• 응용통계연구
• /
• 제25권4호
• /
• pp.669-680
• /
• 2012

Noise removal of document images is a necessary step during preprocessing to recognize characters effectively because it has influences greatly on processing speed and performance for character recognition. We have considered using the spatial filters such as traditional mean filters and Gaussian filters, and wavelet transformed based methods for noise deduction in natural images. However, these methods are not effective for the noise removal of document images. In this paper, we present noise removal of document images using support vector regression. The proposed approach consists of two steps which are SVR training step and SVR test step. We construct an optimal prediction model using grid search with cross-validation in SVR training step, and then apply it to noisy images to remove noises in test step. We evaluate our SVR based method both quantitatively and qualitatively for noise removal in Korean, English and Chinese character documents, and compare it to some existing methods. Experimental results indicate that the proposed method is more effective and can get satisfactory removal results.

• 토지주택연구
• /
• 제1권1호
• /
• pp.1-7
• /
• 2010

Case-based reasoning (CBR) method can make estimators understand the estimation process more clearly. Thus, CBR is widely used as a methodology for cost estimation. In CBR, the quality of case retrieval affects the relevance of retrieved cases and hence the overall quality of the reminding capability of CBR system. Thus, it is essential to retrieve relevant past cases for establishing a robust CBR system. Case retrieval needs the following tasks to obtain appropriate case(s); indexing, search, and matching (Aamodt and Plaza 1994). However, the previous CBR researches mostly deal with matching process that has limits such as accuracy and efficiency of case retrieval. In order to address this issue, this research presents a CBR cost model for building projects that has two-step retrieval process: decision tree and nearest neighbor methods. Specifically, the proposed cost model has indexing, search and matching modules. Features in the model are divided into shape-based and scale-based attributes. Based on these, decision tree is established for facilitating the search task and nearest neighbor method was utilized for matching task. In regard to applying nearest neighbor method, attribute weights are assigned using GA optimization and similarity is calculated using the principle of distance measuring. Thereafter, the proposed CBR cost model is developed using 174 cases and validated using 12 test cases.

• 한국정보통신학회논문지
• /
• 제11권1호
• /
• pp.139-149
• /
• 2007

비동기 OFCDM 시스템은 동기 시스템과 달리 반드시 셀 탐색과정을 가져야 한다 이 과정을 초기 동기라고 하며 초기 동기를 위한 셀 탐색 방법이 다음과 같이 3단계 방법으로 수행된다. 셀 탐색 1 단계에서 보호구간의 상관을 이용한 OFCDM 심볼 동기 즉, FFT 윈도우 타이밍 추정과 탐색 2 단계에서는 주파수영역에서 CSSC(Cell Specific Scrambling Code) 위상 천이성질을 이용한 CPICH(Common Pilot Channel)의 상관을 획득함으로써 프레임 타이밍 및 CSSC 그룹을 검출하고 마지막으로 탐색 3 단계에서 그룹 안에 속한 CSSC 위상 즉, 최적의 CSSC를 얻게 된다. 본 논문에서는 기존의 CPICH를 기반으로 하는 3단계 셀 탐색과정 중 2단계에서 그룹을 나타내는 그룹코드를 블록형태로 변형하여 이동국의 복잡도를 줄인다. 그러나 복잡도를 줄이면 성능에 영향을 주지만 블록형태로 구성했을 때 최소의 성능열화를 가지는 조합을 찾는다. 제안된 적절한 조합을 가지는 블록형태의 그룹코드는 모의실험 통하여 기존의 그룹코드와 거의 동일한 성능을 유지하면서 복잡도를 줄일 수 있음을 비교 검증하였다.

• 한국국방경영분석학회지
• /
• 제26권1호
• /
• pp.47-55
• /
• 2000

The purpose of this paper is to develop a new heuristic algorithm for vehicle routing problem. The algorithm is composed of two steps. First step is to make a initial solution using sweeping algorithm. Second step is to improve initial solution for optimal solution using node exchange algorithm and tabu search algorithm. We have proven that our algorithm has produced better results than solutions obtained by saving algorithm and genetic in ten example problems with different unit size.

• 한국CDE학회논문집
• /
• 제11권4호
• /
• pp.315-325
• /
• 2006

It is very often necessary to search for similar parts during designing a new product because its parts are often easily designed by modifying existing similar parts. In this way, the design time and cost can be reduced. Thus it would be nice to have an efficient similarity comparison algorithm that can be used anytime in the design process. There have been many approaches to compare shape similarity between two solids. In this paper, two parts represented in B-Rep is compared in two steps: one for overall appearances and the other for detail features. In the first step, geometric information is used in low level of detail for easy and fast pre-classification by the overall appearance. In the second step, feature information is used to compare the detail shape in high level of detail to find more similar design. To realize the idea above, a multi resolution algorithm is proposed so that a given solid is described by an overall appearance in a low resolution and by detail features in high resolution. Using this multi-resolution representation, parts can be compared based on the overall appearance first so that the number of parts to be compared in high resolution is reduced, and then detail features are investigated to retrieve the most similar part. In this way, computational time can be reduced by the fast classification in the first step while reliability can be preserved by detail comparison in the second step.

• 한국문헌정보학회지
• /
• 제48권4호
• /
• pp.5-23
• /
• 2014

This study reports the first step in the Classification-based Search and Knowledge Discovery (CSKD) project, which aims to combine information organization and retrieval approaches for building digital library applications. In this study, we explored the generation and application of a faceted vocabulary as a potential mechanism to enhance knowledge discovery. The faceted vocabulary construction process revealed some heuristics that can be refined in follow-up studies to further automate the creation of faceted classification structure, while our concept search application demonstrated the utility and potential of integrating classification-based approach with retrieval-based approach. Integration of text- and classification-based methods as outlined in this paper combines the strengths of two vastly different approaches to information discovery by constructing and utilizing a flexible information organization scheme from an existing classification structure.

• 한국컴퓨터산업학회논문지
• /
• 제4권4호
• /
• pp.613-624
• /
• 2003

본 논문은 우선순위 큐와 접미어 트리로 색인 구조를 생성한 후. 이미지 시퀀스 데이터베이스에서 다차원 타임 워핑 거리 함수를 이용하여 유사한 이미지 서브시퀀스를 신속하고 정확하게 검색할 수 있는 방법을 제안한다. 본 논문에서 제안된 방법은 사전에 정의된 중요도에 따라 선별된 이미지 시퀀스로 구성된 우선순위 큐 색인의 이미지 서브시퀀스에 대한 유사성 거리 계산을 첫 단계로 시행하여 유사한 서브시퀀스집합을 얻고 만족할 결과를 얻지 못했을 경우에는 두 번째 단계로 나머지 유사 서브시퀀스에 대해 디스크 기반의 접미어 트리를 색인 구조체로 하여 유사한 서브시퀀스를 검색하는 것이다. 하한 거리 함수를 활용하여 질의 이미지 시퀀스와 유사한 이미지 서브시퀀스를 검색하는 과정에서 생성 가능한 오류를 방지 하면서 동시에 비 유사 이미지 서브시퀀스를 제거하도록 한다.

• Journal of applied mathematics & informatics
• /
• 제8권1호
• /
• pp.181-197
• /
• 2001

A heuristic method TABU-CSP using Tabu Search (TS) is described for solving Constraint Satisfaction Problems (CSPs). The method is started with a complete but inconsistent solution of a binary CSP and obtained in prespecified number of iterations either a consistent solution or a near optimal solution with an acceptable number of conflicts. The repair in the solution at each iterative step is done by using two heuristics alternatively. The first heuristic is a min-conflicts heuristic that chooses a variable with the maximum number of conflicts and reassigns it the value which leads to the minimum number of conflicts. If the acceptable solution is not reached after the search continued for a certain number of iterations, the min-conflict heuristic is changed and the variable selected least number of times is chosen for repair. If an acceptable solution is not reached, the method switches back to the min-conflict heuristic and proceeds further. This allowed the method to explore a different region of search space space for the solution as well as to prevent cycling. The demonstration of the method is shown on a toy problem [9]which has no solution. The method is then tested on various randomly generated CSPs with different starting solutions. The performance of the proposed method in terms of the average number of consistency is checked and the average number of conflicts is conflicts is compared with that of the Branch and Bound(BB) method used to obtain the same solution. In almost all cases, the proposed method moves faster to the acceptable solution than BB.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송공학회 2011년도 추계학술대회
• /
• pp.184-187
• /
• 2011

영상 압축은 멀티미디어 전송에 있어 핵심적인 기술이다. 동영상 압축 기술 중 움직임 예측은 H.264, MPEG-4 등의 압축 표준에서 시간적 중복성을 줄이기 위해 이용되고 있다. 따라서 영상의 압축 효율을 높이는 다양한 움직임 예측 알고리듬이 제안되었다. 이에 본 논문은 계산량을 줄이기 위해서 EPDS(Edge-Based Partial Distortion Search)를 기반으로 한 개선된 이단 탐색 움직임 예측 알고리듬을 제안한다. 이를 위하여 이단 탐색에서의 적응적 탐색 구간 적용 기술을 사용하였다. 제안한 알고리듬은 FS보다 98.11배 빠르다. 뿐만 아니라, PSNR을 통해 화질이 비슷하게 유지됨을 알 수 있다. 따라서 제안한 알고리듬은 고화질 디지털 영상 실시간 구현에 적합하다.

• 전자공학회논문지B
• /
• 제30B권6호
• /
• pp.35-48
• /
• 1993

In this paper, a hierarchical motion vector estimation algorithm using pyramidal structure is proposed. Using a smaller measurement window at each level of a pyramid than that of the conventional scheme, the proposed algorithm, based on the TSS(three step search), reduces the computational complexity greatly with its performance comparable to that of the TSS. By increasing the number of cnadidate motion vectors which are to be used as the initial search points for motion vector estimation at the next level, the performance improves further. Then the computational complexity of the proposed hierarchical algorithm depends on the number of candidate motion vectors, with its PSNR (peak signal to noise ratio) ranging between those of the TSS and the full search method. The simulation results with two different block sizes and various test sequences are given and its hardware implementation is also sketched.