• The KIPS Transactions:PartB
• /
• v.14B no.3 s.113
• /
• pp.145-152
• /
• 2007

In this paper, we propose an automatic extraction model for unknown translations and implement an unknown translation extraction system using the proposed model. The proposed model as a phrase-alignment model is incorporated with three models: a phrase-boundary model, a language model, and a translation model. Using the proposed model we implement the system for extracting unknown translations, which consists of three parts: construction of parallel corpora, alignment of Korean and English words, extraction of unknown translations. To evaluate the performance of the proposed system, we have established the reference corpus for extracting unknown translation, which comprises of 2,220 parallel sentences including about 1,500 unknown translations. Through several experiments, we have observed that the proposed model is very useful for extracting unknown translations. In the future, researches on objective evaluation and establishment of parallel corpora with good quality should be performed and studies on improving the performance of unknown translation extraction should be kept up.

• The Journal of the Korea Contents Association
• /
• v.9 no.10
• /
• pp.13-21
• /
• 2009

This paper describes research of image enhancement for detection of face area. Typical face recognition algorithms used fixed parameter filtering algorithms to optimize face images for the recognition process. A fixed filtering scheme introduces errors when applied to face images captured in various different environmental conditions. For acquiring face image of good quality from the image including complex background and illumination, we propose a method for image enhancement using the categories based on the image intensity values. When an image is acquired average values of image from sub-window are computed and then compared to training values that were computed during preprocessing. The category is selected and the most suitable image filter method is applied to the image. We used histogram equalization, and gamma correction filters with two different parameters, and then used the most suitable filter among those three. An increase in enrollment of filtered images was observed compared to enrollment rates of the original images.

• Journal of the Korea Computer Graphics Society
• /
• v.10 no.1
• /
• pp.1-6
• /
• 2004

본 논문에서는 프랙탈 영상압축에서 화질/압축률을 향상 시키면서 압축시간을 획기적으로 향상시키는 방법을 제안한다. 본 방법은 레인지블록의 크기가 아주 작으면 유사변환 계수들의 값을 극히 제한하더라도 유사한 도메인블록을 아주 가까운 주변에서 쉽게 찾을 수 있음을 활용하여 압축시간을 단축시키고 화질/압축률을 향상 시킨다. 또한, 본 방법은 인접한 레인지블록 들의 압축에 사용되는 계수들이 좋은 상호관계를 가지도록 유도하여 화질/압축률을 더욱 향상 시킨다. 본 방법은 대부분의 프랙탈 영상압축 방법에 쉽게 적용되어 그 성능을 향상시킬 수 있다. 특히 압축시간이 전역탐색 방법에 비해서 $512{\times}512$ 영상에서 약 60000 배 $256{\times}256$ 영상에서 약 15000 배 빠르며 실시간 동영상의 I-frame에도 사용가능 하다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2012.07a
• /
• pp.411-414
• /
• 2012

영상의 화질을 향상시키기 위한 다양한 방법이 제안되어 왔는데 DCT 영역에서 영상의 화질을 향상시키는 방법은 각 블록별 특성을 효율적으로 이용할 수 있고 JPEG, MPEG 등 표준 압축 기법으로 압축된 영상에 적용이 용이한 장점이 있다. 본 논문에서는 DCT 영역에서 contrast measure를 이용한 화질 향상 기법에서 발생할 수 있는 blocking effect를 크게 감소시키는 lapped transform 영역의 화질 향상 기법을 제안한다. 모의 실험을 통해서 제안하는 기법이 영상의 contrast를 향상시키면서 blocking effect를 크게 감소시키는 것을 보인다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.426-427
• /
• 2012

본 논문은 부호화된 저해상도의 깊이 영상과 고해상도의 색상 영상을 입력으로 고해상도의 깊이 영상을 생성하는 새로운 방법을 제안한다. 제안하는 방법은 결합 양측 필터를 이용하여 저해상도 깊이 영상의 경계 정보를 향상시킨다. 그런 다음, 깊이 영상 보간 단계에서 향상된 경계 정보를 참조하여 고품질 고해상도의 깊이 영상을 생성한다. 실험을 통한 깊이 영상과 합성영상의 화질 평가에서, 제안하는 방법이 기존의 3DV-ATM 깊이 영상 보간법보다 높은 성능을 보인다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2000.05a
• /
• pp.233-237
• /
• 2000

Generally, the still image magnification uses .image growing, interpolation in order to get magnificated image. Still image Magnification does not get high-resolution image because, amount of information is not sufficient. In this thesis, we proposed the enhance method of high resolution image magnification. Result of apply proposed method to Lena image, we gained result of enhancement more better than formerly simple technique.

• Journal of Korea Multimedia Society
• /
• v.8 no.9
• /
• pp.1187-1194
• /
• 2005

In this paper, new contrast enhancement algorithms that use temporal decimation method and approximated CDF(Cumulative Distribution Function) are proposed. They reduce the amount of computation which is required for image contrast enhancement. Simulation results show that the algorithms can achieve significant reduction in the computational cost and the hardware complexity. Visual test and standard deviation of their histogram have been introduced to evaluate the resultant output images of the proposed method and the original ones.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.11-14
• /
• 2003

본 논문에서는 실시간 고해상도 FPD(Flat Panel Display)에서 동영상의 화질 향상을 위해 입력되는 영상신호의 평균과 분산을 이용함으로써 화면의 밝기상태에 따라 적응적으로 콘트라스트를 향상시켰다. 또한, 영상의 깎기에 따른 가중치 결정은 표본(픽셀) 수가 적절히 많으면, 그 분포는 정규분포를 따른다는 "중심극한이론(Central Limit Theorem)"을 적용하여 고해상도 입력 영상에 대한 히스토그램의 분포가 정규분포와 유사하다고 가정하였으며 영상의 밝기 종류를 총 4가지로 구분하여 영상의 밝기 종류에 따라 최적의 가중치로 콘트라스트를 향상시켰다. 제안한 방법은 C언어로 시뮬레이션 하였으며 시뮬레이션 결과 향상된 영상을 얻을 수 있었다.

• Journal of Korea Multimedia Society
• /
• v.14 no.11
• /
• pp.1365-1372
• /
• 2011

This paper proposes a cognitive contrast enhancement algorithm based on the non-linear masking to advance low cognitive contrast in dark regions of images. In order to improve brightness in dark regions of an image, we propose a new contrast enhancement algorithm based on the non-linear masking using regional adaptive parameters of an image. For performance evaluation of the proposed method, chromaticity and saturation comparison as a quantitative assessment and z-score comparison as a qualitative assessment were executed between test images and their simulated images by SSR, MSR, a conventional non-linear masking and the proposed method, respectively. As a result, the proposed method showed low chromaticity and saturation difference and improved cognitive contrast for the three methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.7
• /
• pp.1681-1685
• /
• 2014

The visual quality of medical image is an important factor for diagnosis accuracy. Therefore, the methods to improve the quality of medical image have studied. Among them, frequency domain filter is very powerful method to impove the visual quality of image. In this paper, the X-ray medical image using optimized high-pass filter was improved edges. The result image was improved edge and contrast of flat area using optimized high frequency emphasis filter. At last, the result image is to minimize the noise using the minimum mean square error(MMSE) filter. As a result, the proposed method has enhanced contrast and edge of the image in the contrast of existing filters, with the noise canceling effect.