• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.662-665
• /
• 1988

This paper proposes the Minimum-Distance Classification(MDC) processor using the Residue Number System(RNS). The proposed MDC Processor in this paper is efficient for real-time pattern clustering application and illustrate satisfiable error rate in application experiments of image segmentation but error rate increase as cluster number do.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.880-882
• /
• 2005

내용기반 영상 검색 시스템은 데이터베이스에 저장된 정지영상의 색이나, 질감, 형태 등의 특징을 이용한다. 본 연구는 실험 영상 집합에서 주요 객체를 추출하여, 객체들의 외형으로부터 분리된 토큰들을 군집화 한 후, 그 군집단위를 색인어로 사용하여 검색하는 방법이다. 기존의 내용기반 영상 검색 시스템에서 모양 정보는 그 표현과 색인 정합 등의 문제로 처리 방법이 명확하지 않았고, 회전, 크기 변화, 폐색 등에 민감했다. 따라서 기존 방법의 문제점을 해결하기 위해서 토큰을 이용한 색인을 이용하여 지역 정보와, 이들 지역 정보들의 관계에 의한 전역 정보를 복합적으로 이용한 방법을 제안한다.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1371-1373
• /
• 1996

A clustering algorithms with dynamic adjustment of learning rate for GBFCM(Gradient Based FCM) is proposed in this paper. This algorithm combines two idea of dynamic K-means algorithms and GBFCM : learning rate variation with entropy concept and continuous membership grade. To evaluate dynamic GBFCM, we made comparisons with Kohonen's Self-Organizing Map over several tutorial examples and image compression. The results show that DGBFCM(Dynamic GBFCM) gives superior performance over Kohonen's algorithm in terms of signal-to-noise.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.575-578
• /
• 2003

본 논문은 제한된 영역 안의 다수 물고기를 추적하는 방법을 제안한다. 고정된 카메라로 물고기가 있는 수조의 영상을 얻은 다음 실시간으로 얻는 매경영상을 통해 물고기의 이미지만을 얻는다. 이렇게 얻어진 이미지를 ART2 알고리즘을 통해 clustering을 하고 각각의 물고기라 추정되는 cluster와 이전까지 측정되어진 물고기 좌표와의 거리 계산을 통해 각각의 물고기의 개체 인식을 하게 된다. 본 논문에서는 기존의 물고기 이미지를 얻는 방법을 개선하여 다 개체 추적을 위한 깨끗한 개체 이미지를 얻는 방법과, 각 cluster들과 이진 물고기 위치와의 거리계산을 통한 개체 인식 방법에 대해 초점을 맞추었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10c
• /
• pp.352-354
• /
• 2002

최근 위성영상을 이용한 GIS 시스템이 많이 생겨나면서 위성영상을 이용한 연구가 많이 진행중이다. 하지만 위성영상의 경우 파일 자체의 사이즈가 크기 때문에 본 영상을 처리하기가 쉽지 않으며 시간 또한 많이 소모되게 된다. 또한 효율적인 자료처리를 하기 위해서는 고성능의 하드웨어가 필요하다는 문제점이 있다. 따라서 본 논문에서는 병렬처리를 이용하는 클러스터링 시스템을 사용하여 대용량의 위성영상을 보다 빠르고 효율적으로 처리할 수 있는 시스템을 설계하였다. 본 논문에서 제안한 시스템을 사용하면 앞의 문제점을 해결할 수 있으며 빠른 영상 분석이 가능하게 된다. 병렬 컴퓨터의 노드를 증가시키면서 제안한 시스템의 속도가 빨라지는 것을 실험을 통해 보였다.

• Korean Journal of Digital Imaging in Medicine
• /
• v.7 no.1
• /
• pp.33-38
• /
• 2005

Modern hospitals have been greatly facilitated with information technology (IT) such as hospital information system (HIS). One of the most prominent achievements is medical imaging and image data management so-called Picture Archiving and Communication Systems (PACS). Due to inevitable use of diagnostic images (such as X-ray, CT, MRI), PACS made tremendous impact not only on radiology department but also nearly all clinical departments for exchange and sharing image related clinical information. There is no doubt that better use of PACS leads to highly efficient clinical administration and hospital management. However, due to rapid and widespread acceptance of PACS storage and management of digitized image data in hospital introduces overhead and bottleneck when transferring images among clinical departments within and/or across hospitals. Despite numerous technical difficulties, financing for installing PACS is a major hindrance to overcome. In addition, a mirroring or a clustering backup can be used to maximize security and efficiency, which may not be considered as cost-effective approach because of extra hardware expenses. In this study therefore we have developed a new based on grid of distributed PACS in order to balance between the cost and network performance among multiple hospitals.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.08a
• /
• pp.142-145
• /
• 2008

This paper proposes a computationally efficient algorithm for color image segmentation using self-organizing map(SOM) and grassfire algorithm. We reduce a computation time by decreasing the number of input neuron and input data which is used for learning at SOM. First converting input image to CIE $L^*u^*v^*$ color space and run the learning stage with the SOM-input neuron size is three and output neuron structure is 4by4 or 5by5. After learning, compute output value correspondent with input pixel and merge adjacent pixels which have same output value into segment using grassfire algorithm. The experimental results with various images show that proposed method lead to a good segmentation results than others.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.399-408
• /
• 2020

The construction industry is suffering from aging workers, frequent accidents, as well as low productivity. With the rapid development of information technologies in recent years, automatic construction, especially automatic cranes, is regarded as a promising solution for the above problems and attracting more and more attention. However, in practice, limited by the complexity and dynamics of construction environment, manual inspection which is time-consuming and error-prone is still the only way to recognize the search object for the operation of crane. To solve this problem, an image-processing-based automated object recognition approach is proposed in this paper, which is a fusion of Convolutional-Neutral-Network (CNN)-based and traditional object detections. The search object is firstly extracted from the background by the trained Faster R-CNN. And then through a series of image processing including Canny, Hough and Endpoints clustering analysis, the vertices of the search object can be determined to locate it in 3D space uniquely. Finally, the features (e.g., centroid coordinate, size, and color) of the search object are extracted for further recognition. The approach presented in this paper was implemented in OpenCV, and the prototype was written in Microsoft Visual C++. This proposed approach shows great potential for the automatic operation of crane. Further researches and more extensive field experiments will follow in the future.

• The KIPS Transactions:PartB
• /
• v.9B no.1
• /
• pp.113-118
• /
• 2002

This paper presents a cluster-based image retrieval method. It retrieves images from a related cluster after classifying images into clusters using RAGMD, a clustering technique. When images are retrieved, first they are retrieved not from the whole image database one by one but from the similar cluster, a similar small image group with a query image. So it gives us retrieval-time reduction, keeping almost the same precision with the exhaustive retrieval. In the experiment using an image database consisting of about 2,400 real images, it shows that the proposed method is about 18 times faster than 7he exhaustive method with almost same precision and it can retrieve more similar images which belong to the same class with a query image.

• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.591-600
• /
• 2006

This paper describes the development and implementation of a algorithm to decompose word images from image regions mixed text/graphics in document images using statistical analyses. To decompose word images from image regions, the character components need to be separated from graphic components. For this process, we propose a method to separate them with an analysis of box-plot using a statistics of structural components. An accuracy of this method is not sensitive to the changes of images because the criterion of separation is defined by the statistics of components. And then the character regions are determined by analyzing a local crowdedness of the separated character components. finally, we devide the character regions into text lines and word images using projection profile analysis, gap clustering, special symbol detection, etc. The proposed system could reduce the influence resulted from the changes of images because it uses the criterion based on the statistics of image regions. Also, we made an experiment with the proposed method in document image processing system for keyword spotting and showed the necessity of studying for the proposed method.