• 정보처리학회논문지B
• /
• 제11B권6호
• /
• pp.653-660
• /
• 2004

객체지향 분석-합성 부호화는 일련의 영상들을 여러 개의 동 객체로 분할한 후 각 객체의 움직임을 추정하고 보상한다. 그것은 각 객체에 있는 움직임 정보를 추정하기 위해 변환 파라미터 기법을 적용하는데 이때 변환 파라미터 기법은 그레디언트 연산자를 사용하기 때문에 매우 복잡한 계산이 요구된다. 본 논문의 목적은 객체지향 분석-합성 부호화에서 계층적 구조를 사용한 효율적인 변환파라미터 기법을 개발하는 것이다. 이러한 목표를 달성하기 위해 본 논문은 계층적 구조를 사용한 하이브리드 변환파라미터 추정 방법과 적응형 변환 파라미터 방법의 두 가지 알고리듬을 제안한다. 전자는 파라미터 검증 방법을 사용하는데 원 영상을 1/4로 축소한 저해상도 영상에서 파라미터 검증 처리 방법에 의해 6-파라미터 또는 8-파라미터로 추정한다. 후자는 동일한 계층적 방법을 적용한 다음 변환 파라미터를 적응적으로 추정하기 위해 temporal co-occurrence 행렬에 기반 한 움직임 량을 측정하는 움직임 판단기준을 사용한다. 이러한 방법은 고속이며, 병렬처리 기법을 사용할 경우 쉽게 하드웨어로 구현할 수 있는 이점이 있다. 이론 분석 및 모의시험 결과 제안한 방법이 기존 방법에 비해 약 1/4 정도로 월등한 계산량 감축을 얻을 수 있었으며, 아울러 제안한 방법들에 의해 복원된 신호대 잡음비는 6-파라미터와 8-파라미터 추정 방법에 의해 복원된 결과들 사이에 있음을 보여 준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권7호
• /
• pp.2400-2419
• /
• 2014

Pre-segmented pixels can reduce the difficulty of segmentation and promote the segmentation performance. This paper proposes a novel segmentation method based on merging texture superpixels by computing inner similarity. Firstly, we design a set of Gabor filters to compute the amplitude responses of original image and compute the texture map by a salience model. Secondly, we employ the simple clustering to extract superpixles by affinity of color, coordinates and texture map. Then, we design a normalized histograms descriptor for superpixels integrated color and texture information of inner pixels. To obtain the final segmentation result, all adjacent superpixels are merged by the homogeneity comparison of normalized color-texture features until the stop criteria is satisfied. The experiments are conducted on natural scene images and synthesis texture images demonstrate that the proposed segmentation algorithm can achieve ideal segmentation on complex texture regions.

• 한국멀티미디어학회논문지
• /
• 제18권3호
• /
• pp.349-358
• /
• 2015

Simulating color appearance of makeup effect is an important issue in computer graphics as well as cosmetic industry. Most of previous works on makeup simulation are simple color blending to mimic the cosmetic effects. Some of previous works employed Kubelka-Munk model to accurately simulate the layering effect of cosmetics. However, the simulation limited on single point, and the rest of area are still computed by simple color blending utilizing the color of the single point simulation. This paper presents an image-based method to compute the color appearance effect of makeup application using per-pixel Kubelka-Munk model. Unlike the previous methods, it is possible to compute per-pixel application thickness as well as optical property of cosmetics. The computed thickness pattern can be used in makeup simulation for a more realistic makeup simulation.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1997년도 학술대회
• /
• pp.135-138
• /
• 1997

Multi-view 영상 DB의 surround view 입체 화상을 재현하기 위해서는 영상 정보를 효과적으로 합성, 보간하는 방법이 필연적으로 요구된다. 다시점 입체 영상의 표시 기능을 구현하기 위해서 이론적으로는 충분한 개수의 카메라를 상하 좌우로 배치하여 영상을 획득하고 보는 이의 위치에 가장 적합한 영상을 선택하여 표현하면 된다. 이 경우 많은 수의 카메라로부터 입력되는 방대한 영상 데이터의 저장, 처리, 전송, 설치 문제 등 현실적으로 많은 제약점이 존재한다. 이러한 문제점을 해결하기 위해 기존의 블록 매칭과 같은 3D 구조 추정에 기초하여 블록 단위의 깊이 정보와 텍스쳐 정보의 추출, 다시점 영상 set의 가장 왼쪽 영상으로부터 시작하여 차례로 한 줄씩 쌓아서 얻어진 EPI(Epipolar Plane Image)에 기초한 유사 영상 값의 자취선 탐색 방법에 의한 시차와 텍스쳐 정보 추출로 전체 다안화상을 다해상도로 표현하여 전송하는 방식을 제안한다. 다해상도의 영상 표현과 점진적 전송 방법을 통해 다시점 영상 검색 시스템의 성능향상을 위한 네트워크 모델링을 제안하고자 한다.

• International journal of advanced smart convergence
• /
• 제4권2호
• /
• pp.6-13
• /
• 2015

With the spread of various kinds of cameras such as digital cameras and DSLR and a growing interest in high-definition and high-resolution images, a method that synthesizes multiple images is being studied among various methods. High Dynamic Range (HDR) images store light exposure with even wider range of number than normal digital images. Therefore, it can store the intensity of light inherent in specific scenes expressed by light sources in real life quite accurately. This study suggests feature points synthesis algorithm to improve the performance of HDR panorama recognition method (algorithm) at recognition and coordination level through classifying the feature points for image recognition using more than one multi frames.

• 융합신호처리학회 학술대회논문집
• /
• 한국신호처리시스템학회 2000년도 추계종합학술대회논문집
• /
• pp.85-88
• /
• 2000

Signal splitting and perfect reconstruction in subband coding is based on the assumption that quantization errors are negligible. But if subband signal is quantized, 4 types of errors occurs thus it is not impossible to do perfect reconstruction. These errors are QMF design error, aliasing error, signal error and random error. By using the QMF for subband splitting, the QMF error does not present. and by using the Lloyd-Max quantizer for the quantization and by using an appropriate synthesis filter, all signal dependent errors can be cancelled and the remaining error is random error which is uncorrelated with the original image〔1〕. In this thesis, Lenna and Camera-Man image are devided into 10 subbands by using the D4 and D20 wavelet And the subband signals are quantized by using the Lloyd-Max quantizer and the quantization errors are compared. and evaluated.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 추계학술대회 논문집 학회본부
• /
• pp.442-444
• /
• 1996

This paper presents a new image rectification method using stereo image pairs to synthesize arbitrary viewing images. The image rectification is a preprocessing procedure that generates a vertically aligned images and makes epipolar lines collinear. The proposed rectification method has more robustness by considering the real situations such as the mismatch of pan angle, tilt angle and vertical shifting of cameras than previous method[5] which considers only pan angle. We evaluate the proposed method by comparison with previous method using synthesized images.

• 대한전자공학회논문지SP
• /
• 제44권2호
• /
• pp.19-26
• /
• 2007

시그마필터는 특성화된 근접분포구도로 시그마 값을 국부통계값들로부터 산출한다. 표준평균필터를 교정하여 잡음을 제거하는 동시에 에지를 보존하도록 설계되어 있으나 미세부분 향상에는 취약하다. 종래의 시그마 접근들도 잡음제거에 치중되어 있었을 뿐 특징구역의 향상은 소홀하였다. 본 논문은 국부통계값들과 함수 부합을 활용한 적응영상향상 알고리즘을 제안한다, 이들 값들은 영상향상의 적응 실현에 유용하여 잡음을 평활시키고 영상의 미세부분을 향상한다. 국부적응처리를 위하여 매 이동창에서 평가척도를 만족하는 파라미터가 추정되고 비중화된다. 그리고 실험 결과는 제안된 방식의 효능을 보여준다.

• 복식
• /
• 제51권3호
• /
• pp.111-127
• /
• 2001

This study aims to apply the formative aesthetic of human body to the form of clothing. For this purpose I try to find the various methods of analysis used in the work of sculpture. The method of inference and the checklists of design are used to relate the sculpture with the clothing design specifically. This methodology intends to regard human body as an artistic form and use the image of sculpture to the maximum. Especially I try to derive the motives of design and recreate them in clothing design emphasizing silhouette. On this methodology, following results were developed. First, the observations on the formative characteristic of human body show that the transformed form of human body expresses more perfect image of human body than the original form. The power of simplicity heightens the total beauty of the work. Second, the image of human body expressed in simplicity heightens the total beauty of the work. Second, the image of human body expressed in simplicity and exaggeration can be variously recreated in a silhouette with the formative and cubic effect, simplicity, and activity. Third, the elegant and static image found in the analysis and synthesis of human body can be used as a motive of clothing design and the changed details lead to the transformation of silhouette. Fourth, in developing designs by the item of checklists, one motive can be variously recreated according to the methods of designs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권1호
• /
• pp.183-200
• /
• 2020

This paper presents an efficient interactive framework for perspective scene completion and editing tasks, which are available largely in the real world but rarely studied in the field of image completion. Considering that it is quite hard to extract perspective information from a single image, this work starts from a friendly and portable interactive platform to obtain the basic perspective data. Then, in order to make this interface less sensitive, easier and more flexible, a perspective-rectification based correction mechanism is proposed to iteratively update the locations of the initial points selected by users. At last, a complanate mesh is generated by the geometry calculations from these corrected initial positions. This mesh must approximate the perspective direction and the structure topology as much as possible so that the filling process can be conducted under the constraint of the perspective effects of the original image. Our experiments show the results with good qualities and performances, and also demonstrate the validity of our approaches by various perspective scenes and images.