• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2000년도 춘계학술대회논문집 - 한국공작기계학회
• /
• pp.513-518
• /
• 2000

Surface roughness is one of the most important parameters to estimate quality of products. As this reason. so many studies were carried out through various attempts that were contact or non-contact using computer vision. Even though these efforts, there were few good results in this research. However, texture analysis is making a important role to solve these problems in various fields including universe, aviatiion, living thing and fibers. In this study, texture parameter was obtained by means of position operator according to variation of angle direction and distance. As a result, it was found that surface texture was more effected by direction then distance

• 한국통신학회논문지
• /
• 제32권5C호
• /
• pp.530-535
• /
• 2007

변이공간영상(Disparity space image, DSI) 방법은 스테레오 영상간의 정합을 찾는 방법이다. 이 방법은 각 화소 단위로 변이값을 계산해 내는 장점이 있다. DSI 방법은 비용함수를 최소화시키는 정합을 찾는 방법이다. 이 비용함수에서 폐색영역비용 값과 정합 보상값을 경험적으로 정하여왔다. 본 논문에서는 변이공간영상 방법에서 폐색영역비용과 정합보상값이 영상 잡음과 물체와 배경간의 차이에 영향을 받는 것을 이론적으로 분석하였다.

• Journal of International Society for Simulation Surgery
• /
• 제3권1호
• /
• pp.9-11
• /
• 2016

Purpose In this paper we proposed bi-directional hierarchical regression for accurate human finger landmark detection with only using depth information.Materials and Methods Our algorithm consisted of two different step, initialization and landmark estimation. To detect initial landmark, we used difference of random pixel pair as the feature descriptor. After initialization, 16 landmarks were estimated using cascaded regression methods. To improve accuracy and stability, we proposed bi-directional hierarchical structure.Results In our experiments, the ICVL database were used for evaluation. According to our experimental results, accuracy and stability increased when applying bi-directional hierarchical regression more than typical method on the test set. Especially, errors of each finger tips of hierarchical case significantly decreased more than other methods.Conclusion Our results proved that our proposed method improved accuracy and stability and also could be applied to a large range of applications such as augmented reality and simulation surgery.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권5호
• /
• pp.2253-2272
• /
• 2018

We propose a deep learning method for multi-focus image fusion. Unlike most existing pixel-level fusion methods, either in spatial domain or in transform domain, our method directly learns an end-to-end fully convolutional two-stream network. The framework maps a pair of different focus images to a clean version, with a chain of convolutional layers, fusion layer and deconvolutional layers. Our deep fusion model has advantages of efficiency and robustness, yet demonstrates state-of-art fusion quality. We explore different parameter settings to achieve trade-offs between performance and speed. Moreover, the experiment results on our training dataset show that our network can achieve good performance with subjective visual perception and objective assessment metrics.

• 정보보호학회논문지
• /
• 제11권6호
• /
• pp.15-26
• /
• 2001

복잡한 암호학적 연산 없이 인간의 시각만으로 비밀정보를 직접 복원할 수 있는 시각암호는 영상형태의 비밀 정보를 n개의 랜덤한 영상(슬라이드)으로 분산시킬 때, 화소가 확장되면서 영상의 크기가 커지고 휘도가 떨어지는 문제점이 있다. 따라서 화장 화소의 수를 줄이고 휘도를 개선시키는 연구가 요구되고 있다. 본 논문에서는 n개의 슬라이드 중 k개를 겹치면 비밀정보를 복원할 수 있는 (k, n) 시각암호론 위하여 누적행렬에 따라 기저행렬을 생성하는 새로운 구성법을 제안한다. k가 홀수일 때 그 구성이 완전하며, k가 짝수일 때는 복수의 휘도를 허용함으로서 특별한 쌍의 최대 휘도를 높일 수 있는 방식이다. 제안 방식은 기존방식 중에서 최량의 휘도를 달성하는 Droste방식에 비하여 간단한 구성이면서 평균 휘도가 개선됨을 보인다. 또한, 일반 접근구조를 위한 기저행렬의 구성이 가능함을 보인다.

• International Journal of Computer Science & Network Security
• /
• 제23권3호
• /
• pp.177-186
• /
• 2023

Hyperspectral imaging technology is one of the most efficient and fast-growing technologies in recent years. Hyperspectral image (HSI) comprises contiguous spectral bands for every pixel that is used to detect the object with significant accuracy and details. HSI contains high dimensionality of spectral information which is not easy to classify every pixel. To confront the problem, we propose a novel RGB channel Assimilation for classification methods. The color features are extracted by using chromaticity computation. Additionally, this work discusses the classification of hyperspectral image based on Domain Transform Interpolated Convolution Filter (DTICF) and 3D-CNN with Bi-directional-Long Short Term Memory (Bi-LSTM). There are three steps for the proposed techniques: First, HSI data is converted to RGB images with spatial features. Before using the DTICF, the RGB images of HSI and patch of the input image from raw HSI are integrated. Afterward, the pair features of spectral and spatial are excerpted using DTICF from integrated HSI. Those obtained spatial and spectral features are finally given into the designed 3D-CNN with Bi-LSTM framework. In the second step, the excerpted color features are classified by 2D-CNN. The probabilistic classification map of 3D-CNN-Bi-LSTM, and 2D-CNN are fused. In the last step, additionally, Markov Random Field (MRF) is utilized for improving the fused probabilistic classification map efficiently. Based on the experimental results, two different hyperspectral images prove that novel RGB channel assimilation of DTICF-3D-CNN-Bi-LSTM approach is more important and provides good classification results compared to other classification approaches.

• 한국정밀공학회지
• /
• 제26권6호
• /
• pp.68-73
• /
• 2009

One of the traditional optical methods to monitor a tool is a CCD sensor-based vision system which captures an aspect of the tool in real time. In the case using the CCD sensor, specific lens-modules are necessary to monitor the tool with higher resolution than its pixel size, and a microprocessor is required to attain desired data from captured images. Thus theses additional devices make the entire measurement system complex. Another method is to use a pair of an optical source and a detector per measuring axis. Since the method is based on the intensity modulation, the structure of the measurement system is simper than the CCD sensor-based vision system. However, in the case measuring the three dimensional position of the tool, it is difficult to apply to micro machine-tools because there may not be space to integrate three pairs of an optical source and a detector. In this paper, in order to develop a tool-origin measurement system which is employed in micro machine-tools, the improved method to measure a tool origin in x, y and z axes is introduced. The method is based on the intensity modulation and employs one pair of an optical source radiating divergent beams and a quadrant photodiode to detect a three dimensional position of the tool. This paper presents the measurement models of the proposed tool-origin sensor. The models were verified experimentally The verification results show that the proposed method is possible and the induced models are available for design.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.629-632
• /
• 2007

While conventional interferometric SAR (InSAR) technique is an excellent tool for displacement observation, it is only sensitive to one-dimensional deformation along the satellite's line-of-sight (LOS). Recently, a multiple aperture interferogram (MAI) technique has been developed to overcome this drawback. This method successfully extracted along-track displacements from InSAR data, based on split-beam InSAR processing, to create forward- and backward- looking interferograms, and was superior to along-track displacements derived by pixel-offset algorithm. This method is useful to measure along-track displacements. However, it does not only decrease the coherence of MAI because three co-registration and resampling procedures are required for producing MAI, but also is confined to a suitable interferometric pair of SAR images having zero Doppler centroid. In this paper, we propose an efficient and robust method to generate MAI from interferometric pair having non-zero Doppler centroid. The proposed method efficiently improves the coherence of MAI, because the co-registration of forward- and backward- single look complex (SLC) images is carried out by time shift property of Fourier transform without resampling procedure. It also successfully removes azimuth flat earth and topographic phases caused by the effect of non-zero Doppler centroid. We tested the proposed method using ERS images of the Mw 7.1 1999 California, Hector Mine Earthquake. The result shows that the proposed method improved the coherence of MAI and generalized MAI processing algorithm.

• 한국정보전자통신기술학회논문지
• /
• 제13권1호
• /
• pp.58-63
• /
• 2020

본 논문은 스테레오 카메라를 이용한 모바일 로봇의 위치 추정 정확도 향상을 위한 방법을 제안한다. 스테레오 카메라로 획득한 스테레오 이미지로부터 위치 정보를 복원하기 위해서는 왼쪽 영상의 각 픽셀에 대응하는 대응점을 오른쪽 영상에서 찾아야 한다. 일반적으로 에피폴라 라인 위의 점들과 픽셀 유사도를 연산하여 대응점을 찾는 방법이 있다. 하지만 모든 에피폴라 라인 위의 점들을 다 탐색해야한다는 단점이 있고, 픽셀 값에 의해서만 유사도가 계산된다는 단점이 있다. 이를 보완하기 위해 본 논문에서는 좌/우 영상의 특징점을 추출 및 매칭하여 대응하는 점들이 같은 y축 상에 있을 경우, x좌표 값의 차를 구함으로 대응점 탐색방법을 간략하게 구현하였다. 또한 매칭이 되지 않아 소실되는 점들의 정보는 기존 알고리즘을 통해 대응점을 구함으로 특징점 수를 최대한 보존하고자 하였다. 특징점 및 대응점의 좌표를 통해 복원된 특징점의 3D 좌표를 기반으로 모바일 로봇의 위치를 보정하였다. 실험 결과, 제안하는 방법을 통해 좌표 보정을 위한 특징점 수를 증가시켰고, 특징점 추출만 수행한 경우보다 모바일 로봇의 위치도 보정 가능함을 확인하였다.

• 치과방사선
• /
• 제27권2호
• /
• pp.83-90
• /
• 1997

This study was performed to demonstrate the effect of linear or nonlinear contrast enhancement on subtraction images. Three different textures were radiograped on dental film. The first radiograph was taken without the presence of an object. the second, which showed trabucular bone, was taken of the molar area of a human. the third radiograph was taken of the coronal part of molars. Each film was digitized into a 1312 x 1024 pixel x 8 bit depth matrix by means of a Nikon 35 mm film scanner(LS-3510AF, Japan) with fixed gain and internal dark current correction to maintain constant illumination. The scanner was interfaced to a Macintosh Le ill computer(Apple Computer, Charlotte, N.C) This resulted in three pairs of images, including different textures-plain, bone and enamel. Digital regular, linearly and nonlinearly enhanced subtraction was performed. Computer software was ,used to simulate lesions in the shape of a 2D-Gaussian curve on each of a pair of images. The each subtraction images were presented in a random sequence to two groups of 10 observers(students and dentists). ROC analysis was used to compare observer performance. The following results were obtained ; 1. All of LCE subtraction, equalized subtraction and regular subtraction images of plain texture were diagnosed the best by far. 2. The data revealed a siginificant LCE effect in both the student group and the expert group. 3. Clinical expertise was a helphul factor for the observers in this study.