• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.06a
• /
• pp.181-182
• /
• 2014

본 논문에서는 어파인(affine) 변환에 불변하는 지역 검출기에 대하여 다양한 기술자의 성능을 비교하였다. 지난 수 년간 다양한 특징 기술자들이 연구되어 왔고, 이러한 특징 기술자들은 각각의 목적에 따라 상이한 특성을 갖고 있기 때문에 동일한 조건에서 다양한 기술자들의 성능을 비교하는 연구가 필요하다. 그러나 어파인 변환에 불변하는 지역 검출기에 대해 최적의 특징 기술자를 찾는 연구는 미흡한 실정이다. 따라서 본 논문에서는 지역적인 패치 기반의 특징 기술자뿐만 아니라 바이너리 기술자와 최근에 제안된 기술자들의 성능을 비교하였다. 제안하는 실험에서는 MSER (maximally stable extremal regions) 검출기를 이용하여 어파인 변환에 불변하는 지역을 검출하였고, 영상 확대 및 축소, 회전, 시점 변환 및 변형 가능한 물체에 대하여 각각 기술자의 성능을 비교하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.7 no.6
• /
• pp.1214-1218
• /
• 2006

This paper presents method to speed up processing time in construction of panoramic images. The method based on invariant feature uses image down-scaling and image edge information. Reducing image size and applying feature descriptor to image portions superimposed with edge causes to reduce the number of features and to improve processing speed. In the experiments, it was shown that the proposed method was 3.26$\sim$13.87% shorter in processing time than the exiting method fer 24-bit color images of 640$\times$480 size.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.3
• /
• pp.21-26
• /
• 2003

A new method to realize 3-dimensional object pattern recognition system using Fourier-based feature extractor has been proposed. The procedure to obtain the invariant feature vector is as follows ; A closed surface is generated by tracing the surface of object using the 3-dimensional polar coordinate. The centroidal distances between object's geometrical center and each closed surface points are calculated. The distance vector is translation invariant. The distance vector is normalized, so the result is scale invariant. The Fourier spectrum of each normalized distance vector is calculated, and the spectrum is rotation invariant. The Fourier-based feature generating from above procedure completely eliminates the effect of variations in translation, scale, and rotation of 3-dimensional object with closed-surface. The experimental results show that the proposed method has a high accuracy.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1992.10a
• /
• pp.513-516
• /
• 1992

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.165-171
• /
• 2018

Shadow is a physical phenomenon observed in natural scenes and has a negative effect on various image processing systems such as intelligent video surveillance, traffic surveillance and aerial imagery analysis. Therefore, shadow detection should be considered as a preprocessing process in all areas of computer vision. In this paper, we define and analyze various feature elements for shadow detection in a single natural image that does not require a reference image. The shadow elements describe the intensity, chromaticity, illuminant-invariant, color invariance, and entropy image, which indicate the uncertainty of the information. The results show that the chromaticity and illuminant-invariant images are effective for shadow detection. In the future, we will define a fusion map of various shadow feature elements, and continue to study shadow detection that can adapt to various lighting levels, and shadow removal using chromaticity and illuminance invariant images.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.699-704
• /
• 2006

본 논문은 회전 및 천이불변 이미지 텍스처 검색의 새로운 방식을 소개한다. 주파수 영역의 극좌표계에서 동일한 공간 주파수에서 각도 방향으로 투영을 하는 각도 투영법을 제안하며, 제안된 각도 투영법을 이용하여 주파수 영역에서 푸리에 계수이 합과 표준편차를 특징벡터로 이용한다. 각도 투영법을 쉽게 구현하기 위해 극좌표계에서 라돈변환이 수행된다. 실험 시 MPEG-7 데이터를 이용하였으며 그 결과는 여러 텍스처 이미지를 검색하는데 있어서 특징을 잘 구별해 내는 결과를 보여준다. 또한 제안된 회전 및 천이불변 특징 추출 알고리듬은 등방성 텍스처나 국부적인 방향성을 보이는 텍스처 영상 검색에도 효율적인 검색률을 보인다.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.903-906
• /
• 2001

본 논문에서는 조명의 변화에 의해 컬러 영상의 컬러 성분이 달라지더라도 영상 내 컬러간의 편차값을 나타내는 공분산 행렬(covariance matrix)의 고유벡터(eigenvector)와 영상 내 화소들의 컬러 성분과의 상관관계는 거의 변화하지 않는 특징을 이용한 조명 변화에 강인한 영상 검색 방법을 제안한다. 제안된 방법은 영상에서 컬러 성분들의 공분산 행렬과 공분산 행렬의 고유치(eigenvalue), 고유벡터를 계산한 후, 가장 큰 고유치에 관계된 고유벡터로 화소를 투영시키고, 투영된 벡터의 크기 성분으로 영상을 재구성한다. 재구성된 영상으로부터 7개의 불변 모멘트(moment)를 계산하고, 공분산의 가장 큰 고유치를 가중치로 부과하여 특징벡터를 추출한다. 7개의 불변 모멘트로부터 구한 특징벡터는 영상 내 물체의 이동, 영상의 회전, 크기 변화뿐만 아니라, 조명의 변화에 의해 컬러가 변화할 경우에도 유사한 영상을 잘 검색한다. 제안된 방법의 성능 확인을 위하여 5가지 조명에서 얻은 영상 데이터베이스를 이용하여 실험하였으며, 실험 결과 히스토그램 인터섹션에 비해 적은 특징량으로 검색이 가능하면서 조명 변화에도 대응할 수 있는 검색 결과를 얻을 수 있었다.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.191-201
• /
• 2005

In this paper, we propose a method to calculate camera motion parameter, which is based on efficient invariant features irrelevant to the camera veiwpoint. As feature information in previous research is variant to camera viewpoint. information content is increased, therefore, extraction of accurate features is difficult. LM(Levenberg-Marquardt) method for camera extrinsic parameter converges on the goat value exactly, but it has also drawback to take long time because of minimization process by small step size. Therefore, in this paper, we propose the extracting method of invariant features to camera viewpoint and two-stage calculation method of camera motion parameter which enhances accuracy and convergent degree by using camera motion parameter by 2D homography to the initial value of LM method. The proposed method are composed of features extraction stage, matching stage and calculation stage of motion parameter. In the experiments, we compare and analyse the proposed method with existing methods by using various indoor images to demonstrate the superiority of the proposed algorithm.

• Journal of the Korea Society for Simulation
• /
• v.19 no.4
• /
• pp.111-122
• /
• 2010

In this study, a length adjustment algorithm for cyclic signals in manufacturing process using Time Invariant Feature point Extraction and Matching(TIFEM) is proposed. In order to precisely compensate the length of cyclic signals which have irregular length in the middle of signal as well as in the full length more feature points are needed. The extracted feature must involve information about the pattern of signal and should have invariant properties on time and scale. The proposed TIFEM algorithm extracts features having the intrinsic properties of the signal characteristics at first. By using those extracted features, feature vector is constructed for each time point. Among those extracted features, the only effective features are filtered and are chosen such as basis for the length adjustment. And then the partial length adjustment is performed by matching feature points. To verify the performance of the proposed algorithm, the experiments were performed with the experimental data mimicking the three kinds of signals generated from the actual semiconductor process.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.11
• /
• pp.116-123
• /
• 1994

A novel opto-digital pattern recognition method which has shift, rotation, and scale invariant properties is proposed for recognizing two dimensional images having straight lines. The algorithm is composed of three stages. In the first stage the line features of the image are extracted. The second stage imposes the shift, rotation, and scale invariant properties on the extracted features through normalizing procedure. The required normalizing equations are analytically explained. In the last stage, the artificial feedforward neural network is trained with the extracted features. In order to evaluated the proposed algorithm, nine different edge enhnaced binary images composed of straight lines are tested. Thus the proposed algorithm can recognize the patterns event though they are shifted, rotated, and scaled.