• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1269-1279
• /
• 2019

In medical image analysis, segmentation is considered as a vital process since it partitions an image into coherent parts and extracts interesting objects from the image. In this paper, we consider automatic segmentations of OCT retinal images to find six layer boundaries using convolutional neural networks. Segmenting retinal images by layer boundaries is very important in diagnosing and predicting progress of eye diseases including diabetic retinopathy, glaucoma, and AMD (age-related macular degeneration). We applied well-known CNN architecture for general image segmentation, called Segnet, U-net, and CNN-S into this problem. We also proposed a shortest path-based algorithm for finding the layer boundaries from the outputs of Segnet and U-net. We analysed their performance on public OCT image data set. The experimental results show that the Segnet combined with the proposed shortest path-based boundary finding algorithm outperforms other two networks.

• Journal of KIISE:Software and Applications
• /
• v.30 no.7_8
• /
• pp.719-726
• /
• 2003

This paper proposes a multimodal registration method for segmentation of the Visible Human color images, in which color characteristics of bones are very similar to those of its surrounding fat areas. Bones are initially segmented in CT images, and then registered into color images to lineate their boundaries in the color images. For the segmentation of bones in CT images, a thresholding method is developed. The registration method registers boundaries of bodies in CT and color images using a cross-correlation approach, in which the boundaries of bodies are extracted by thresholding segmentation methods. The proposed method has been applied to segmentation of bones in a head and legs whose boundary is ambiguous due to surrounding fat areas with similar color characteristics, and produced promising results.

• Journal of Korea Foundry Society
• /
• v.29 no.1
• /
• pp.33-37
• /
• 2009

Cartesian grid system has mainly been used in the casting simulation even though it does not nicely represent sloped and curved surfaces. These distorted boundaries cause several problems. A special treatment is necessary to clear these problems. In this paper, we propose a new method that can consider the cutting cells which are cut by casting and mold based on the partial cell treatment (PCT). This method provides a better representation of geometry surface and will be used in the computation of velocities that are defined on the cell boundaries in the Cartesian grid system. Various test examples for several casting process were computed and validated. The analysis results of more accurate fluid flow pattern and less momentum loss owing to the stepped boundaries in the Cartesian grid system were confirmed. By using the cut cell method, performance of computation gets better because of reducing the whole number of meshes.

• 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.

• Proceedings of the Materials Research Society of Korea Conference
• /
• 2011.05a
• /
• pp.239.1-239.1
• /
• 2011

Dye sensitized solar cells (DSC) are promising devices for inexpensive, nontoxic, transparent, and large-scale solar energy conversion. Generally thick $TiO_2$ nanoporous films act as efficient photoanodes with their large surface area for absorbing light. However, electron transport through nanoparticle networks causes the slowdown and the loss of electron transport because of a number of interparticle boundaries inside the conduction path. We have studied DSCs with precisely dimension-controlled $TiO_2$ nanotubes array as photoanode. $TiO_2$ nanotubes array is prepared by template-directed fabrication method with atomic layer deposition. Well-ordered nanotubes array provides not only large surface area for light absorbing but also direct pathway for electrons with minimalized grain boundaries. Large enlongated anatase grains in the nanotubes could enhance the conductivity of electrons, but also suppress the recombination with holes through defect sites during diffusion into the electrode. To study the effect of grain boundaries, we fabricated two kinds of nanotubes which have different grain sizes by controlling deposition conditions. And we studied electron conduction through two kinds of nanotubes with different grain structures. The solar cell performance was studied as a function of thickness and grain structures. And overall solar-to-electric energy conversion efficiencies of up to 7% were obtained.

• Korean Journal of Computational Design and Engineering
• /
• v.4 no.3
• /
• pp.173-179
• /
• 1999

In reverse engineering, when a shape containing multi-patched surfaces is digitized, the boundaries of these surfaces should be detected. The objective of this paper is to introduce a computationally efficient segmentation technique for extracting edges, ad partitioning the 3D measuring point data based on the location of the boundaries. The procedure begins with the identification of the edge points. An automatic edge-based approach is developed on the basis of local geometry. A parametric quadric surface approximation method is used to estimate the local surface curvature properties. the least-square approximation scheme minimizes the sum of the squares of the actual euclidean distance between the neighborhood data points and the parametric quadric surface. The surface curvatures and the principal directions are computed from the locally approximated surfaces. Edge points are identified as the curvature extremes, and zero-crossing, which are found from the estimated surface curvatures. After edge points are identified, edge-neighborhood chain-coding algorithm is used for forming boundary curves. The original point set is then broke down into subsets, which meet along the boundaries, by scan line algorithm. All point data are applied to each boundary loops to partition the points to different regions. Experimental results are presented to verify the developed method.

• Proceedings of the KIEE Conference
• /
• 1998.07d
• /
• pp.1361-1363
• /
• 1998

Poly-Si grain boundaries act as potential barriers as well as recombination centers for the photo-generated carriers in solar cells. Thereby, grain boundaries of poly-Si are considered as a major source of the poly-Si cell efficiency was reduced This paper investigated grain boundary effect of poly-Si wafer prior to the solar cell fabrication. By comparing I-V characteristics inner grain, on and across the grain boundary, we were able to detect grain potentials. To reduce grain boundary effect we carried out pretreatment, $POCl_3$ gettering, and examined carrier lifetime. This paper focuses on resistivity variation effect due to grain boundary of poly-Si. The resistivity of the inner grain was $2.2{\Omega}-cm$, on the grain boundary$2.3{\Omega}-cm$, across the grain boundary $2.6{\Omega}-cm$. A measured resistivity varied depending on how many grains were included inside the four point probes. The resistivity increased as the number of grain boundaries increased. Our result can contribute to achieve high conversion efficiency of poly-Si solar cell by overcoming the grain boundary influence.

• Laser Solutions
• /
• v.7 no.3
• /
• pp.25-36
• /
• 2004

This study was performed to clarification of the formation of weld discontinuities in the dissimilar laser fusion zone. Welding parameters were beam power of 1300, 1430, 1560, and 1700 W and travel speed of 1, 1.3, and 1.7 m/min. Most cavities in the fusion zone were observed near the tip. Cavities in the fusion zone observed to be formed and grown from pores in the tip. More cavities were formed as the beam position moves to the tip side. Small cavities were decreased but large cavities were increased when the energy input increased. W content in the fusion zone was increased with heat input and as the beam position close to the tip. In the fusion zone, W content in the dendrite boundary was increased with heat input. Considering the propagation path and fracture morphology, cracks were solidification cracking, and were initiated and propagated along the dendrite boundaries. The formation of cracks might be related with the W rich ${\mu}$ phase which was formed in the grain boundaries and dendrite boundaries.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.8
• /
• pp.9-16
• /
• 1999

Generally, a speaker structures utterances very clearly by grouping words into phrases. This facilitates the listener's recovery of the meaning of the utterance and the speaker's intention. To this purpose, a speaker uses, among other things, prosodic information such as intonation pause, duration, intensity, etc. The research described here is concerned with the relationship between the strength of prosodic boundaries in spoken utterances as perceived by untrained listeners(Perceptual boundary strength, PBS)-In this paper, the preceptual boundary strength is used as the same meaning of the prosodic boundary strength-and prosodic information. We made a rule determinating the prosodic boundaries and verified the usefulness of the prosodic phrase as a recognition unit. Experiments results showed that the performance of speech recognition(SR) is improved in aspect of recognition rate and time compared with that using sentences as recognition unit. In the future we will suggest the methods that estimate more appropriate boundaries and study more various methods of prosody assisted SR.

• Phonetics and Speech Sciences
• /
• v.9 no.4
• /
• pp.9-17
• /
• 2017

The aim of this study is to examine whether Chinese Korean learners (CKL) can correctly produce the aspiration in 'a lenis obstruents /k/, /t/, /p/, /ʧ/+/h/ sound' sequence at the lexical and post-lexical level. For this purpose 4 Korean native speakers (KNS), 10 advanced and 10 intermediate CKL participated in a production test. The material analyzed consisted of 10 Korean sentences in which aspiration can be applied at different prosodic boundaries (syllable, word, accentual phrase). The results showed that for KNS and CKL, the rate of application of aspiration was different according to prosodic boundaries. Aspiration was more frequently applied at the lexical level than at the post-lexical level and it was more frequent at the word boundary than at the accentual phrase boundary. For CKL, pronunciation errors were either non-application of aspiration or coda obstruent omission. In the case of non-application of aspiration, CKL produced the target syllable as an underling form and they did not transform it as a surface form. In the case of coda obstruent ommision, most of the errors were caused by the inherent complexity of phonological process.