• 정보처리학회논문지B
• /
• 제14B권3호
• /
• pp.215-222
• /
• 2007

최근 정보기술의 발달과 함께 문자 인식의 중요성이 높아지고 있다. 특히, 유비쿼터스 시대가 도래하면서 개인휴대용 정보 단말기, 태블릿 PC 등 유비쿼터스 컴퓨팅 장비가 급속도로 대중화 되고 있다. 이에 사람마다 다양한 필체로 인한 문제가 발생하고 있으며, 인식률을 높일 수 있는 문자 인식에 대한 연구가 필요한 실정이다. 본 연구에서는 다중 해상도 병합을 이용한 수정된 적응 공명 이론 신경망을 제안한다. 이는 자율 학습 신경망과 다중 해상도의 관점에서 접근하여 문자 인식 문제에 적용시켜 본 것이다. 노이즈와 문자 특성 정보를 구별하고 인식률을 높이기 위해 고해상도와 저해상도 정보를 같이 이용하는 다중 해상도 병합 방법을 제안한다. 또한, 다중 해상도 병합 방법의 효과를 극대화할 수 있는 적응 공명 이론 신경망의 유사도 측정 방법을 제안하여 기존의 방법보다 우수한 실험 결과를 제시하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1057-1060
• /
• 2004

We propose new rotation moment invariants based on multiresolution filter bank techniques. The multiresolution pyramid motivates our simple but efficient feature selection procedure based on the fuzzy C-mean clustering, combined with the Mahalanobis distance. The procedure verifies an impact of random noise as well as an interesting and less known impact of noise due to spatial transformations. The recognition accuracy of the proposed techniques has been tested with the preceding moment invariants as well as with some wavelet based schemes. The numerical experiments, with more than 30,000 images, demonstrate a tangible accuracy increase of about 3% for low noise, 8% for the average noise and 15% for high level noise.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 1999년도 학술대회
• /
• pp.21-25
• /
• 1999

Wavelet transform decomposes a video frame into a set of subframes with different resolutions corresponding to different frequency bands. The block size of highest layer subframe is too small to estimate correct motion. To decrease this aperture problem in the approximation frame, multiresolution motion estimation (MRME) using hierarchical block matching is presented in this paper. In the multiresolution motion estimation approach, motion vectors in the subframes are estimated by the motion vectors in the approximation frame and are refined at each subframe. It reduces computational time in motion estimation. It is shown that our MRME approach has a superior performance than traditional MRME approaches.

• 방송공학회논문지
• /
• 제1권2호
• /
• pp.96-107
• /
• 1996

영상 검색 시스템에서 공유망이나 저속 링크망 같은 통신망을 사용해 영상 DB를 조회하여 목표 영상을 결정하려는 경우 고화질 영상을 전송하게 되는 경우 전송 지연과 같은 문제점을 극복하기 힘들다. 본 논문에서는 다해상도의 영상 표현과 점진적 전송 방법을 통해 영상 검색 시스템의 성능 향상을 위한 브라우징 방법과 최적화 방법을 제안하였다. 제안된 통계적 모델 분석과 성능에 대하여 모의 실험을 통하여 성능 평가를 수행하였다. 여러 중간 해상도 계층을 사용하는 사용자-시스템간 대화형에 의한 검색 시스템은 단일 하위 계층을 사용하는 것보다 전송 지연 시간 측면의 큰 이득을 얻을 수 있음을 보였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2009년도 정보 및 제어 심포지움 논문집
• /
• pp.169-171
• /
• 2009

The histogram specification is to change the histogram shape of the image into the already defined shape. This technique can be applied usefully in various image processing fields which include a machine vision. However, the histogram specification technique has its basic limits. For example, the histogram does not have location information of pixel within the image and receives the digital image, which is stored through a quantization process, as an input. Namely, the accuracy of specification falls in the high-resolution image because the larger the resolution of image is becoming, the more the pixels having similar value are becoming. Therefore, we proposed the multiresolution histogram specification method for improving the accuracy of specification. Consequently, we can know that if the histogram specification is accomplished by using the proposed algorithm, destination image and source image were changed almost similarly.

• 대한기계학회논문집A
• /
• 제28권3호
• /
• pp.251-258
• /
• 2004

Since the multiscale wavelet-based numerical methods allow effective adaptive analysis, they have become new analysis tools. However, the main applications of these methods have been mainly on elliptic problems, they are rarely used for eigenvalue analysis. The objective of this paper is to develop a new multiscale wavelet-based adaptive Galerkin method for eigenvalue analysis. To this end, we employ the hat interpolation wavelets as the basis functions of the finite-dimensional trial function space and formulate a multiresolution analysis approach using the multiscale wavelet-Galerkin method. It is then shown that this multiresolution formulation makes iterative eigensolvers very efficient. The intrinsic difference-checking nature of wavelets is shown to play a critical role in the adaptive analysis. The effectiveness of the present approach will be examined in terms of the total numbers of required nodes and CPU times.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1997년도 추계학술대회
• /
• pp.184-187
• /
• 1997

Small PACS based on a personal computer or CR has initially been designed to improve the performance of cost-effective PACS implementation. In that system, Wavelet compression scheme is newly adopted to store images hierarchically to storage unit, and retrieve and display images progressively or display workstation. In this compression method, image is decomposed into subclasses of image by wavelet transform, and then the subclasses of image are vector quantized using a multiresolution codebook.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.1674-1677
• /
• 2002

In this paper, the new method to extract the features of iris signals is proposed; Multiresolution ICA (M-ICA) provides good properties to represent signals with time-frequency. The conventional methods were to use the technique of filter bank analysis, while ICA is unsupervised learning algorithm using high-order statistics. M-ICA could make use of strengths of learn- ing method and multiresolution. Also, we performed comparative studies of different feature extraction techniques applied to personal identification using iris pat- tern. To measure goodness of methods, we use Fisher’s discriminant ratio to quantify the class-separability of features generated by various techniques.

• 전자공학회논문지B
• /
• 제28B권12호
• /
• pp.51-58
• /
• 1991

In this paper, we propose a multiresolution edge detection method which selects the edge detection window size and scale automatically by using the local variance information as an edgeness measure of a region. The mode of the local variance distribution which is calculated over the (2p + 1) x (2p + 1) windows is used to determine the resolution of the given pixel and the edge operator with different scale can be applied to the pixel depending on its resolution. The combination of the resolution determination scheme with the conventional Canny and LOG edge detectors gives the proposed multiresolution edge detection schemes. The effectness of the proposed schemes is shown via computer simulation.

• 전자공학회논문지B
• /
• 제29B권10호
• /
• pp.78-89
• /
• 1992

In this paper, a multiresolution edge detction algorithm for speckle images is proposed. Due to the signal dependency of speckle images, the number of edge points detected depends on the local average intensity. Thus the edge detection method independent of the average intensity is required to detect properly real significant changes in an original signal. In the proposed method, candidate area is first selected based on the statistical propeties of speckle images,i.e., based on the busyness measure such as the CoV(coefficient of variation) and the difference between the real and theoretical CDF(cumulative density function). Then the real edges are extracted in a multiresolution environment. Computer simulation with test images shows that the proposed method reduces significantly false edges in relatively homogeneous areas while detects fine details properly.