• Journal of Korea Multimedia Society
• /
• v.5 no.4
• /
• pp.415-425
• /
• 2002

In this paper, we present a content-based image retrieval method which is based on the feature extraction in the wavelet transform domain. In order to overcome the drawbacks of the feature vector making up methods which use the global wavelet coefficients in subbands, we utilize the energy value of wavelet coefficients, and the shape-based retrieval of objects is processed by moment which is invariant in translation, scaling, rotation of the objects The proposed methods reduce feature vector size, and make progress performance of classification retrieval which provides fast retrievals times. To offer the abilities of region-based image retrieval, we discussed the image segmentation method which can reduce the effect of an irregular light sources. The image segmentation method uses a region-merging, and candidate regions which are merged were selected by the energy values of high frequency bands in discrete wavelet transform. The region-based image retrieval is executed by using the segmented region information, and the images are retrieved by a color, texture, shape feature vector.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.5
• /
• pp.137-144
• /
• 2014

This paper proposes a novel procedure that uses a combination of overlapped basic convex shapes to decompose 2D silhouette image. A basic convex shape is used here as a structuring element to give a meaningful interpretation to 2D images. Poisson equation is utilized to obtain the basic shapes for either the whole image or a partial region or segment of an image. The reconstruction procedure is used to combine the basic convex shapes to generate the original shape. The decomposition process involves a merging stage, filtering stage and finalized by compromising stage. The merging procedure is based on solving Poisson's equation for two regions satisfying the same symmetrical conditions which leads to finding equivalencies between basic shapes that need to be merged. We implemented and tested our novel algorithm using 2D silhouette images. The test results showed that the proposed algorithm lead to an efficient shape decomposition procedure that transforms any shape into a simpler basic convex shapes.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.16 no.2
• /
• pp.187-194
• /
• 1998

In this study, effective multispectral Landsat TM band combinations for a merging with the high resolution IRS-1C PAN data using the IHS method to improve landuse accuracy is discussed. From the pre-classified image using the merged images with TM all six band images(with the exception of band 6 image) and PAN image, a sample data which has ten classes was generated. An evaluation of the overall classification accuracy for the representative seven merged images which were merged using each TM three-band images and IRS-1C PAN image by IHS method for the sample area. The increase in classification accuracy is most significant with the inclusion of two of TM4, TM5 and TM7 infrared band images. Especially, the largest increase(11.8 percent) in landuse classification accuracy were investigated when Landsat TM247 bands were merged with IRS-1C PAN data. The classification accuracy when TM three band image and PAN image were used without merging is higher than result of the case of using the merged images.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.6
• /
• pp.113-119
• /
• 2001

In this paper, we propose an improved watershed algorithm that resolves the oversegmentation problem shown in the previous watershed algorithm and its modifications when the spatial video segmentation is performed. The principal idea of the proposed algorithm is merging the shallow catchment basin whose depth is less than a given threshold into the deeper one during flooding step. In the flooding process, the growth of the existing catchment basins and the extraction of newly flooded ones are accomplished. We present the experimental results using several MPEG test sequences in the last part of the paper. As a consequence, the proposed algorithm shows good segmentation results according to the thresholds applied by adding very small amount of calculations.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.647-650
• /
• 2000

PACS의 보급으로 인하여 CT, MRI 등의 의료영상이 진료에 광범위하게 사용되고 있고, 또 의사가 좀 더 정량적이거나 사실적인 visualization을 위해서 분할은 필수적으로 수행되어져야 할 과정이라고 할 수 있다. 의료 영상에서 watershed 알고리듬을 이용하여 분할을 하는데 있어 가장 큰 문제가 되는 점은 과분할현상(Oversegmentation)이기 때문에 그 분할된 영역을 의미 있는 영역별로 합치는 영역 병합(merge) 과정을 필요로 하게 된다. 의료영상에서 모호한 경계는 매우 빈번하게 나타나기 때문에 기존의 병합 방법을 적용하는데 어려움이 있다. 본 논문에서는 이런 모호한 경계를 갖는 영상에서도 알맞는 병합을 가질 수 있는 적응적 영역 병합 방법을 제안한다. 제안된 분할 방법을 DICOM 영상의 폐 영상과 다리 뼈 영상에서 실험하였다. 그 결과 뼈와 폐영역을 성공적으로 병합하면서 인접한 장기들과는 구분 지을 수 있었다.

• Proceedings of the IEEK Conference
• /
• 2000.09a
• /
• pp.639-642
• /
• 2000

본 논문에서는 구름이나 연기와 같은 non-rigid object에 대한 영역 분할 방식에 대해 연구하였다. Non-rigid object의 효과적인 영역 분할을 위해서 object의 윤곽선을 정확히 파악해 낼 수 있는 장점을 가진 watershed 알고리즘을 사용하였다. 하지만 이 알고리즘은 object가 많은 영역으로 분할되는 oversegmentation 현상이 발생하여 본 논문에서는 pre, post-processing을 통해 이 oversegmentation 현상을 극복하고자 하였다. Pre-processing에서는 noise를 제거하고 영상을 단순화하면서 정확한 gradient magnitude를 구할 수 있는 방법에 대해서, post-processing에서는 통계적인 분석을 통한 region merging을 이용하여 object를 최적화 상태로 찾아줄 수 있는 방법에 대하여 연구하였다.

• The Bulletin of The Korean Astronomical Society
• /
• v.38 no.2
• /
• pp.49.2-49.2
• /
• 2013

We report preliminary results from a radio study of central galaxies in cool and non-cool core clusters. A cooling flow is expected to rapidly form in the center of galaxy clusters unless additional heating mechanisms such as merging with sub clusters are at work. It has been suggested that cool flows can feed the AGN in the central galaxies, increasing their power. On the other hand, the AGN feedback can also affect the surrounding medium, heating back up the gas in the cluster core region. In this study, we investigate the co-evolution of cool flows and the AGN of galaxies located in the cluster center. For this study, we have selected 13 radio bright central galaxies from clusters with a range of cooling time scale. In this work, we present results of our recent observations using the Korean VLBI Network. We discuss the properties of the sample in radio and other wavelengths.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.1
• /
• pp.723-733
• /
• 2009

This study proposes a sequence of procedures to extract building boundaries and planar patches through segmentation of rasterized lidar data. Although previous approaches to building extraction have been shown satisfactory, there still exist needs to increase the degree of automation. The methodologies proposed in this study are as follows: Firstly, lidar data are rasterized into grid form in order to exploit its rapid access to neighboring elevations and image operations. Secondly, propagation of errors in raw data is taken into account for in assessing the quality of gradients-driven properties and further in choosing suitable parameters. Thirdly, extraction of planar patches is conducted through a sequence of processes: histogram analysis, least squares fitting, and region merging. Experimental results show that the geometric components of building models could be extracted by the proposed approach in a streamlined way.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.571-574
• /
• 2005

In this paper, we propose an efficient image segmentation technique for large-sized monochrome images using a hybrid approach which combines threshold and region-based techniques. First, an image is partitioned into fixed-size blocks and for each block the representative intensity is determined by averaging pixel intensities within the block. Next, the neighborhood blocks that have similar characteristics with respect to a specific threshold are merged in order to form candidate regions. Finally, those candidate regions are refined to get final target object regions by merging regions considering the spatial locality and certain criteria. We have performed experiments on images selected from various domains and showed that our technique was able to extract target object regions appropriately from most images.

• Proceedings of the Korea Contents Association Conference
• /
• 2004.11a
• /
• pp.505-510
• /
• 2004

This paper suggests a new CT-image segmentation algorithm. This algorithm uses morphological filters and the watershed algorithms. The proposed CT-image segmentation algorithm consists of six parts: preprocessing, image simplification, feature extraction, decision making, region merging, and postprocessing. By combining spatial and temporal information, we can get more accurate segmentation results. The simulation results illustrate not only the segmentation results of the conventional scheme but also the results of the proposed scheme; this comparison illustrates the efficacy of the proposed technique. Furthermore, we compare the various medical images of the structuring elements. Indeed, to illustrate the improvement of coding efficiency in postprocessing, we use differential chain coding for the shape coding of results.