• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2003.05a
• /
• pp.490-494
• /
• 2003

운송 컨테이너의 식별자를 추출하고 인식하는 것은 컨테이너 식별자들의 크기나 위치가 정형화되어 있지 않고 외부의 잡음으로 인하여 식별자의 형태가 훼손되어 있기 때문에 어렵다. 본 논문에서는 이러한 특성을 고려하여 컨테이너 영상에 대해 Canny 마스크를 이용하여 에지를 검출하고, Canny 마스크가 적용된 영상에서 수직·수평 히스토그램을 적용하여 컨테이너의 식별자 영역을 추출한다. 추출된 컨테이너의 식별자 영역을 삼각형 타입의 퍼지 이진화 방법을 적용하여 이진화하고 이진화된 컨테이너 식별자 영역을 윤곽선 추적 알고리즘으로 개별 식별자를 추출한다. 제안된 방법의 성능을 평가하기 위하여 실제 컨테이너 영상에 적용한 결과, 기존의 방법보다 컨테이너의 식별자 추출에서 우수한 성능이 있음을 확인하였다.

• Annual Conference of KIPS
• /
• 2015.04a
• /
• pp.1054-1056
• /
• 2015

폐 결절과 폐 종양은 전 세계 사망의 주요 원인인 폐암의 초기 증상일 수 있기 때문에 임상적으로 중요하다. 그래서 많은 학자들은 이를 검출하기 위해 컴퓨터를 통한 이미지 분석을 시도하였고, 그러기 위한 첫걸음으로 폐 윤곽선을 추출했다. 본 논문에서는 파티클 필터를 이용한 폐 윤곽선을 추출함으로써, 폐 외벽에 붙어있는 폐 결절 및 폐 종양도 분리할 수 있는 방법을 제안한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.90-92
• /
• 2018

본 논문에서는 입력 영상을 카메라의 자세 정보에 따라 적절히 와핑한 후 이들을 심(Seam)을 따라 이어붙인 360VR 에서 갑작스런 객체 출현에 의해 중첩 영역에서 발생하는 왜곡 문제를 해결할 방법을 제안한다. 임의의 객체가 나타났을 때, 객체의 윤곽선을 반영하여 심(Seam)을 재설정함으로써 객체가 우그러지거나, 잘려나가는 등의 왜곡 문제를 해결한다. 이를 위해 본 논문에서는 가우시안(Gaussian) 혼합 모델 기반 전경/배경분리에 의한 움직이는 객체 추출, 객체 윤곽선 검출, 윤곽선에 기반한 심(Seam) 조정, 새로운 심(Seam) 기반 스티칭으로 왜곡을 없애는 방법을 제안하였다. 그리고 이를 실제 촬영 영상에 적용하여 왜곡 개선 효과를 보였다.

• Journal of Korea Multimedia Society
• /
• v.11 no.1
• /
• pp.34-43
• /
• 2008

This paper presents a system for recognizing sunglasses and a mask of an ATM (Automatic Teller Machine) user. The proposed system extracts firstly facial contour, then from this extraction results it estimates the regions of eyes and mouth. Finally, it recognizes sunglasses and a mouth using Histogram Indexing based on those regions. We adopt a face shape model to be able to extract facial contour and to estimate the regions of eyes and mouth when those regions are occluded by sunglasses and a mask. To improve the fitting accuracy of the shame model, we adopt 2-step face detection method and conduct fitting several times by varying the initial position of the model instance. To achieve a good performance of the face detection method based on a background model, we enable the system to automatically update the background model. In experiment, we present some experiments on setting parameters of the system with images taken from in our laboratory, and demonstrate the results of recognizing sunglasses and a mask.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.9 no.4
• /
• pp.75-79
• /
• 2009

In this paper the method was proposed which uses ${\lambda}$-fuzzy measure to detect the edge of the features of the face region. In the conventional method the features was founded using valley, brightness and edge. This method had its drawbacks that it is so sensitive to the external noises and environments. This paper proposed ${\lambda}$-fuzzy measure to cope with this drawbacks. By considering each weight of the pixels the integral evaluation was considered using the center of area method. Thus the continuity of the edge was kept by way of the neighborhood information and the reduction of time complexity wad resulted in.

• Journal of KIISE:Software and Applications
• /
• v.37 no.11
• /
• pp.866-870
• /
• 2010

This paper presents an improved Snake algorithm that contains additional energy term related to adjacent edges. The suggested algorithm represents the distance between an adjacent edge and the current cell as energy, and extracts object contours more effectively by including the energy tenn to the whole energy function. The adjacent edge-based snake algorithm not only make it possible to detect object boundaries which are concave, but also can detect the boundaries of complex objects without weight adjustment. Experimental results show that the proposed method extracts object boundaries more accurately than other existing methods without loss of speed.

• Journal of Korea Multimedia Society
• /
• v.5 no.4
• /
• pp.399-404
• /
• 2002

To restore image degraded by motion blur and additive noise, it is very difficult. In conventional restoration method, regularization is usually applied to all over the image without considering the local characteristics of image. As a result, ringing artifacts appear in edge regions and the noise amplification is introduced in flat regions. To solve this problem we propose an adaptive restoration method using directional regularization operator considering edges and the regularization operator with no direction for flat regions. We verified that the proposed method showed better results in the resolution. As a result it showed visually better image and improved better ISNR further than the conventional methods.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.07a
• /
• pp.315-317
• /
• 2012

본 논문에서는 인체의 골격 위치와 깊이 정보를 사용하여 주위 환경에 강건한 특성을 지니는 움직이는 사람 영역 검출 방법을 제안한다. 먼저 영상 내에서 인체의 골격 위치를 검출한 다음 인체 골격의 중심이 될 수 있는 지점에 대해 인체의 평균적 깊이 범위 내에서 깊이 세분화를 수행한다. 그리고 깊이 세분화를 통하여 검출된 사람 영역의 후보군에 대해 윤곽선 기반의 움직임 검출기법을 사용하여 후보군 내에서 움직이는 사람에 해당하는 특징점을 검출한다. 마지막으로 잡음 제거 및 움직이는 사람에 해당하는 영역 검출을 위하여 개선된 깊이 세분화 과정을 수행한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.8 no.6
• /
• pp.1419-1427
• /
• 2007

In this paper, we propose an algorithm which implements a multi-sided side match finite-state vector quantization(MSMVQ). After extracting the edge information from an image and classifying the image into edge blocks or non-edge blocks, we construct an edge map. We subdivide edge blocks into sixteen classes using discrete cosine transform(DCT) AC coefficients. Based on edge map information, a state codebook is made from the master codebook, and side match calculation is done for two-sided or three-sided current block of image. For reducing transmitted bits, a decision is made whether or not to encode the non-edge blocks among the pre-coded blocks by using the master codebook. Also for reducing allocation bits of codeword indices to decoder, a variable length coder is used. Considering the comparison with side match finite-state vector quantization(SMVQ) and two-sided SMVQ(TSMVQ) algorithm about Zelda, Lenna, Bridge and Peppers image, the new algorithm shows better picture quality than SMVQ and TSMVQ respectively.

• Journal of Korea Multimedia Society
• /
• v.10 no.7
• /
• pp.923-933
• /
• 2007

In this paper, we present a method for performance enhancement of the marker detection system by using SVM(Support Vector Machine) and LDA(Linear Discriminant Analysis). It converts the input image to a binary image and extracts contours of objects in the binary image. After that, it approximates the contours to a list of line segments. It finds quadrangle by using geometrical features which are extracted from the approximated line segments. It normalizes the shape of extracted quadrangle into exact squares by using the warping technique and scale transformation. It extracts feature vectors from the square image by using principal component analysis. It then checks if the square image is a marker image or a non-marker image by using a SVM classifier. After that, it computes feature vectors by using LDA for the extracted marker images. And it calculates the distance between feature vector of input marker image and those of standard markers. Finally, it recognizes the marker by using minimum distance method. Experimental results show that the proposed method achieves enhancement of recognition rate with smaller feature vectors by using LDA and it can decrease false detection errors by using SVM.