• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.635-638
• /
• 2005

The purpose of video segmentation is to segment video sequence into shots where each shot represents a sequence of frames having the same contents, and then select key frames from each shot for indexing. There are two types of shot changes, abrupt and gradual. The major problem of shot change detection lies on the difficulty of specifying the correct threshold, which determines the performance of shot change detection. As to the clustering approach, the right number of clusters is hard to be found. Different clustering may lead to completely different results. In this thesis, we propose a video segmentation method using a color-X$^2$ intensity histogram-based fuzzy c-means clustering algorithm.

• Science of Emotion and Sensibility
• /
• v.7 no.4
• /
• pp.57-65
• /
• 2004

In this paper, we present a hybrid approach which incorporates color, texture and shape in content-based image retrieval. Colors in each image are clustered into a small number of representative colors. The feature descriptor consists of the representative colors and their percentages in the image. A similarity measure similar to the cumulative color histogram distance measure is defined for this descriptor. The co-occurrence matrix as a statistical method is used for texture analysis. An optimal set of five statistical functions are extracted from the co-occurrence matrix of each image, in order to render the feature vector for eachimage maximally informative. The edge information captured within edge histograms is extracted after a pre-processing phase that performs color transformation, quantization, and filtering. The features where thus extracted and stored within feature vectors and were later compared with an intersection-based method. The content-based retrieval system is tested to be effective in terms of retrieval and scalability through experimental results and precision-recall analysis.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.11-14
• /
• 2001

본 논문은 컬러를 이용한 영상 검색 방법에 관한 것으로 영상 데이터의 효율적인 관리를 위해 먼저 전처리 단계로 웨이블릿 변환을 수행한 후 가장 낮은 저주파 부밴드 영상을 획득한다. 그리고, 변환 후 획득된 영상을 클러스터로 구분한 후, 고유치 및 고유 벡터를 이용하여 특징을 추출하여 색인 정보로 이용하였다. 클러스터링은 영상 화소의 컬러공간 상의 3차원 거리를 클러스터링의 기준으로 삼아 순차 영역 분할(Sequential Clustering) 방법을 적용하였다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.11a
• /
• pp.126-131
• /
• 2001

현재 널리 사용되는 hand-held형 단말기들은 영상을 표현할 때 제한된 수의 칼라만으로 표현할 수 있다. 따라서 자연색 칼라 팔레트를 이용하여 단말기에 나타낼 때 최적의 칼라 팔레트를 구현하는 것과 원영상의 각각의 칼라로부터 팔레트 칼라로 최적으로 정합 시키는 것이 요구된다. 본 논문에서는 효율적으로 칼라 팔레트를 설계하는 히스토그램 기반 영상 의존적 스칼라 양자화 알고리즘을 제안한다. 제안 알고리즘은 칼라 우선순위 결정 부분과 양자화 부분으로 구성되며 양자화 후 ANC(Adaptive Neighborhood-Clustering) 알고리즘을 적용하여 성능을 개선한다. 이 방법은 자연색 칼라 영상을 적은 비트로 표현했음에도 출력 영상이 인간의 눈에 적합하다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.11a
• /
• pp.306-308
• /
• 2003

본 논문은 컬러영상내 움직이는 객체의 효과적인 검출을 위해 색상과 위치정보를 적용시킨 K-means 클러스터링 알고리즘을 이용하여 움직이는 객체들을 추출한 방법을 제안하고 있다. 최종 클러스터링된 중심픽셀(prototype)이 갖고있는 RGB 값을 사용해 프레임을 비교해 객체와 배경의 분리를 가능하게 했고 마지막으로 후처리를 이용해 남아있는 배경잡음을 제거하였다. 본 연구의 실험은 여러 교통장면을 포함한 다양한 영상에서 이루어졌으며 실험결과 제안된 알고리즘은 기존의 픽셀이나 블록기반의 방법에 비해 보다 정확한 객체 검출이 가능했으며 한 가지 특징 정보를 사용한 클러스터링에 비해 보다 높은 정확도를 보였다.

• Proceedings of the IEEK Conference
• /
• 2003.11a
• /
• pp.369-372
• /
• 2003

In this paper, we propose impr oved binary tree vector quantization based on spatial sensitivity which is one of the human visual properties. We combine the weights based on spatial masking effect 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 qualify test and PSNR.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.481-483
• /
• 2001

본 논문에서는 동영상으로부터 색상, 서체, 크기와 같은 사전 지식 없이도 글자/자막을 효율적으로 추출하는 방법을 제안한다. 해상도가 낮고 복잡한 배경을 포함할 수 있는 비디오에서 글자 인식률 향상을 위해 먼저 동일한 텍스트 영역의 존재하는 프레임들을 자동적으로 추출한 후 이들의 시간적 평균영상을 만들어 향상된 영상을 얻는다. 평균영상의 외각선 영상의 투영 값을 통해 문자영역을 찾고 각 텍스트 영역에 대해 1차 배경제거 과정인 region filling을 적용하여 글자의 배경들을 제거 함으로써 글자를 추출한다. 1차 배경제거의 결과를 검증하고 추가적으로 k-means를 이용한 color clustering을 적용하여 남아있는 배경들을 효율적으로 제거 함으로써 최종 글자영상을 추출한다.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2007.04a
• /
• pp.169-173
• /
• 2007

Nowadays the aerial photos is using to get the information around our spatial environment and it increases by geometric progression in many fields. The aerial photos need in a simple object such as cartography and ground covey classification and also in a social objects such as the city plan, environment, disaster, transportation etc. However, the shadow, which includes when taking the aerial photos, makes a trouble to interpret the ground information, and also users, who need the photos in their field tasks, have restriction. This study, for removing the shadow, uses the single image and the image without the source of image and taking situation. Also, this study present clustering algorism based on HIS color model that use Hue, Saturation and Intensity, especially this study used I(intensity) to extract shadow area from image. And finally by filtering in Fourier frequency domain creates the intrinsic image which recovers the 3-D color information and removes the shadow.

• Proceedings of the IEEK Conference
• /
• 2001.06c
• /
• pp.141-144
• /
• 2001

In this paper, a new algorithm for extracting and recognizing characters from video, without pre-knowledge such as font, color, size of character, is proposed. To improve the recognition rate for videos with complex background at low resolution, continuous frames with identical text region are automatically detected to compose an average frame. Using boundary pixels of a text region as seeds, we apply region filling to remove background from the character Then color clustering is applied to remove remaining backgrounds according to the verification of region filling process. Features such as white run and zero-one transition from the center, are extracted from unknown characters. These feature are compared with a pre-composed character feature set to recognize the characters.

• Journal of information and communication convergence engineering
• /
• v.6 no.4
• /
• pp.444-447
• /
• 2008

In this paper, we proposed the recognition system of car license plates to mitigate traffic problems. The processing sequence of the proposed algorithm is as follows. At first, a license plate segment is extracted from an acquired car image using morphological features and color information, and noises are eliminated from the extracted license plate segment using line scan algorithm and Grassfire algorithm, and then individual codes are extracted from the license plate segment using edge tracking algorithm. Finally the extracted individual codes are recognized by an FCM algorithm. In order to evaluate performance of segment extraction and code recognition of the proposed method, we used 100 car images for experiment. In the results, we could verify the proposed method is more effective and recognition performance is improved in comparison with conventional car license plate recognition methods.