http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Content-Based Image Retrieval Using Adaptive Color Histogram
Yoo Gi-Hyoung,Park Jung-Man,You Kang-Soo,Yoo Seung-Sun,Kwak Hoon-Sung The Korea Institute of Information and Commucation 2005 韓國通信學會論文誌 Vol.30 No.9C
From the 90's, the image information retrieval methods have been on progress. As good examples of the methods, Conventional histogram method and merged-color histogram method were introduced. Dey could get good result in image retrieval. However, Conventional histogram method has disadvantages if the histogram is shifted as a result of intensity change. Merged-color histogram, also, causes more process so, it needs more time to retrieve images. In this paper, we propose an improved new method using Adaptive Color Histogram(ACH) in image retrieval. The proposed method has been tested and verified through a number of simulations using hundreds of images in a database. The simulation results have quickly yielded the highly accurate candidate images in comparison to other retrieval methods. We show that ACH's can give superior results to color histograms for image retrieval.
인체동작분석시 Wavelet변환을 이용한 영상자료의 보간 및 분석
김기형,김민기,유경석,김희영 한국운동역학회 1997 한국운동역학회지 Vol.7 No.1
Inputting data of human motion analysis means signal processing of changes in linear time dependent spatial coordinates of anatomical landmarks. Commercial CCD camera appears to be sampling 30 fps imposing limitation for human motion analysis which needs at least 60 fps. For the interpolation 60 fps fast algorithm of inverse wavelet transformation (IWT) was utilized producing 60 fps out of normal 30 fps. The original data from free fall and cycling motion of lower extremity were used to test the applicabiility of wavelet interpolation to human motion analysis. The test results showed linear relationship between two data sets. In the test of free fall, data curves of two sets, theoretical 30 frame data and 60 frame data after inverse wavelet transformation, appeared to be almost identical. Regression analysis of free fall test showed R^2 = 0.99 meaning Y = IWT. In the test with cycling motion of lower extremity % cycle of maximum flexion and extension at the joints was compared between two data sets showing same result, as in free fall test.
내용 기반 영상 검색 시스템을 위한 효율적인 특징 벡터 추출에 관한 연구
유기형,곽훈성,Yoo Gi-Hyoung,Kwak Hoon-Sung 한국정보처리학회 2006 정보처리학회논문지B Vol.13 No.3
Recently, multimedia DBMS is appeared to be the core technology of the information society to store, manage and retrieve multimedia data efficiently. In this paper, we propose a new method for content based-retrieval system using wavelet transform, energy value to extract automatically feature vector from image data, and suggest an effective retrieval technique through this method. Wavelet transform is widely used in image compression and digital signal analysis, and its coefficient values reflect image feature very well. The correlation in wavelet domain between query image data and the stored data in database is used to calculate similarity. In order to assess the image retrieval performance, a set of hundreds images are run. The method using standard derivation and mean value used for feature vector extraction are compared with that of our method based on energy value. For the simulation results, our energy value method was more effective than the one using standard derivation and mean value. 최근 다양하고 방대한 멀티미디어 데이터를 효율적으로 저장, 관리 및 검색할 수 있는 멀티미디어 데이터베이스 시스템이 정보화 사회의 중요한 핵심 기술로 대두되고 있다. 내용 기반 이미지 검색을 위해 본 논문에서는 웨이브렛 변환과 에너지 값을 사용하여 이미지 데이터로부터 특징 벡터를 완전 자동으로 추출하는 방법과 이를 이용한 효율적인 검색 기법을 제안한다. 웨이브렛 변환은 이미지 압축이나 신호 분석 등에서 많이 사용되며, 특히 웨이브렛 계수 값은 영상의 특성을 잘 반영하고 웨이브렛 영역에서 계산되는 예제영상(Query image)과 데이터베이스에 저장된 영상간의 유사성을 추정하는데 더 효율적이다. 영상 검색에 있어, 특징 벡터로 사용되는 표준편차와 평균 값을 에너지 값과 비교 분석하였다. 실험결과, 표준편차나 평균 값을 이용하는 것보다 에너지 값을 사용하는 것이 더 효과적이었다.