• Journal of Korean Neurosurgical Society
• /
• v.64 no.4
• /
• pp.495-504
• /
• 2021

Three-dimensional printing (3DP) applications possess substantial versatility within surgical applications, such as complex reconstructive surgeries and for the use of surgical resection guides. The capability of constructing an implant from a series of radiographic images to provide personalized anatomical fit is what makes 3D printed implants most appealing to surgeons. Our objective is to describe the process of integration of 3DP implants into the operating room for spinal surgery, summarize the outcomes of using 3DP implants in spinal surgery, and discuss the limitations and safety concerns during pre-operative consideration. 3DP allows for customized, light weight, and geometrically complex functional implants in spinal surgery in cases of decompression, tumor, and fusion. However, there are limitations such as the cost of the technology which is prohibitive to many hospitals. The novelty of this approach implies that the quantity of longitudinal studies is limited and our understanding of how the human body responds long term to these implants is still unclear. Although it has given surgeons the ability to improve outcomes, surgical strategies, and patient recovery, there is a need for prospective studies to follow the safety and efficacy of the usage of 3D printed implants in spine surgery.

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.56-66
• /
• 2023

The goal of deep learning is to extract complex features from multidimensional data use the features to create models that connect input and output. Deep learning is a process of learning nonlinear features and functions from complex data, and the user data that is employed to train deep learning models has become the focus of privacy concerns. Companies that collect user's sensitive personal information, such as users' images and voices, own this data for indefinite period of times. Users cannot delete their personal information, and they cannot limit the purposes for which the data is used. The study has designed a deep learning method that employs privacy protection technology that uses distributed collaborative learning so that multiple participants can use neural network models collaboratively without sharing the input datasets. To prevent direct leaks of personal information, participants are not shown the training datasets during the model training process, unlike traditional deep learning so that the personal information in the data can be protected. The study used a method that can selectively share subsets via an optimization algorithm that is based on modified distributed stochastic gradient descent, and the result showed that it was possible to learn with improved learning accuracy while protecting personal information.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.5 s.305
• /
• pp.19-26
• /
• 2005

In this paper, a new method for obtaining three-dimensional shape of an object by measuring relative blur between images using wavelet analysis has been described. Most of the previous methods use inverse filtering to determine the measure of defocus. These methods suffer from some fundamental problems like inaccuracies in finding the frequency domain representation, windowing effects, and border effects. Besides these deficiencies, a filter, such as Laplacian of Gaussian, that produces an aggregate estimate of defocus for an unknown texture, can not lead to accurate depth estimates because of the non-stationary nature of images. We propose a new depth from defocus (DFD) method using wavelet analysis that is capable of performing both the local analysis and the windowing technique with variable-sized regions for non-stationary images with complex textural properties. We show that normalized image ratio of wavelet power by Parseval's theorem is closely related to blur parameter and depth. Experimental results have been presented demonstrating that our DFD method is faster in speed and gives more precise shape estimates than previous DFD techniques for both synthetic and real scenes.

• Journal of the Korea Convergence Society
• /
• v.8 no.8
• /
• pp.33-40
• /
• 2017

In this paper, we propose a text extraction method by pattern analysis on contour for effective text detection in image. Text extraction algorithms using edge based methods show good performance in images with simple backgrounds, The images of complex background has a poor performance shortcomings. The proposed method simplifies the color of the image by using K-means clustering in the preprocessing process to detect the character region in the image. Enhance the boundaries of the object through the High pass filter to improve the inaccuracy of the boundary of the object in the color simplification process. Then, by using the difference between the expansion and erosion of the morphology technique, the edges of the object is detected, and the character candidate region is discriminated by analyzing the pattern of the contour portion of the acquired region to remove the unnecessary region (picture, background). As a final result, we have shown that the characters included in the candidate character region are extracted by removing unnecessary regions.

• Proceedings of the Korea Contents Association Conference
• /
• 2003.05a
• /
• pp.255-259
• /
• 2003

The technique of birdeye image generation of terrain through the use of satellite digital images and digital maps are very important elements and have applications in planning establishment as well as the actual design of several construction work in complex fields. This paper studies stereo perspective image generation as a possibility through 3-dimensional analysis combined with digital elevation data and remotely sensed images. For this, first of all, ortho-images generated by very accurate GCP and DEM from contour file makes 3-dimensional terrain analysis possible and allows stereo-viewing at the highway construction planning sites. So, we developed the technical methods for the 3-dimensional approach on the planning sites of highways by use of perspective orthoimages. From this research diverse terrain analysis is possible through stereo perspective image generation, and can leads to various application in road construction through gain study results from access to realtime virtual spatial on the objects area in korea.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.344-346
• /
• 2004

IKONOS 1m satellite imagery is particularly well suited for 3-D feature extraction and 1 :5,000 scale topographic mapping. Because the image line and sample calculated by given RPCs have the error of more than 11m, in order to be able to perform feature extraction and topographic mapping, rational polynomial coefficients(RPCs) camera model that are derived from the very complex IKONOS sensor model to describe the object-image geometry must be refined by several Ground Control Points(GCPs). This paper presents a quantitative evaluation of the geometric accuracy that can be achieved with IKONOS imagery by refining the offset and scaling factors of RPCs using several GCPs. If only two GCPs are available, the offsets and scale factors of image line and sample are updated. If we have more than three GCPs, four parameters of the offsets and scale factors of image line and sample are refined first, and then six parameters of the offsets and scale factors of latitude, longitude and height are updated. The stereo images acquired by IKONOS satellite are tested using six ground points. First, the RPCs model was refined using 2 GCPs and 4 check points acquired by GPS. The results from IKONOS stereo images are reported and these show that the RMSE of check point acquired from left images and right are 1.021m and 1.447m. And then we update the RPCs model using 4 GCPs and 2 check points. The RMSE of geometric accuracy is 0.621 m in left image and 0.816m in right image.

• The Journal of Information Technology
• /
• v.4 no.2
• /
• pp.129-136
• /
• 2001

Most of the acoustic microscopes have been constructed acoustic image by simply measuring the amplitude of the reflected signal from the specimen. This method fails to produce images of good quality because the change in amplitude is not sensitive enough to specimen with fine variation. In this paper, we have been constructed the acoustic microscope system which has been able to measure simultaneously the amplitude and phase of the reflected ultrasonic signal. And also we have been constructed the amplitude and phase images for the 500 won coin as a sample and the alumium spacimen with internal round defect, and compared and analyzed these images. In expermental result, the phase image have shown better sensitive than the amplitude image and given better contrast for the micro height variation of specimen. It will be expected that the phase image can be used as an additional bit of information to improve ambiguituities in amplitude image on nondestructive testing for specimen with fine variation.

• Journal of Sensor Science and Technology
• /
• v.19 no.2
• /
• pp.99-111
• /
• 2010

This paper proposes an efficient hardware architecture to estimate disparities between 2D images for generating 3D depth images in a stereo vision system. Stereo matching methods are classified into global and local methods. The local matching method uses the cost functions based on pixel windows such as SAD(sum of absolute difference), SSD(sum of squared difference) and NCC(normalized cross correlation). The NCC-based cost function is less susceptible to differences in noise and lighting condition between left and right images than the subtraction-based functions such as SAD and SSD, and for this reason, the NCC is preferred to the other functions. However, software-based implementations are not adequate for the NCC-based real-time stereo matching, due to its numerous complex operations. Therefore, we propose a fast pipelined hardware architecture suitable for real-time operations of the NCC function. By adopting a block-based box-filtering scheme to perform NCC operations in parallel, the proposed architecture improves processing speed compared with the previous researches. In this architecture, it takes almost the same number of cycles to process all the pixels, irrespective of the window size. Also, the simulation results show that its disparity estimation has low error rate.

• The Journal of the Korea Contents Association
• /
• v.10 no.4
• /
• pp.19-27
• /
• 2010

In recent years, high-throughput genome-wide RNA interference screening is emerging as an essential tool to biologists in understanding complex cellular processes. The manual analysis of the large number of images produced in each study spends much time and the labor. Hence, automatic cellular image analysis becomes an urgent need, where segmentation is the first and one of the most important steps. However, those factors such as the region overlapping, a variety of shapes, and non-uniform local characteristics of cellular images become obstacles to efficient cell segmentation. To avoid the problem, a new watershed-based cell segmentation algorithm using a localized segmentation method and a feature vector is proposed in this paper. Localized approach in segmentation resolves the problems caused by a variety of shapes and non-uniform characteristics. In addition, the poor performance of segmentation in overlapped regions can be improved by taking advantage of a feature vector whose component features complement each other. Simulation results show that the proposed method improves the segmentation performance compared to the method in Cellprofiler.

• Journal of the Korean Society for Precision Engineering
• /
• v.33 no.11
• /
• pp.885-891
• /
• 2016

3D images are generally manufactured by complex production processes. We suggested a simple method to make 3D images based on a mechanical machining technology in this study. We designed a tetrahedron consisted of many arcs having the depth of $100{\mu}m$ and the pitch of $500{\mu}m$, and machined them on an aluminum plate using end-milling under several conditions of feed-rate and depth of cut. The area of undeformed chip including depth of cut and feed-rate can predict quality of the machined arcs more precisely than the undeformed chip thickness including only feed rate. Moreover, a diamond tool can improve the quality than a CBN tool when many arcs are machined. Based on the analysis, the designed tetrahedron having many arcs was machined with no burr, and it showed different images when observed from the left and right directions. Therefore, it is verified that a 3D image can be designed and manufactured on a metal plate by end-milling under optimized machining conditions.