to recognize syllable unit phonetic value for a performance enhancement of a dialogue serial speech recognition. Also, I presented a plan to remove a regulation to create unused notation from a real life in a restoration regulation with a plan to reduce number candidate of a restoration meeting. A design implemented a restoration candidate set generator in order a syllable restoration regulation display that it created a proper restoration candidate set. The proper notation meeting that as a result of having proved about a standard pronunciation example and a word extracted from a pronunciation dictionary at random, the notation that an utterance was former was included in proved with what a generation became.

• Journal of KIISE:Software and Applications
• /
• v.37 no.4
• /
• pp.264-272
• /
• 2010

Example-based super resolution is a method to restore a high resolution image from low resolution images through training and retrieval of image patches. It is not only good in its performance but also available for a single frame low-resolution image. However, its time complexity is very high because it requires lots of comparisons to retrieve image patches in restoration process. In order to improve the restoration speed, an efficient patch retrieval algorithm is essential. In this paper, we applied various high-dimensional feature retrieval methods, available for the patch retrieval, to a practical example-based super resolution system and compared their speed. As well, we propose to apply the multi-phase candidate reduction approach to the patch retrieval process, which was successfully applied in character recognition fields but not used for the super resolution. In the experiments, LSH was the fastest among conventional methods. The multi-phase candidate reduction method, proposed in this paper, was even faster than LSH: For $1024{\times}1024$ images, it was 3.12 times faster than LSH.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.22 no.1
• /
• pp.21-27
• /
• 2004

It will be a real good news fer the people who were lost their hometown by the construction of a large dam to be restored to the farmer state. Focused on Cheung-pyung around where most part were submerged by the Chungju large Dam founded in eurly 1980s, It used remote sensing image restoration Technique in this study in order to restore topographical features before the flood with stereo effects. We gathered comparatively good satellite photos and remotely sensed digital images, then its made a new fusion image from these various satellite images and the topographical map which had been made before the water filled by the DAM. This task was putting together two kinds of different timed images. And then, we generated DEM including the outskirts of that area as matching current contour lines with the map. That could be a perfect 3D image of test areas around before when it had been water filled by making perspective images from all directions included north, south, east and west, fer showing there in 3 dimensions. Also, for close range visiting made of flying simulation can bring to experience their real space at that time. As a result of this experimental task, it made of new fusion images and 3-D perspective images and simulation live images by remotely sensed photos and images, old paper maps about vanished submerged Dam areas and gained of possibility 3-D terrain image restoration about submerged area by large Dam construction.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.12C
• /
• pp.1029-1034
• /
• 2010

For All Digital QPSK receivers, a phase recovery scheme is required to fix the arbitrarily rotated I/Q quadrature signals due to the transmission path and clock mismatch between the transmitter and the receiver. The conventional Costas phase recovery loop scheme requires a separate AGC(Automatic Gain Control) to obtain the performance independent of input signal power. This paper proposes a simple scheme which separates the phase and amplitude of the input signal via CORDIC algorithm and performs the phase recovery and amplitude compensation simultaneously. The proposed scheme can considerably reduce the logic resources in hardware implementation, has been verified by C++ and Model Sim simulations.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.293-299
• /
• 2012

Electrical impedance tomography is an imaging modality for determining the electrical properties inside a domain. Small currents are injected and the resulting voltages are measured through the electrodes. The internal electrical properties are reconstructed based on these voltage and current data. In this paper, a novel on-line Landweber algorithm was developed to fast estimate the resistivity distribution in the inverse calculation. Additionally, to enhance the reconstruction performance, a step-length was computed from the eigenvalue of the weighting matrix. The numerical experiments have been performed to evaluate the reconstruction performance of the proposed method.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.495-499
• /
• 1997

컴퓨터의 사용이 보편화됨에 따라 컴퓨터와 사용자 사이의 쉽고 자연스러운 의사 소통을 위한 자연어 인터페이스에 대한 연구가 활발히 진행되고 있다. 이 중에서 특히, 음성인식 분야는 음성명령, 받아쓰기 시스템 등 일반적인 컴퓨터 사용자의 요구를 충족시켜 줄 수 있는 분야로 주목을 받고 있다. 그러나 음성인식은 인식 자체만으로는 인식률에 한계가 있으며, 인식 결과를 향상시키기 위해서는 후처리 단계가 필요하다. 본 논문에서는 음성 인식의 성능을 향상시키기 위해 음성 인식의 결과로 들어온 연속된 한국어 음성을 올바른 음절로 복원시켜 주는 시스템을 구현하였다. 이 시스템에서는 어절단위의 연속된 한국어 음성을 입력으로 받아 한국어 발음 규칙을 역으로 적용하여 원래의 음절로 복원시키고, 형태소 분석기를 이용하여 복원된 음절이 올바른지를 확인하고 수정한다. 초등학교 교과서에 나오는 문장을 대상으로 본 시스템의 성능을 실험한 결과, 90.42%의 복원율을 나타내었다. 현재 정확하게 복원이 되지 않는 것 중에는 동음이의어가 차지하는 비중이 크며, 이 문제는 구문분석이나 의미분석을 이용하여 어느 정도 개선할 수 있을 것으로 보인다.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.1930-1931
• /
• 2011

세계적으로 많은 연구원들이 3차원 모델링에 대하여 연구하고 있다. 특히 무인자동차의 주행을 위한 센서시스템, 경로생성, 3차원 월드모델링 방법 등에 대한 연구가 많이 진행되고 있다. 이 논문은 스테레오 카메라를 이용한 3차원 도시환경복원을 위한 방법을 제안한다. 전체적인 시스템은 다중센서(스테레오 카메라, DGPS, IMU), PC, 이동로봇(전기차)으로 구성하였다. 스테레오 카메라를 통해 들어오는 이미지는 스테레오 정합기법을 이용하여 지역좌표계의 3차원 점군을 획득하는데 이용되며, DGPS와 IMU를 통해 얻은 정보는 이동로봇의 위치를 추정하는데 이용된다. 지역좌표계의 3차원 점군과 이동로봇의 위치를 융합하면 세계좌표계의 3차원 점군을 얻을 수 있으며, 이를 이용하여 도시환경을 복원을 시행하였다. 또한 스테레오 정합기법을 통해 얻어지는 점군의 중복복원을 회피하기 위하여 임시추적을 이용한다. 임시추적을 통해 동일한 점으로 판단되는 경우 중복복원을 방지하는 알고리즘을 제안한다. 실험결과는 3차원 도시환경 복원을 수행하여 점군으로 표현하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.1
• /
• pp.121-126
• /
• 2009

Plane-based computational integral imaging (CIIR) provides the reconstruction of depth-dependent 3D plane images. However, it has problem degrading the resolution of reconstructed images due to the artifact noise according to the depth. In this paper, to overcome this problem, a signal model for plane-based CIIR is explain. Also the compensation process is introduced to remove the noise caused from CIIR. Computational experiments show that we analyze the characteristics of noise in the reconstructed image of 2D Gaussian image and the high-resolution images can be obtained by using the compensation process.

• Journal of KIISE
• /
• v.42 no.11
• /
• pp.1452-1458
• /
• 2015

Korean Morphological Analysis is a difficult process. Because Korean is an agglutinative language, one of the most important processes in Morphological Analysis is Morpheme Recovery. There are some methods using Heuristic rules and Pre-Analyzed Partial Words that were examined for this process. These methods have performance limits as a result of not using contextual information. In this study, we built a Korean morpheme recovery system using deep learning, and this system used word embedding for the utilization of contextual information. In '들/VV' and '듣/VV' morpheme recovery, the system showed 97.97% accuracy, a better performance than with SVM(Support Vector Machine) which showed 96.22% accuracy.