• 반도체디스플레이기술학회지
• /
• 제12권3호
• /
• pp.59-64
• /
• 2013

Accurate and robust image registration is important task in many applications such as image retrieval and computer vision. To perform the image registration, essential required steps are needed in the process: feature detection, extraction, matching, and reconstruction of image. In the process of these function, feature extraction not only plays a key role, but also have a big effect on its performance. There are two representative algorithms for extracting image features, which are scale invariant feature transform (SIFT) and speeded up robust feature (SURF). In this paper, we present and evaluate two methods, focusing on comparative analysis of the performance. Experiments for accurate and robust feature detection are shown on various environments such like scale changes, rotation and affine transformation. Experimental trials revealed that SURF algorithm exhibited a significant result in both extracting feature points and matching time, compared to SIFT method.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2006년도 한국컴퓨터종합학술대회 논문집 Vol.33 No.1 (B)
• /
• pp.193-195
• /
• 2006

As multimedia information increases sharply, In image retrieval field the method that can analyze image data quickly and exactly is required. In the case of image data, because each data includes a lot of informations, between accuracy and speed of retrieval become trade-off. To solve these problem, feature vector extracting process that use Genetic Algorithm for implementing prompt and correct image clustering system in case of retrieval of mass image data is proposed. After extracting color and texture features, the representative feature vector among these features is extracted by using Genetic Algorithm.

• Journal of Information Processing Systems
• /
• 제14권6호
• /
• pp.1318-1330
• /
• 2018

Video captioning refers to the process of extracting features from a video and generating video captions using the extracted features. This paper introduces a deep neural network model and its learning method for effective video captioning. In this study, visual features as well as semantic features, which effectively express the video, are also used. The visual features of the video are extracted using convolutional neural networks, such as C3D and ResNet, while the semantic features are extracted using a semantic feature extraction network proposed in this paper. Further, an attention-based caption generation network is proposed for effective generation of video captions using the extracted features. The performance and effectiveness of the proposed model is verified through various experiments using two large-scale video benchmarks such as the Microsoft Video Description (MSVD) and the Microsoft Research Video-To-Text (MSR-VTT).

• 한국전자거래학회지
• /
• 제19권2호
• /
• pp.95-108
• /
• 2014

오피니언 마이닝은 문서로부터 의견을 추출하는 텍스트 마이닝의 응용분야로 현재 활발한 연구가 진행되고 있다. 대부분의 관련 연구는 특정 제품군에 대해서 주어진 특징별로 긍정과 부정 평가를 나누는 감성분류에 초점을 맞추고 있다. 하지만 제품별로 강조되는 특성들을 구별해내는 연구는 거의 이루어지고 있지 않다. 본 논문에서는 특성별로 오피니언 문서들을 분류하고, 이를 이용하여 특정 제품군에 대해서 제품별로 강조되는 특성들을 선별하는 기법을 제안한다. 제안된 기법에서는 텍스트 클러스터링을 활용하였으며, 새로운 유사도 계산 방식을 사용하였다. 또한 실험을 통하여 제안된 방법의 유용성을 증명하였다.

• 인터넷정보학회논문지
• /
• 제9권1호
• /
• pp.129-135
• /
• 2008

본 논문은 가중 퍼지소속함수 기반 신경망(Neural Network with Weighted Fuzzy Membership Functions, NEWFM)을 사용하여 생성된 퍼지규칙과 비중복면적 분산 측정법에 의해 추출된 최소의 특징입력을 이용하여, 1일 후의 KOSPI 예측을 하는 방안을 제안하고 있다. NEWFM은 KOSPI의 최근 32일 동안의 CPPn,m(Current Price Position of day n for n-1 to n-m days)을 이용하여 1일 후의 KOSPI 상승과 하락을 예측한다. 특징입력으로써 CPPn,m과 최근 32일간의 CPPn,m을 웨이블릿 변환한 38개의 계수들 중 비중복면적 분산 측정법을 적용하여 추출된 5개의 계수가 사용되었다. 제안된 방법으로 1991년부터 1998년까지의 실험군을 사용한 결과 평균 67.62%의 예측율을 나타내었다.

• 한국컴퓨터그래픽스학회논문지
• /
• 제9권2호
• /
• pp.11-18
• /
• 2003

본 논문은 2차원 영상에서 커서를 특징 경계로 이동시키는 스내핑(snapping)과 특징 경계를 추출하는 래핑(wrapping)을 3차원 메쉬로 확장하여 메쉬상의 기하적 특징을 사용자가 의도한 대로 추출할 수 있는 기법을 다룬다. 먼저 메쉬상의 나타나는 기하적 특징을 계량화하기 위해 근사 곡률과 움직임 비용함수를 정의한다. 이들 수치 값을 기반으로 기하적 스내핑과 기하적 래핑 알고리즘을 설계한다. 본 논문에서는 제안한 알고리즘을 얼굴 메쉬와 치아 메쉬상에 나타나는 기하적 특징을 추출하기 위해 적용하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.517-519
• /
• 2004

This paper describes an approach to estimate a robot pose with an image. The algorithm of pose estimation with an image can be broken down into three stages : extracting scale-invariant features, matching these features and calculating affine invariant. In the first step, the robot mounted mono camera captures environment image. Then feature extraction is executed in a captured image. These extracted features are recorded in a database. In the matching stage, a Random Sample Consensus(RANSAC) method is employed to match these features. After matching these features, the robot pose is estimated with positions of features by calculating affine invariant. This algorithm is implemented and demonstrated by Matlab program.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.265-271
• /
• 2001

It is highly for the research in artificial intelligence area to be able to manage knowledge as human beings do. One of the fantastic natures that human knowledge management systems have is being active. Human beings actively manage their knowledge, solve conflicts and make inference. It makes a major difference from artificial intelligent systems. This paper focuses on the discussion of the features of that human knowledge systems, which underlies the active nature. With the features extracted, further research can be done to construct a suitable infrastructure to facilitate these features to build a man-made active knowledge management system. This paper proposed 10 features that human beings follow to maintain their knowledge. We believe it will advance the evolution of active knowledge management systems by realizing these features with suitable knowledge representation/decision models and software agent technology.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 추계종합학술대회 논문집
• /
• pp.911-914
• /
• 1998

In this paper, the importance of including small image features at the initial levels of a progressive second generation video coding scheme is presented. It is shown that a number of meaningful small features called details shouuld be coded in order to match their perceptual significance to the human visual system. We propose a method for extracting, perceptually selecting and coding of visual details in a video sequence using morphological laplacian operator and modified post-it transform is very efficient for improving quality of the reconstructed images.

• 산업기술연구
• /
• 제20권B호
• /
• pp.207-211
• /
• 2000

For efficient massive image retrieval, an image retrieval requires that several important objectives are satisfied, namely: automated extraction of features, efficient indexing and effective retrieval. In this work, we present a technique for extracting the 4-dimension directional feature. By directional detail, we imply strong directional activity in the horizontal, vertical and diagonal direction present in region of the image texture. This directional information also present smoothness of region. The 4-dimension feature is only indexed in the 4-D space so that complex high-dimensional indexing can be avoided.