• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.134-141
• /
• 2023

We present a novel method aimed at refining ground truth data through regularization and modification, particularly applicable when working with the original ground truth set. Enhancing the performance of deep neural networks is achieved by applying regularization techniques to the existing ground truth data. In many machine learning tasks requiring pixel-level segmentation sets, accurately delineating objects is vital. However, it proves challenging for thin and elongated objects such as blood vessels in X-ray coronary angiography, often resulting in inconsistent generation of ground truth data. This method involves an analysis of the quality of training set pairs - comprising images and ground truth data - to automatically regulate and modify the boundaries of ground truth segmentation. Employing the active contour model and a recursive ground truth generation approach results in stable and precisely defined boundary contours. Following the regularization and adjustment of the ground truth set, there is a substantial improvement in the performance of deep neural networks.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.5
• /
• pp.303-311
• /
• 2003

Since the MPEG-4 visual standard enables content-based functionalities, it is necessary to extract video object from natural video sequences. Segmentation algorithms can largely be classified into automatic segmentation and user-assisted segmentation. In this paper, we propose a user-assisted VOP generation method based on the geometric active contour. Since the geometric active contour, unlike the parametric active contour, employs the level set method to evolve the curve, we can draw the initial curve independent of the shape of the object. In order to generate the edge function from a smoothed image, we propose a vector-valued diffusion process in the LUV color space. We also present a discrete 3-D diffusion model for easy implementation. By combining the curve shrinkage in the vector field space with the curve expansion in the empty vector space, we can make accurate extraction of visual objects from video sequences.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.23 no.3
• /
• pp.313-322
• /
• 2005

Rapid advances in technology and changes in human and cultural activities bring about changes to the earth surface in terms of spatial extension as well as time frame of the changes. Such advances introduce shorter updating frequency of maps and geospatial database. To satisfy these requirements, recent research efforts in the geoinformatics field have been focused on the automation and speeding up of the mapping processes which resulted in products such as the digital photogrammetric workstation, GPSIINS, applications of satellite imagery, automatic feature extraction and the LiDAR system. The possibility of automatically extracting buildings and generating contours from airborne LiDAR data has received much attention because LiDAR data produce promising results. However, compared with the manually derived building footprints using traditional photogrammetric process, more investigation and analysis need to be carried out in terms of accuracy and efficiency. On the other hand, generation of the contours with LiDAR data is more efficient and economical in terms of the quality and accuracy. In this study, the effects of various conditions of the pre-processing phase and the subsequent building extraction and contour generation phases for digital mapping have on the accuracy were investigated.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.2
• /
• pp.76-84
• /
• 2017

This paper presents an efficient method for generating spatiotemporal images in order to detect leukocyte motion in microvessels. Leveraging the constraint that leukocytes move along the contour line of the blood vessel wall, our proposed method efficiently generates spatiotemporal images for leukocyte motion detection. To that end, translational motion caused by in vivo movement is first removed by a template matching method. Second, the blood vessel region is detected by an automatic threshold selection method in order to binarize temporal variance images. Then, the contour of the blood vessel wall is expressed via B-spline function. Finally, using the detected blood vessel wall's contour as an initial curve, the plasma layer for the most accurate position is determined in order to find the spatial axis via snake, and the spatiotemporal images are generated. Experimental results show that the spatiotemporal images are generated effectively through comparison of each step with three images.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.17 no.6
• /
• pp.1361-1371
• /
• 1993

The effort of this paper is to develop a methodology of computer aided design and manufacture of spatial cams. The integrated CAD/CAM systems for spatial cams are developed to enable manufacturer to design and machine them readily. The contour of spatial cams can be obtained by applying envelope theory to the cam/follower motion. The mathematical cam contour is evaluated at some increment to generate the numerical data for the CNC programming. Incremental generation of points along a cam contour can be accomplished in consideration with the specified tolerance. The computerized procedure is described in detail with accompanying examples.

• Journal of KIISE:Computer Systems and Theory
• /
• v.36 no.4
• /
• pp.311-325
• /
• 2009

This paper presents a method for analyzing Hangul glyphs with their outline fonts and obtaining intermediate fonts with two different fonts. The glyphs are represented and analyzed hierarchically such as characters, components(letters) and strokes. With the analysis results, we obtain several intermediate glyphs by morphing two different glyphs of same character. For a natural glyph contour morphing, we employ the curve morphing algorithm by weighted mean of strings. In addition, we provide four operations for transformation of glyphs with different topology. As a result, it is illustrated that the proposed Hangul glyphs morphing scheme is useful for new font generation from any exist fonts or handwritings.

• Journal of Advanced Navigation Technology
• /
• v.5 no.2
• /
• pp.123-133
• /
• 2001

The existing visualization methods using the satellite images or map images require complicated preprocessing stages and a large amount of visual data to represent the 3-D terrain. This paper presents a 3-D visualization method for geographical information, which enables automatic generation of 3-D terrain. It is generated based, on contour information obtained from a numerical map. This paper also introduces a method that resolves the three main problems needed to visualize 3-D terrain from contour lines such as correspondence, tiling, and branching. The virtual contour line is defined to extend a distorted contour line to have a similar shape to the corresponding contour line that is used, to generate 3-D surfaces. It helps that 3-D terrain is represented exactly and in detail.

• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10a
• /
• pp.273-278
• /
• 1988

This paper represents the computer application techniques of initial and modification machining for dies with 3-dimensional scluptured surfaces. All procedures from die design to die machining and measurement are covered. The component of modelling is data management and modification (extrapolation and smoothing), surface modelling, and nc program preparation. Also this paper introduces the utility for successful and efficient operation of system such as map generation, data communication, tool path verification, contour map generation, graphic processing of extrapolation and smoothing results, and CAD/CAM system interface. Examples are given to illustrate the modelling.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.4
• /
• pp.469-476
• /
• 2009

The new laser scanning technology allows to attain 3D information faster with higher accuracy on surface ground, vegetation and buildings of the earth surface. This acquired information can be used in many areas after modifying them appropriately by users. The contour production for accurate landform is an advanced technology that can reveal the mountain area landscapes hidden by the trees in detail. However, if extremely precise LiDAR data is used in constructing the contour, massive-sized data intricates the contour diagram and could amplify the data size inefficiently. This study illustrates the algorithm producing contour that is filtered in stages for more efficient utilization using the LiDAR contour produced by the detailed landscape data. This filtering stages allow to preserve the original landscape shape and to keep the data size small. Point Filtering determines the produced contour diagram shape and could minimize data size. Thus, in this study we compared experimentally filtered contour with the current digital map(1:5,000).

• Aerospace Engineering and Technology
• /
• v.11 no.1
• /
• pp.118-125
• /
• 2012

The purpose of this study is to analyze the ortho image quality change according to the generation technique of Digital Elevation Model(DEM) based on the digital map. First of all, two different types of DEM were generated using contour layer(Case1), contour layer and altitude layer(Case2) from the digital map on the scale of 1/5,000. After generating and evaluating two types of DEM, KOMPSAT-2 ortho images were generated by using them. In conclusion, Case2 DEM was more effective to use in the slope and switchback area, on the other hand, Case1 DEM was much better than Case2 DEM for preventing a topographic distortion in flat area.