• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.484-487
• /
• 2003

본 논문에서는 CCD 카메라로부터 입력된 얼굴영상에서 피부색상 정보를 이용하여 얼굴을 검출하고 얼굴특징자인 눈, 코, 입의 얼굴특징 벡터를 추출한 후, 벡터들로부터 특징 평가함수를 적용하여 개인의 얼굴을 인식하는 알고리즘을 제안하였다. 제안한 논문에서는 입력 영상에서 대하여 얼굴 피부색의 정보와 명암도 정보를 동시에 사용하여 얼굴영역을 검출한 후, 검출한 얼굴 영역에서 특징점인 눈, 코, 입 등을 추출한 다음, 각 특징 점들에 대한 기하학적 위치특성과 상관성을 이용한 얼굴특징 평가함수를 구성하였다. 제안한 알고리즘으로 230 장의 얼굴영상에 대하여 실험에 적용한 결과 얼굴검출 효율과 인식 성능을 개선할 수 있었다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.2
• /
• pp.91-95
• /
• 2004

In this paper, we propose a fuzzy controller for the evaluation of the quantization parameters in the H.263 coder. Our method adopts the Mamdani method for fuzzification and adopts the centroid method for defuzzification respectively. The inputs are variance, entropy in the spatial domain, current motion vector and previous motion vector in the temporal. Fuzzy variables are determined to be compatible in visual characteristics and fuzzy membership function is induced and then, FAM banks are designed to reduce the number of rules. In this paper, fuzzy quantization has been applied to a practical video compression. This results show that the quality of decode image enhances and the rate control method using fuzzy quantization is effective.

• Korean Journal of Remote Sensing
• /
• v.15 no.3
• /
• pp.183-194
• /
• 1999

The Brightness, color and texture included in a multispectral satellite data are used as important factors to analyze and to apply the image data for a proper use. One of the most significant process in the satellite data analysis using texture or color information is to extract features effectively expressing the information of original image. It was described in this paper that six features were introduced to extract useful features from the analysis of the satellite data, and also a classification network using the back-propagation neural network was constructed to evaluate the classification ability of each vector feature in SPOT imagery. The vector features were adopted from the training set selection for the interesting region, and applied to the classification process. The classification results showed that each vector feature contained many merits and demerits depending on each vector's characteristics, and each vector had compatible classification ability. Therefore, it is expected that the color and texture features are effectively used not only in the classification process of satellite imagery, but in various image classification and application fields.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.1
• /
• pp.161-169
• /
• 1996

This paper presents a new search region prediction method using vector quantization for the motion estimation. We find motion vectors using the full search BMA from two successive frame images first. Then the motion vectors are used for training a codebook. The trained codebook is the predicted search region. We used the unsupervised neural network for VQ encoding and codebook design. A major advantage of formulating VQ as neural networks is that the large number of adaptive training algorithm that are used for neural networks can be applied to VQ. The proposed method reduces the computation and reduce the bits required to represent the motion vectors because of the smaller search points. The computer simulation results show the increased PSNR as compared with the other block matching algorithms.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2001.11b
• /
• pp.95-98
• /
• 2001

본 논문에서는 동영상 압축 방식에서 압축 효율을 증가시키는 움직임 벡터 추정 방식의 개선된 방법에 대해 제안한다. 움직임 벡터 추정 방식의 하나인 BMA(block matching algorithm) 중에 가장 좋은 성능을 보이는 FSA(full search algorithm)은 움직임의 정도를 예측하지 않고 모든 블록에 대해 고정적인 탐색 영역이 결정되어 있다. 이는 계산량을 상당히 크게 하는 원인이 된다. 제안된 방식은 블록 사이의 움직임이 유사한 특성을 이용하여 블록 단위의 동적인 탐색 영역을 결정하여 계산량을 효율적으로 줄이면서 FSA와 유사한 특성을 유지하게 된다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2000.11a
• /
• pp.218-223
• /
• 2000

영상에서 색상은 조명과 물체의 반사 특성에 의해 걸정되므로고 정확한 조명성분 추출을 통해 물체 고유의 색상을 복원할 수 있다. 물체 색상과 하이라이트 색상의 분포와 이들간의 관계를 잘 반영하여 모델링한 Dichromatic 반사 모델에서는, 3차원 RGB 공간에서의 하이라이트(highlight) 영역에 의한 클러스터 분포형상으로부터 표면반사벡터를 구해 이것을 조명벡터로 결정하였다. 그러나, 표면반사벡터의 방향은 물체색상의 영향을 받아 실제 조명벡터와 동일한 방향을 나타내지 못한다는 것을 실험을 통해 알 수 있었다. 실제적으로 하이라이트영역에 대한 클러스터는 물체 색상으로부터 조명색상에 근접한 방향으로 형성되며, 조명벡터로는 글러스터의 최대값으로 향하는 것을 취하는 것이 보다 정확하다는 특성이 있음을 확인하였다. 본 논문에서는 여러 가지 실험을 통해 이러한 특성이 타당함을 제시하고, 그래픽반사모델을 이용하여 하이라이트 색상에 대한 새로운 해석 방법을 제시한다.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.369-374
• /
• 2002

In this paper, we propose the react-time car license plate recognition algorithm using intensity variation and geometric pattern vector. Generally, difference of car license plate region between character and background is more noticeable than other regions. And also, car license plate region usually shows high density values as well as constant intensity variations. Based on these characteristics, we first extract car license plate region using intensity variations. Secondly, lightness compensation process is performed on the considerably dark and brightness input images to acquire constant extraction efficiency. In the proposed recognition step, we first pre-process noise reduction and thinning steps. And also, we use geometric pattern vector to extract features which independent on the size, translation, and rotation of input values. In the experimental results, the proposed method shows better computation times than conventional circular pattern vector and better extraction results regardless of irregular environment lighting conditions as well as noise, size, and location of plate.

• The KIPS Transactions:PartB
• /
• v.11B no.1
• /
• pp.21-26
• /
• 2004

Color image quantization is a process of selecting a set of colors to display an image with some representative colors without noticeable perceived difference. It is very important in many applications to display a true color image in a low cost color monitor or printer. The basic problem is how to display 256 colors or less colors, called color palette, In this paper, we propose improved binary tree vector quantization based on spatial sensitivity which is one of the human visual properties. We combine the weights based on the responsibility of human visual system according to changes of three Primary colors in blocks of images with the process of splitting nodes using eigenvector in binary tree vector quantization. The test results show that the proposed method generates the quantized images with fine color and performs better than the conventional method in terms of clustering the similar regions. Also the proposed method can get the better result in subjective quality test and WSNR.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.359-362
• /
• 2000

본 논문에서는 비디오 영상에서 지역적 움직임 특성을 표현할 수 있는 지역적 움직임 활동(motion activity)에 관한 기술자(descriptor)를 제안한다. 제안된 방법은 화면 전체에 대해 지역적으로 높은 움직임 활동 정도를 갖는 영역에 대한 공간적 정보를 기술하고, 카메라 움직임에 무관하게 물체의 움직임 활동 특성을 정확히 표현하기 위해 움직임 벡터의 통계적 특성과 화면 분할을 이용한다 본 논문에서 제안하는 움직임 활동의 공간적 특성을 이용하면 동영상에서 화면의 일부에서 일어나는 움직임을 이용한 검색이 가능하고, 물체 추적, 감시 시스템에서도 활용이 가능하다. 실험으로 제안한 방법을 이용해서 움직임 활동이 높은 영역의 추출과정을 보이고, 이를 이용한 검색 결과를 보인다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.10C
• /
• pp.1036-1043
• /
• 2005

In this paper, we propose a sequential motion vector recovery algorithm for H.264 video coding standard. Motion vectors of H.264 video coding standard cover relatively smaller areas than other standard, since motion estimation of H.264 takes place in the fashion of variable block size. Therefore, the correlation of motion vectors between neighboring blocks increases as the block size of motion estimation is lowered. Under the framework of sequential recovery, we introduce a motion vector recovery using $\alpha$-trimed mean filter. Experimental results show that proposed algorithm is useful in real time video delivery .with nearly comparable or better visual quality than previous approaches such as macro block boundary matching and Lagrage interpolation.