• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.4
• /
• pp.353-362
• /
• 2012

3D building modeling from airborne Lidar without model regularization may cause positional errors or topological inconsistency in building models. Regularization of 3D building models, on the other hand, restricts the types of models which can be reconstructed. To resolve these issues, this paper modelled 3D buildings from airborne Lidar by building model regularization which considers more various types of buildings. Building points are first segmented into roof planes by clustering in feature space and segmentation in object space. Then, 3D building models are reconstructed by consecutive adjustment of planes, lines, and points to satisfy parallelism, symmetry, and consistency between model components. The experimental results demonstrated that the method could make more various types of 3d building models with regularity. The effects of regularization on the positional accuracies of models were also analyzed quantitatively.

• Journal of Korea Multimedia Society
• /
• v.12 no.3
• /
• pp.383-396
• /
• 2009

Bone age assessment has been widely used in pediatrics to identify endocrine problems of children. Since the number of trained doctors is far less than the demands, there has been numerous requests for automatic estimation of bone age. Therefore, in this paper, we propose an automatic bone age assessment method that utilizes pattern classification techniques. The proposed method consists of three modules; a finger segmentation module, a normalized shape model generation module and a bone age estimation module. The finger segmentation module segments fingers and epiphyseal regions by means of various image processing algorithms. The shape model abstraction module employ ASM to improves the accuracy of feature extraction for bone age estimation. In addition, SVM is used for estimation of bone age. Features for the estimation include the length of bone and the ratios of bone length. We evaluated the performance of the proposed method through statistical analysis by comparing the bone age assessment results by clinical experts and the proposed automatic method. Through the experimental results, the mean error of the assessment was 0.679 year, which was better than the average error acceptable in clinical practice.

• Speech Sciences
• /
• v.5 no.1
• /
• pp.7-21
• /
• 1999

This paper proposes an improved training procedure in speech recognition based on the continuous density of the Hidden Markov Model (CDHMM). Of the three parameters (initial state distribution probability, state transition probability, output probability density function (p.d.f.) of state) governing the CDHMM model, we focus on the third parameter and propose an efficient algorithm that determines the p.d.f. of each state. It is known that the resulting CDHMM model converges to a local maximum point of parameter estimation via the iterative Expectation Maximization procedure. Specifically, we propose two independent algorithms that can be embedded in the segmental K -means training procedure by replacing relevant key steps; the adaptation of the number of mixture Gaussian p.d.f. and the initialization using the CDHMM parameters previously estimated. The proposed adaptation algorithm searches for the optimal number of mixture Gaussian humps to ensure that the p.d.f. is consistently re-estimated, enabling the model to converge toward the global maximum point. By applying an appropriate threshold value, which measures the amount of collective changes of weighted variances, the optimized number of mixture Gaussian branch is determined. The initialization algorithm essentially exploits the CDHMM parameters previously estimated and uses them as the basis for the current initial segmentation subroutine. It captures the trend of previous training history whereas the uniform segmentation decimates it. The recognition performance of the proposed adaptation procedures along with the suggested initialization is verified to be always better than that of existing training procedure using fixed number of mixture Gaussian p.d.f.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.5
• /
• pp.187-194
• /
• 2014

Prostate cancer is a malignant tumor occurring in the prostate. Recently, the repetition rate is increasing. Image inspection method which we can check the prostate structure the most correctly is MRI(Magnetic Resonance Imaging), but it is hard to apply it to all the patients because of the cost. So, they use mostly TRUS(Transrectal Ultrasound) images acquired from prostate ultrasound inspection and which are cheap and easy to inspect the prostate in the process of treating and diagnosing the prostate cancer. Traditionally, in the hospital the doctors saw the TRUS images by their eyes and manually segmented the boundary between the prostate and nonprostate. But the manually segmenting process not only needed too much time but also had different boundaries according to the doctor. To cope the problems, some automatic segmentations of the prostate have been studied to generate the constant segmentation results and get the belief from patients. In this study, we propose an average shape model to segment the prostate boundary in TRUS prostate image. The method has 3 steps. First, it finds the probe using edge distribution. Next, it finds two straight lines connected with the probe. Finally it puts the shape model to the image using the position of the probe and straight lines.

• The KIPS Transactions:PartB
• /
• v.15B no.6
• /
• pp.561-574
• /
• 2008

The spot detection phase of the 2-DE image analysis program segments a gel image into spot regions by an image segmentation algorithm and fits the spot regions to a spot shape model and quantifies the spot informations for the next phases. Currently the watershed algorithm is generally used as the segmentation algorithm and there are the Gaussian model and the diffusion model for the shape model. The diffusion model is closer to real spot shapes than the Gaussian model however spots have very various shapes and especially an asymmetric formation in x-coordinate and y-coordinate. The reason for asymmetric formation of spots is known that a protein could not be diffused completely because the 2-DE could not be processed under the ideal environment usually. Accordingly we propose an asymmetric diffusion model in this paper. The asymmetric diffusion model assumes that a protein spot is diffused from a disc at initial time of diffusing process, but is diffused asymmetrically for x-axis and y-axis respectively as time goes on. In experiments we processed spot matching for 19 gel images by using three models respectively and evaluated averages of SNR for comparing three models. As averages of SNR we got 14.22dB for the Gaussian model, 20.72dB for the diffusion model and 22.85dB for the asymmetric diffusion model. By experimental results we could confirm the asymmetric diffusion model is more efficient and more adequate for spot matching than the Gaussian model and the diffusion model.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.5
• /
• pp.213-222
• /
• 2008

This paper is related to color image segmentation and textile texture mapping for the 2D virtual wearing system. The proposed system is characterized as virtually wearing a new textile pattern selected by user to the clothing shape section, based on its intensity difference map, segmented from a 2D clothes model image using color image segmentation technique. Regardless of color or intensity of model clothes, the proposed system is possible to virtually change the textile pattern or color with holding the illumination and shading properties of the selected clothing shape section, and also to quickly and easily simulate, compare, and select multiple textile pattern combinations for individual styles or entire outfits. The proposed system can provide higher practicality and easy-to-use interface, as it makes real-time processing possible in various digital environment, and creates comparatively natural and realistic virtual wearing styles, and also makes semi-automatic processing possible to reduce the manual works to a minimum. According to the proposed system, it can motivate the creative activity of the designers with simulation results on the effect of textile pattern design on the appearance of clothes without manufacturing physical clothes and, as it can help the purchasers for decision-making with them, promote B2B or B2C e-commerce.

• Journal of Internet Computing and Services
• /
• v.18 no.4
• /
• pp.61-67
• /
• 2017

Recently, CCTV has been combined with areas such as big data, artificial intelligence, and image analysis to detect various abnormal behaviors and to detect and analyze the overall situation of objects such as people. Image analysis research for this intelligent video surveillance function is progressing actively. However, CCTV images using 2D information generally have limitations such as object misrecognition due to lack of topological information. This problem can be solved by adding the depth information of the object created by using two cameras to the image. In this paper, we perform background modeling using Mixture of Gaussian technique and detect whether there are moving objects by segmenting the foreground from the modeled background. In order to perform the depth information-based segmentation using the RGB information-based segmentation results, stereo-based depth maps are generated using two cameras. Next, the RGB-based segmented region is set as a domain for extracting depth information, and depth-based segmentation is performed within the domain. In order to detect the center point of a robustly segmented object and to track the direction, the movement of the object is tracked by applying the CAMShift technique, which is the most basic object tracking method. From the experiments, we prove the efficiency of the proposed object detection and tracking method using the RGB-D model.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.414-423
• /
• 2020

In this paper, we propose a Dilated Convolution Gate Linear Unit (DCGLU) to mitigate the lack of sparsity and small receptive field problems caused by the segmentation map extraction process in sound event detection with weak labels. In the advent of deep learning framework, segmentation map extraction approaches have shown improved performance in noisy environments. However, these methods are forced to maintain the size of the feature map to extract the segmentation map as the model would be constructed without a pooling operation. As a result, the performance of these methods is deteriorated with a lack of sparsity and a small receptive field. To mitigate these problems, we utilize GLU to control the flow of information and Dilated Convolutional Neural Networks (DCNNs) to increase the receptive field without additional learning parameters. For the performance evaluation, we employ a URBAN-SED and self-organized bird sound dataset. The relevant experiments show that our proposed DCGLU model outperforms over other baselines. In particular, our method is shown to exhibit robustness against nature sound noises with three Signal to Noise Ratio (SNR) levels (20 dB, 10 dB and 0 dB).

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.913-924
• /
• 2022

In this paper, we presented a database construction of undersea images for the Habitats of Ecklonia cava and Sargassum and conducted an experiment for semantic segmentation using state-of-the-art (SOTA) models such as High Resolution Network-Object Contextual Representation (HRNet-OCR) and Shifted Windows-L (Swin-L). The result showed that our segmentation models were superior to the existing experiments in terms of the 29% increased mean intersection over union (mIOU). Swin-L model produced better performance for every class. In particular, the information of the Ecklonia cava class that had small data were also appropriately extracted by Swin-L model. Target objects and the backgrounds were well distinguished owing to the Transformer backbone better than the legacy models. A bigger database under construction will ensure more accuracy improvement and can be utilized as deep learning database for undersea images.

• Journal of Computing Science and Engineering
• /
• v.8 no.2
• /
• pp.65-77
• /
• 2014

To address the problem of multi-target retrieval (MTR) of remote sensing images, this study proposes a new object-level feature representation model. The model provides an enhanced application image representation that improves the efficiency of MTR. Generating the model in our scheme includes processes, such as object-oriented image segmentation, feature parameter calculation, and symbolic image database construction. The proposed model uses the spatial representation method of the extended nine-direction lower-triangular (9DLT) matrix to combine spatial relationships among objects, and organizes the image features according to MPEG-7 standards. A similarity metric method is proposed that improves the precision of similarity retrieval. Our method provides a trade-off strategy that supports flexible matching on the target features, or the spatial relationship between the query target and the image database. We implement this retrieval framework on a dataset of remote sensing images. Experimental results show that the proposed model achieves competitive and high-retrieval precision.