• Proceedings of the KSRS Conference
• /
• v.2
• /
• pp.772-775
• /
• 2006

Muilti-dimensional feature vector matching algorithm uses multiple features such as intensity, gradient, variance, first or second derivative of a pixel to find correspondence pixels in stereo images. In this paper, we proposed a new method for adjusting automatically the weight of feature in multi-dimensional feature vector matching considering sharpeness of a pixel in feature vector distance curve. The sharpeness consists of minimum and maximum vector distances of a small window mask. In the experiment we used IKONOS satellite stereo imagery and obtained accurate matching results comparable to the manual weight-adjusting method.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.05c
• /
• pp.245-248
• /
• 2002

OCR 시스템에서 feature는 인식성능에 상당히 중요한 역할을 한다. gradient feature는 현재까지 개발되어진 여러 가지 feature들 중에서 폭넓게 사용되고 있는 것 중의 하나이다. 본 논문에서는 변형이 심한 인쇄체 숫자를 실험대상으로 하고, Kirsch mask를 이용한 방향성을 가지는 edge를 추출하여 신경망의 입력벡터로 사용할 때 압축의 크기에 따른 인식성능의 차이를 비교하고, 최적의 벡터크기를 제안한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.10
• /
• pp.2441-2449
• /
• 2015

In this digital information era, utilization of images are essential for various media, and the edge is an important characteristical information of an object in images that includes the size, location, direction and etc. Many domestic and international studies are being conducted in order to detect these edge. Existing edge detection methods include Sobel, Prewitt, Roberts, Laplacian, LoG and etc. which apply fixed weight value. As these existing edge detection methods apply fixed weight mask to the image, edge detection characteristic appears slightly insufficient. Accordingly, in order to supplement these problems, this study used bottom-hat transformation from mathematical morphology and opening operation in improving the image and proposed an algorithm that detects for the edge after calculating mask-based gradient. And to evaluate the performance of the proposed algorithm, a comparison was made against the existing Sobel, Roberts, Prewitt, Laplacian, LoG edge detection methods, in illustrating visual images, and similarities were compared by calculating the MSE value based on the standard of each image.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.3
• /
• pp.1023-1033
• /
• 2014

In this paper, performance improved hole-filling algorithm which includes the boundary noise removing pre-process that can be used for an arbitrary virtual view synthesis has been proposed. Boundary noise occurs due to the boundary mismatch between depth and texture images during the 3D warping process and it usually causes unusual defects in a generated virtual view. Common-hole is impossible to recover by using only a given original view as a reference and most of the conventional algorithms generate unnatural views that include constrained parts of the texture. To remove the boundary noise, we first find occlusion regions and expand these regions to the common-hole region in the synthesized view. Then, we fill the common-hole using the spiral weighted average algorithm and the gradient searching algorithm. The spiral weighted average algorithm keeps the boundary of each object well by using depth information and the gradient searching algorithm preserves the details. We tried to combine strong points of both the spiral weighted average algorithm and the gradient searching algorithm. We also tried to reduce the flickering defect that exists around the filled common-hole region by using a probability mask. The experimental results show that the proposed algorithm performs much better than the conventional algorithms.

• Investigative Magnetic Resonance Imaging
• /
• v.18 no.4
• /
• pp.290-302
• /
• 2014

Purpose : Susceptibility-weighted magnetic resonance (MR) sequence is three-dimensional (3D), spoiled gradient-echo pulse sequences that provide a high sensitivity for the detection of blood degradation products, calcifications, and iron deposits. This pictorial review is aimed at illustrating and discussing its main clinical applications. Materials and Methods: SWI is based on high-resolution, 3D, fully velocity-compensated gradient-echo sequences using both magnitude and phase images. To enhance the visibility of the venous structures, the magnitude images are multiplied with a phase mask generated from the filtered phase data, which are displayed at best after post-processing of the 3D dataset with the minimal intensity projection algorithm. A total of 200 patients underwent MR examinations that included SWI on a 3 tesla MR imager were enrolled. Results: SWI is very useful in detecting multiple brain disorders. Among the 200 patients, 80 showed developmental venous anomaly, 22 showed cavernous malformation, 12 showed calcifications in various conditions, 21 showed cerebrovascular accident with susceptibility vessel sign or microbleeds, 52 showed brain tumors, 2 showed diffuse axonal injury, 3 showed arteriovenous malformation, 5 showed dural arteriovenous fistula, 1 showed moyamoya disease, and 2 showed Parkinson's disease. Conclusion: SWI is useful in detecting occult low flow vascular lesions, calcification and microbleed and characterising diverse brain disorders.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.9
• /
• pp.2199-2205
• /
• 2013

In modern society the image processing has been applied to various digital devices such as smartphone, digital camera, and digital TV. In the field of image processing the edge detection is one of the important parts in the image processing procedure. The image edge means point that the pixel value is changed between background and object rapidly, and includes the important information such as magnitude, location, and orientation. The performance of the existing edge detection method is insufficient for the image degraded by AWGN(additive white Gaussian noise) because it detects edges by using small weighted masks. Therefore, in this paper, to detect edge in AWGN environment effectively, we proposed an algorithm that detects edge as calculated gradient of sorting vector which is transformed by estimated mask from new pixel according to each region.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.711-714
• /
• 2024

In the dynamic landscape of modern machine learning, Federated Learning (FL) has emerged as a compelling paradigm designed to enhance privacy by enabling participants to collaboratively train models without sharing their private data. Specifically, Distillation-based Federated Learning, like Federated Learning with Model Distillation (FedMD), Federated Gradient Encryption and Model Sharing (FedGEMS), and Differentially Secure Federated Learning (DS-FL), has arisen as a novel approach aimed at addressing Non-IID data challenges by leveraging Federated Learning. These methods refine the standard FL framework by distilling insights from public dataset predictions, securing data transmissions through gradient encryption, and applying differential privacy to mask individual contributions. Despite these innovations, our survey identifies persistent vulnerabilities, particularly concerning the susceptibility to logit inversion attacks where malicious actors could reconstruct private data from shared public predictions. This exploration reveals that even advanced Distillation-based Federated Learning systems harbor significant privacy risks, challenging the prevailing assumptions about their security and underscoring the need for continued advancements in secure Federated Learning methodologies.

• Progress in Medical Physics
• /
• v.30 no.4
• /
• pp.139-149
• /
• 2019

Purpose: With neurodegeneration, the signal intensity of the cerebrospinal fluid (CSF) in the brain increases. The objective of this study was to evaluate chemical exchange saturation transfer (CEST) signals with and without the contribution of CSF signals in elderly human brains using two different 3T magnetic resonance imaging (MRI) sequences Methods: Full CEST signals were acquired in ten subjects (Group I) with a three-dimensional (3D)-segmented gradient-echo echo-planar imaging (EPI) sequence and in ten other subjects (Group II) with a 3D gradient and spin-echo (GRASE) sequence using two different 3T MRI systems. The segmented tissue compartments of gray and white matter were used to mask the CSF signals in the full CEST images. Two sets of magnetization transfer ratio asymmetry (MTR_asym) maps were obtained for each offset frequency in each subject with and without masking the CSF signals (masked and unmasked conditions, respectively) and later compared using paired t-tests. Results: The region-of-interest (ROI)-based analyses showed that the MTR_asym values for both the 3D-segmented gradient-echo EPI and 3D GRASE sequences were altered under the masked condition compared with the unmasked condition at several ROIs and offset frequencies. Conclusions: Depending on the imaging sequence, the MTR_asym values can be overestimated for some areas of the elderly human brain when CSF signals are unmasked. Therefore, it is necessary to develop a method to minimize this overestimation in the case of elderly patients.

• Investigative Magnetic Resonance Imaging
• /
• v.9 no.2
• /
• pp.134-139
• /
• 2005

Purpose : To evaluate the usefulness of acoustic noise attenuator on auditory fMRI examination. Materials and methods : The acoustic noise attenuator consists of mask, earmuff and silicon earplug. The soft polyurethane sheet and polyurethane form , which has a good soundproof characteristic were used for mask and earmuff. Auditory fMRI experiments of 500 Hz pure tone stimulation were performed in three different cases; first all of mask, earmuff and earplug, secondly earmuff and earplug only and finally without attenuator in 4 normal hearing volunteers. For data acquisition, BOLD MR imaging technique was employed at a 1.5T MR scanner equipped with high performance gradient system. The raw data were analyzed using a SPM-99 analysis software and the activation maps were obtained. Results : In case of all items of acoustic attenuator used, the results revealed that activation was focused on primary auditory area. When only earmuff and earplug were used, the results showed that the activation spread over primary auditory and secondary associative areas. Last, when no device used, only weak activation was observed on the right auditory cortex. Conclusion : It is expected that the acoustic noise attenuator, which consists of earplugs, earmuffs and mask, is a very useful device in auditory fMRI study.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.1
• /
• pp.10-19
• /
• 1989

This paper proposes the object modeling algorithm using depth data. In order to extract the shape of the object, surface is classified by the magnitude and the direction of Z gradient within the 2x2 mask from input depth data. For the object combined with several primitives is separated by kernel points. Further, spatial relationship between surface regions is extracted for the recognition. Finally, the effectiveness of this algorithm is demonstrated by several experiments.