• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.286-288
• /
• 2006

영상 이해는 컴퓨터 비전의 가장 높은 수준의 처리 기법이다. 영상을 이해하기 위해서는 위치 정보, 물체 존재정보와 같은 기본 컨텍스트들을 추출하는 것이 중요하다. 그러나 실내 환경의 영상 정보는 카메라의 흔들림이나 각도, 빛의 상태에 따라 불확실해지기 때문에 이러한 불확실함에 강인한 영상 인식 기법이 필요하다. 동적 베이지안 네트워크(DBN)는 이러한 불확실한 정보의 처리에 강인하며 장소와 물체의 관계등 고수준의 컨텍스트를 모델링하는데 좋은 성능을 보이는 확률 모델이다. 또한 DBN은 이전 상태를 추론에 활용할 수 있으므로 장소 인식과 같은 컨텍스트의 추출에 좋다. 본 연구에서는 불확실한 실내 환경 영상으로부터 영상 전처리를 통해 특징값을 추출하고, 회전이나 크기 변화에 강인한 물체인식기법인 크기불변 특징 변환기법(SIFT)을 이용하여 물체 존재정보를 추출하여 고수준 컨텍스트가 모델링된 DBN 추론으로 장소 및 물체를 인식하는 방법을 제안한다. 실제 대학 실내 환경에서의 실험으로 DBN을 이용한 영상 인식기법이 좋은 성능을 보임을 확인할 수 있었다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1999.06b
• /
• pp.97-102
• /
• 1999

멀티미디어 데이터의 증가로 사용자가 원하는 데이터의 신속하고 정확한 검색이 필요하게 되었다. 본 논문에서는 모양 정보를 기반으로 영상 데이터를 효과적이며 효율적으로 검색하기 위하여, 새로운 모양 정보 특징 및 검색 방법을 제안한다. 본 논문에서는 화소의 공간적분포로 나타나는 모양 정보를 covariance matrix의 eigenvector를 이용하여, 계층적으로 영역을 분할하고, 각 분할된 영역에서 크기 변화, 위치 이동, 회전에 불변하는 특징들을 추출한다. 영상 정보의 검색은 특징벡터 공간에서 질의 영상에서 추출된 특징과, 데이터베이스에 기록된 영상들의 특징 사이의 거리를 계산하여, 거리에 반비례하는 유사도가 높은 영상들을 출력한다. 제안된 모양 특징은 또한 계층수의 조정에 의해서 모양 정보를 표현할 수 있는 정도를 조절 할 수 있다는 장점이 있다.

• Journal of KIISE:Software and Applications
• /
• v.28 no.8
• /
• pp.570-581
• /
• 2001

본 논문에서는 윤곽선(edge) 기반의 형태 정보와 웨이브렛 변환(wavelet transform)에 의한 방향(direction) 정보를 사요하는데 2단계 상표 영상 검색 시스템을 제안한다. 1 단계에서는 후보 상표 영상을 추출하기 위해 영상의 전반적인 정보로 원 상표 영상(original trademark image)을 웨이브렛 변환하여 얻은 X, Y 방향 고주파(high frequency) 성분으로부터 구한 방향 정보와 영상의 윤곽선에 대해 모멘트를 구하는 향상된 불변 모멘트(improved invariant moment)를 이용한다. 2단계에서는 후부 영상들에 대해 영상의 세부 정보인 윤곽선 각도(edge angle)와 윤곽선 반지름(edge radius) 정보를 추출하여 유사도 측정 알고리즘을 통해 결과 영상을 산출하게 된다. 본 상표 영상 검색 시스템은 문자 색인으로는 색인이 용이 하지 않은 기하학적도형 상표 영상만을 사용하였다. 본 시스템에서는 색상과는 상관없는 특징인 형태 정보와 방향 정보만을 이용하므로 같은 색상 구성을 가진 유사 영상뿐만 아니라, 유사하지만 바탕이 반전된 영상이나 색상이 다른 유사 영상에 대해서도 바르게 검색할 수 있으며, 각 특징을 일반화해줌으로 이동.회전.크기 변화에도 불변하는 견고성을 가진다. 또한 효율적인 검색을 위해 2단계의 구조를 사용하였으며, 각 단계마다 계산량을 줄여 검색 시간을 감소시키도록 설계되었다.

• Journal of Digital Contents Society
• /
• v.12 no.3
• /
• pp.279-289
• /
• 2011

The latest hardware and software techniques are combined to give safe walking guidance and convenient service of realtime walking assistance system for visually impaired person. This system consists of obstacle detection and perception, place recognition, and sign recognition for pedestrian can safely walking to arrive at their destination. In this paper, we exploit the sign object detection system in subway station for sign recognition that one of the important factors of walking assistance system. This paper suggest the adaptive feature map that can be robustly extract the sign object region from complexed environment with light and noise. And recognize a sign using fast zernike moment features which is invariant under translation, rotation and scale of object during walking. We considered three types of signs as arrow, restroom, and exit number and perform the training and recognizing steps through adaboost classifier. The experimental results prove that our method can be suitable and stable for real-time system through yields on the average 87.16% stable detection rate and 20 frame/sec of operation time for three types of signs in 5000 images of sign database.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.6
• /
• pp.149-156
• /
• 2003

This paper proposes a face recognition method based on modified Otsu binarization, Hu moment and linear discriminant analysis (LDA). Proposed method is robust to brightness, contrast, scale, rotation, and translation changes. Modified Otsu binarization can make binary images that have the invariant characteristic in brightness and contrast changes. From edge and multi-level binary images obtained by the threshold method, we compute the 17 dimensional Hu moment and then extract feature vector using LDA algorithm. Especially, our face recognition system is robust to scale, rotation, and translation changes because of using Hu moment. Experimental results showed that our method had almost a superior performance compared with the conventional well-known principal component analysis (PCA) and the method combined PCA and LDA in the perspective of brightness, contrast, scale, rotation, and translation changes with Olivetti Research Laboratory (ORL) database and the AR database.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.1
• /
• pp.15-22
• /
• 2005

In this paper, we propose a face recognition system by using the CCD color image. We first get the face candidate image by using YCbCr color model and adaptive skin color information. And we use it initial curve of active contour model to extract face region. We use the Eye map and mouth map using color information for extracting facial feature from the face image. To obtain center point of Log-polar image, we use extracted facial feature from the face image. In order to obtain feature vectors, we use extracted coefficients from DCT and wavelet transform. To show the validity of the proposed method, we performed a face recognition using neural network with BP learning algorithm. Experimental results show that the proposed method is robuster with higher recogntion rate than the conventional method for the rotation and scale variant.

• Journal of Korea Multimedia Society
• /
• v.3 no.5
• /
• pp.454-460
• /
• 2000

To retrieve complex data such as images, the content-based retrieval method rather than keyword based method is required. In this paper, we implemented a content-based image retrieval system which retrieves object of user query effectively using invariant moments which have invariant properties about linear transformation like position transition, rotation and scaling. To extract the shape feature of objects in an image, we propose a labeling algorithm that extracts objects from an image and apply invariant moments to each object. Hashing method is also applied to reduce a retrieval time and index images effectively. The experimental results demonstrate the high retrieval efficiency i.e precision 85%, recall 23%. Consequently, our retrieval system shows better performance than the conventional system that cannot express the shale of objects exactly.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.6
• /
• pp.170-178
• /
• 2008

A high performance object recognition algorithm using Fourier description of the 3D information of the objects is proposed. Object boundaries contain sufficient information for recognition in most of objects. However, it is not well utilized as the key solution of the object recognition since obtaining the accurate boundary information is not easy. Also, object boundaries vary highly depending on the size or orientation of object. The proposed object recognition algorithm is based on 1) the accurate object boundaries extracted from the 3D shape which is obtained by the laser scan device, and 2) reduction of the required database using the size and rotational invariant feature of the Fourier Descriptor. Such Fourier information is compared with the database and the recognition is done by selecting the best matching object. The experiments have been done on the rich database of MPEG 7 Part B.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.501-508
• /
• 2002

In this paper, we propose a content-based image retrieval using the color ratio and moment of object region. We acquire an optimal spatial information by the region splitting that utilizes horizontal-vertical projection and dominant color. It is based on hypothesis that an object locates in the center of image. We use color ratio and moment as feature informations. Those are extracted from the splitted regions and have the invariant property for various transformation, and besides, similarity measure utilizes a modified histogram intersection to acquire correlation information between bins in a color histogram. In experimental results, the proposed method shows more flexible and efficient performance than existing methods based on region splitting.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.6
• /
• pp.88-100
• /
• 1998

In this paper, an algorithm for a real-time automatic fingerprint identification system is proposed. The fingerprint feature volume is extracted by considering distinct and local characteristics(such as intensity and image quality difference etc.) in fingerprint images, which makes the algorithm properly adaptive to various image acquisitionj methods. Also the matching technique is designed to be invariant on rotation, scaling and translation (RST) changes while being capable of real-time processing. And the classification of fingerprints is performed based on the ridge flow and the relations among singular points such as cores and deltas. The developed fingerprint identification algorithm has been applied to various sets of fingerprint images such as one from NIST(National Institute of Standards and Technology, USA), a pressed fingerprint database constructed according to Korean population distributions in sex, ages and jobs, and a set of rolled-than-scanned fingerprint images. The overall performance of the algorithm has been analyzed and evaluated to the false rejection ratio of 0.07% while holding the false acceptance ratio of 0%.