• 대한전자공학회논문지SP
• /
• 제43권1호
• /
• pp.85-90
• /
• 2006

본 논문에서는 빠르고 안정적이면서도 높은 검색 성공률을 보장하는 내용기반 음악 정보 검색 시스템을 구축하였다. 시스템 질의 구간이나 질의 길이에 따른 시스템 불안정성 문제를 해결할 수 있는 DB 구축 방법인 MFC기법과 각 Superclass별로 특징 벡터의 차수를 차등 적용하여 시스템의 검색 속도를 향상시킬 수 있는 기법을 적용하였다. Superclass를 적용한 시스템은 SuperClass를 적용하지 않은 시스템과의 검색 성공률, 검색 속도 그리고 검색 Precision 비교 실험에서 대등한 성능을 유지하면서 검색 속도를 $20\%\~40\%$ 향상시켰다.

• 한국콘텐츠학회논문지
• /
• 제5권1호
• /
• pp.217-227
• /
• 2005

본 논문은 성능이 우수한 DirectX 기반 다채널 영상 감시 시스템을 설계 구현하고, 성능 분석한 결과를 제시한다. 본 논문의 시스템은 크게 디스플레이 서브시스템, 저장 서브시스템, 검색 및 재생 서브시스템으로 구성된다. 디스플레이 서브시스템은 빠른 디스플레이, 채널 간 디스플레이 동기 및 tearing effect 개선을 위해, DirectDraw의 H/W 가속 기능과 overlay, flip 기능을 효율적으로 이용하여 설계되었다. 저장 서브시스템은 저장 속도 개선을 위해, DirectShow 필터 기반 다중 쓰레드 구조로 설계되어 캡쳐 장치에서 획득되는 다채널의 영상 스트림이 채널별로 압축 저장되고 채널 간 데이터 병목 현상이 최소화되도록 하였다. 검색 및 재생 서브시스템에는 효율적인 인덱스 파일 구조와 영상 데이터 저장 구조, 재생 시에 채널별 동시 재생이 가능하도록 한 효율적인 재생 구조를 설계 구현하여 보다 빠른 재생 및 검색이 가능하도록 하였다. 실험결과, 제안된 시스템이 기존 시스템보다 저장 속도는 최고 2배 까지, 검색 및 재생 속도는 최고 3.5배 정도까지 개선되었음이 확인되었다.

• 반도체디스플레이기술학회지
• /
• 제14권2호
• /
• pp.53-59
• /
• 2015

Since the amount of digital image continues to grow in usage, users feel increased difficulty in finding specific images from the image collection. This paper proposes a novel image searching scheme that extracts the image feature using combination of Advanced SURF (Speed-Up Robust Feature) and DCD (Dominant Color Descriptor). The key point of this research is to provide a new feature extraction algorithm to improve the existing SURF method with removal of unnecessary feature in image retrieval, which can be adaptable to mobile system and efficiently run on the mobile environments. To evaluate the proposed scheme, we assessed the performance of simulation in term of average precision and F-score on two databases, commonly used in the field of image retrieval. The experimental results revealed that the proposed algorithm exhibited a significant improvement of over 14.4% in retrieval effectiveness, compared to OpenSURF. The main contribution of this paper is that the proposed approach achieves high accuracy and stability by using ASURF and DCD in searching for natural image on mobile platform.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제2권6호
• /
• pp.280-298
• /
• 2008

For efficient content-based image retrieval, diverse visual features such as color, texture, and shape have been widely used. In the case of leaf images, further improvement can be achieved based on the following observations. Most plants have unique shape of leaves that consist of one or more blades. Hence, blade-based matching can be more efficient than whole shape-based matching since the number and shape of blades are very effective to filtering out dissimilar leaves. Guaranteeing rotational invariance is critical for matching accuracy. In this paper, we propose a new shape representation, indexing and matching scheme for leaf image retrieval. For leaf shape representation, we generated a distance curve that is a sequence of distances between the leaf’s center and all the contour points. For matching, we developed a blade-based matching algorithm called rotation invariant - partial dynamic time warping (RI-PDTW). To speed up the matching, we suggest two additional techniques: i) priority queue-based pruning of unnecessary blade sequences for rotational invariance, and ii) lower bound-based pruning of unnecessary partial dynamic time warping (PDTW) calculations. We implemented a prototype system on the GEMINI framework [1][2]. Using experimental results, we showed that our scheme achieves excellent performance compared to competitive schemes.

• 대한음성학회지:말소리
• /
• 제67호
• /
• pp.149-166
• /
• 2008

In spoken document retrievals (SDR), subword (typically phonemes) indexing term is used to avoid the out-of-vocabulary (OOV) problem. It makes the indexing and retrieval process independent from any vocabulary. It also requires a small corpus to train the acoustic model. However, subword indexing term approach has a major drawback. It shows higher word error rates than the large vocabulary continuous speech recognition (LVCSR) system. In this paper, we propose an probabilistic slot detection and n-gram based string matching method for phone based spoken document retrievals to overcome high error rates of phone recognizer. Experimental results have shown 9.25% relative improvement in the mean average precision (mAP) with 1.7 times speed up in comparison with the baseline system.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.1851-1854
• /
• 2003

This paper suggests an algorithm which can retrieval images using correlations between the region classification of spatial image and the wavelet transform even though the images are rotated in a ${\pm}$90 degree arc. Owing to this proposed method, it was confirmed from experiments that the search about the whole image is not processed and only a few amount of informations are saved by using the mathematical statistics from the block map and transformed band which is resulted from region classification, and by performing the image search based on these, the improvement of search speed and the efficient search can be done.

• 한국광학회지
• /
• 제15권3호
• /
• pp.278-284
• /
• 2004

지속시간이 펨토초 수준에 이르는 빛펄스의 전기장 및 위상의 시간적 변화를 잴 수 있는 "이차조화파 발생 프로그(SHG FROG: Second Harmonic Generation Frequency Resolved Optical Gating)" 장치 및 소프트웨어를 개발하고 성능을 확인하였다. 이 장치를 써서 잰 실험값으로부터 빛펄스를 복원하는데는 "주요성분 일반 투영(PCGP: Principal Component Generalized Projection)" 방식에 더하여 프로그 궤적의 주파수 및 시간지연 "한계값(marginal)"과 이차조화파의 분광분포에 대한 조건을 덧붙임으로써 복원과정의 안정성과 수렴속도를 개선하였다.

• Bulletin of the Korean Chemical Society
• /
• 제30권9호
• /
• pp.2061-2065
• /
• 2009

Two simple algorithm modifications are made to the THRASH data retrieval program with the aim of improving analysis speed for complex Fourier transform ion cyclotron resonance (FTICR) mass spectra. Instead of calculating the least-squares fit for every charge state in the backup charge state determination algorithm, only some charge states are pre-selected based on the plausibility values obtained from the FT/Patterson analysis. Second, a modification is made to skip figure-of-merit (FOM) calculations in the central m/z region between two neighboring peaks in isotopic cluster distributions, in which signal intensities are negligible. These combined modifications result in a significant improvement in the analysis speed, which reduces analysis time as much as 50% for ubiquitin (8.6 kDa, 76 amino acids) FTICR MS and MS/MS spectra at the reliability (RL) value = 0.90 and five pre-selected charge states with minimal decreases in data analysis quality (Table 3).

• Journal of Computing Science and Engineering
• /
• 제9권1호
• /
• pp.29-38
• /
• 2015

Human action recognition has become an important research topic in computer vision area recently due to many applications in the real world, such as video surveillance, video retrieval, video analysis, and human-computer interaction. The goal of this paper is to evaluate descriptors which have recently been used in action recognition, namely Histogram of Oriented Gradient (HOG) and Histogram of Optical Flow (HOF). This paper also proposes new descriptors to represent the change of points within each part of a human body, caused by actions named as Histogram of Changing Points (HCP) and so-called Average Speed (AS) which measures the average speed of actions. The descriptors are combined to build a strong descriptor to represent human actions by modeling the information about appearance, local motion, and changes on each part of the body, as well as motion speed. The effectiveness of these new descriptors is evaluated in the experiments on KTH and Hollywood datasets.