http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
웨이블렛 잔여 채널 융합 기법을 활용한 U-Net 기반의 단일 영상 비 제거 알고리즘
박태희 한국멀티미디어학회 2023 멀티미디어학회논문지 Vol.26 No.9
Single image deraining aims to reconstruct a clean rain-free background image from a single image deteriorated by rain streaks and rain accumulation. However, actual rain streaks have various densities, shapes, and directions, so it is not easy to decompose rainy image into a clean background layer and rain steaks layers. This paper proposes an U-Net based single image deraining network using the wavelet residue channel fusion strategy. The proposed residue channel is computed in wavelet low-frequency domain to learn enough background information, and combined with four wavelet subbands in fusion block, allowing them to take advantage of their respective strengths. To extract the main features for rain removal, we propose the extraction module based on LSTM and SE_Res. Furthermore, we present an encoder-decoder subnetwork based on U-Net structure to capture multiscale information of rain steaks. To evaluate the performance of the proposed network, experiments were performed on widely used benchmarks, and the results show that our method outperforms some popular single image deraining methods.
간소화된 주성분 벡터를 이용한 벡터 그래픽 캐릭터의 얼굴표정 생성
박태희,Park, Tae-Hee 한국정보통신학회 2008 한국정보통신학회논문지 Vol.12 No.9
본 논문은 간소화된 주성분 벡터를 이용한 벡터 그래픽 캐릭터의 다양한 얼굴 표정 생성 방법을 제안한다. 먼저 Russell의 내적 정서 상태에 기반하여 재정의된 벡터 그래픽 캐릭터들의 9가지 표정에 대해 주성분 분석을 수행한다. 이를 통해 캐릭터의 얼굴 특성과 표정에 주된 영향을 미치는 주성분 벡터를 찾아내고, 간소화된 주성분 벡터로부터 얼굴 표정을 생성한다. 또한 캐릭터의 특성과 표정의 가중치 값을 보간함으로써 자연스러운 중간 캐릭터 및 표정을 생성한다. 이는 얼굴 애니메이션에서 종래의 키프레임 저장 공간을 상당히 줄일 수 있으며, 적은 계산량으로 중간 표정을 생성할 수 있다. 이에 실시간 제어를 요구하는 웹/모바일 서비스, 게임 등에서 캐릭터 생성 시스템의 성능을 상당히 개선할 수 있다. This paper presents a method that generates various facial expressions of vector graphic character by using the simplified principle component vector. First, we analyze principle components to the nine facial expression(astonished, delighted, etc.) redefined based on Russell's internal emotion state. From this, we find principle component vector having the biggest effect on the character's facial feature and expression and generate the facial expression by using that. Also we create natural intermediate characters and expressions by interpolating weighting values to character's feature and expression. We can save memory space considerably, and create intermediate expressions with a small computation. Hence the performance of character generation system can be considerably improved in web, mobile service and game that real time control is required.
박태희,Park, Taehee 대한임베디드공학회 2019 대한임베디드공학회논문지 Vol.14 No.4
In this paper, an efficient single dehazing algorithm is proposed based on linear transformation by assuming that a linear relationship exists in saturation component between the haze image and haze-free image. First, we analyze the linearity of saturation channel, estimate the medium transmission map in terms of the saturation component. Then, the intensity of haze-free image is assumed by using CLAHE to enhance contrast of haze image. Experimental results demonstrate that proposed algorithm can naturally recover the image, especially can remove color distortion caused by conventional methods. Therefore, our approach is competitive with other state-of-the art single dehazing methods.