• The Journal of the Korea Contents Association
• /
• v.10 no.4
• /
• pp.66-75
• /
• 2010

In Augmented Reality, it needs restoration and tracking of a real-time scene structure for the augmented 3D model from input video or images. Most of the previous approaches construct accurate 3D models in advance and try to fit them in real-time. However, it is difficult to measure 3D model accurately and requires long pre-processing time to construct exact 3D model specifically. In this research, we suggest a real-time scene structure analysis method for the wide indoor mobile augmented reality, using only generic models without exact pre-constructed models. Our approach reduces cost and time by removing exact modeling process and demonstrates the method for restoration and tracking of the indoor repetitive scene structure such as corridors and stairways in different scales and details.

• Journal of KIISE
• /
• v.43 no.8
• /
• pp.869-877
• /
• 2016

In this paper, we propose an automated segmentation method of femoral cartilage in knee MR images using multi-atlas-based locally-weighted voting. The proposed method involves two steps. First, to utilize the shape information to show that the femoral cartilage is attached to a femur, the femur is segmented via volume and object-based locally-weighted voting and narrow-band region growing. Second, the object-based affine transformation of the femur is applied to the registration of femoral cartilage, and the femoral cartilage is segmented via multi-atlas shape-based locally-weighted voting. To evaluate the performance of the proposed method, we compared the segmentation results of majority voting method, intensity-based locally-weighted voting method, and the proposed method with manual segmentation results defined by expert. In our experimental results, the newly proposed method avoids a leakage into the neighboring regions having similar intensity of femoral cartilage, and shows improved segmentation accuracy.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.11C
• /
• pp.1029-1039
• /
• 2009

In this paper, the existing disparity aquisition algorithms were analyzed, on the bases of which a disparity generation technique that is superior in accuracy to the generation time was proposed. Basically it uses a pixel-by-pixel motion estimation technique. It has a merit of possibility of a high-speed operation. But the motion estimation technique has a disadvantage of lower accuracy because it depends on the similarity of the matching window regardless of the distribution characteristics of the texture in an image. Therefore, an enhanced technique to increase the accuracy of the disparity is required. This paper introduced a variable-sized window matching technique for this requirement. By the proposed technique, high accuracies could be obtained at the homogeneous regions and the object edges. A hardware to generate disparity image was designed, which was optimized to the processing speed so that a high throughput is possible. The hardware was designed by Verilog-HDL and synthesized using Hynix $0.35{\mu}m$ CMOS cell library. The designed hardware was operated stably at 120MHz using Cadence NC-VerilogTM and could process 15 frames per second at this clock frequency.

• Journal of The Korean Association For Science Education
• /
• v.31 no.1
• /
• pp.128-142
• /
• 2011

The goal of this study was to investigate how hypotheses were elaborated after their initial appearances in the context of scientific problem solving. Data were collected from a class in which preservice elementary school teachers in groups carried out abductive inquiry of earth science. The analysis revealed two major processes of hypothesis elaboration: theory-driven and evidence-driven. The theory-driven process was in turn distinguished into two kinds of subprocesses: one is in pursuit of internal coherence and the other external coherence. The evidencedriven elaboration also had two subprocesses, which were triggered by direct evidence and indirect or analogical evidence, respectively. In addition, hypotheses were more often than not modified by a wrong theory or evidence whether it was driven by a theory or evidence. Implications for science education and related research were discussed.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.39 no.2
• /
• pp.107-115
• /
• 2002

In this paper, we describe a novel method to generate an intermediate scene using BDM (Bidirectional Disparity Morphing) from the parallel stereopair. Because an image is composed of several layers and each layer has a similar disparity, it is available to use the block based disparity estimation. In order to prevent the false correspondence, however, we closely investigate the corresponding block as we adaptively vary the block size according to the estimation error. Therefore, we can detect the occlusion because of larger estimation error of the occluded region. We define three occluding patterns, which ate derived from the peculiar property of the disparity map, in order to smooth the computed disparity map. The filtered disparity map using these patterns presents that the false disparities ate well corrected and the boundary between foreground and background becomes sharper. As a result, we can improve the quality of the intermediate scenes.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.11A
• /
• pp.1872-1879
• /
• 2001

As multiview video applications become more popular, correspondence problem for stereo image matching plays an important role in expanding view points. Thus, we propose an efficient dense disparity estimation algorithm considering features of each image pair of multiview image sets. Main concepts of the proposed algorithm are based on the region-dividing-bidirectional-pixel-matching method. This algorithm makes matching process efficient and keeps the reliability of the estimated disparities. Other improvement have obtained by proposed cost function, matching window expanding technique, disparity regularization, and disparity assignment in ambiguous region. These techniques make disparities more stable by removing false disparities and ambiguous regions. The estimated disparities are used to synthesize intermediate views of multiview images. Computer simulation demonstrates the excellence of the proposed algorithm in both subjective and objective evaluations. In addition, processing time is reduced as well.

• Journal of KIISE:Software and Applications
• /
• v.32 no.1
• /
• pp.22-33
• /
• 2005

In this paper. we propose an image registration algorithm based on variable-sized blocks of ellipsoidal prototype model which is similar in shape to human face. While matching blocks, the existing cylindrical prototype model which only takes into account left and right curvature can accomplish a correct alignment on left and right images. But, registration errors are produced from up and down images because the cylindrical prototype model not reflects characteristics of head shape and jaw structure of human. The proposed method is a block matching algorithm which uses variable-sized blocks with considering left-right and up-down curvature of ellipsoidal face model and can correctly align images by using the correlation between them. We then adapt image mosaic technique to generate a face texture from aligned images. For this purpose, we stitch them with assigning linear weights according to the overlapped region and remove ghost effects to make more realistic facial texture.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.4
• /
• pp.164-174
• /
• 2015

In a real scenario, radiometric change has frequently occurred in the stereo image acquisition process using multiple cameras with geometric characteristics or moving a single camera because it has different camera parameters and illumination change. Conventional stereo matching algorithms have a difficulty in finding correct corresponding points because it is assumed that corresponding pixels have similar color values. In this paper, we present a new method based on the local descriptor reflecting intensity, gradient and texture information. Furthermore, an adaptive weight for local descriptor based on the entropy is applied to estimate correct corresponding points under radiometric variation. The proposed method is tested on Middlebury datasets with radiometric changes, and compared with state-of-the-art algorithms. Experimental result shows that the proposed scheme outperforms other comparison algorithms around 5% less matching error on average.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.13 no.5
• /
• pp.436-444
• /
• 2002

This paper presents a new method, which uses defected ground structure (DGS) on the ground planes of planar transmission lines such as microstrip and coplanar waveguide (CPW), to reduce the size of amplifiers. The main idea can be summarized as follow; DGS on the ground plane of microstrip or CPW line shows an increased slow-wave effect due to the additional equivalent L-C components. So the electrical length of the transmission line with DGS is longer than that of the standard transmission line for the same physical length. Then, the length of the transmission line with DGS can be shortened in order to maintain the original electrical length to be the same. This leads the matching of the original amplifier to be kept. In order to show the proposed method is valid, two kinds of amplifiers, the original amplifier and reduced amplifier, are fabricated, measured, and compared using both microstrip and CPW. The measured performances of the reduced amplifiers with DGS are quite similar to the ones of the original amplifiers for both microstrip and CPW amplifiers, even though the size of matching networks of the amplifiers with DGS are much smaller than those of the original amplifiers.

• Journal of Intelligence and Information Systems
• /
• v.9 no.1
• /
• pp.125-137
• /
• 2003

In eastern countries stamps have been used more commonly than signatures when approving contracts and documents. Unlike finger prints, stamp images do not share similar patterns to each other and the resolution of stamp images is determined by the input status such as pressure under which stamps are put. This paper discusses the development of a system for recognizing stamp images of Korean or Chinese characters. Recognition of stamp images consists of several steps: acquisition of stamp images from an input device, digitization, contrast stretching, noise removal, and matching. We tested the system on 50 stamp images (20 stamp images of Korean characters, 20 images of Chinese characters, and 10 similar images). There was little difference in discrimination rate between the stamp images of Korean character and those of Chinese characters. 46 stamps images out of 50 were successfully recognized, resulting in 92% discrimination rate. Orientation and pressure under which stamps are put played an important role in determining discrimination rate. Automated stamp image recognition can be made more practical and useful by extending the types of stamp images to ellipses and rectangles and by improving the discrimination rate.