• Title/Summary/Keyword: 검출기

Search Result 4,898, Processing Time 0.031 seconds

A Real-Time Viola-Jones Object Detector using PSO with Tracking Method (Tracking 방식의 PSO를 이용한 실시간 Viola-Jones 물체 검출기)

  • Park, Byeong-Ju;Lee, Jae-Heung
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2014.11a
    • /
    • pp.917-920
    • /
    • 2014
  • 본 논문에서는 SWO 방식의 물체 검출기를 개선하여 비디오 환경에 적합하며 실시간 처리가 가능한 Tracking 방식의 PSO 물체 검출기를 제안한다. PSO 방식 스캔은 각각의 입자들이 전역 최적 값으로 수렴하기 때문에 다중 검출에는 적지 않은데, 본 논문에서는 다중 물체를 검출하고 관리할 수 있도록 Tracking 개념을 적용하였다. 제안하는 방법을 적용하면 검출기의 오검출률을 줄이고 안정적인 검출 결과를 얻을 수 있으며 속도가 향상되어 실시간 처리가 가능하다. 논문에서 제안한 알고리즘을 적용해 본 결과 기존의 Viola-Jones 얼굴 검출기와 비교하여 검출률은 동일하면서 속도가 최대 21배 향상되었음을 확인하였다.

Impulse Noise Removal Using Noise Detector and Total Variation Optimization (잡음 검출기와 총변량 최적화를 이용한 영상의 임펄스 잡음제거)

  • Lee Im-Geun
    • The Journal of the Korea Contents Association
    • /
    • v.6 no.4
    • /
    • pp.11-18
    • /
    • 2006
  • A new algorithm for removing salt and pepper impulse noise in image using impulse noise detector and total variation optimization is presented. The proposed two types of noise detectors which are based on the adaptive median filter, can detect impulse noise with high accuracy while reducing the probability of detecting image details as impulses. And the detectors maintain its performance independent of noise density. For removing impulses, total variation optimization is applied only to those detected noise candidate to reduces unnecessary computation. The proposed approach successfully remove impulse noise while preserving image details.

  • PDF

Hybrid Iterative Detection Algorithm for MIMO Systems (다중 안테나 시스템을 위한 Hybrid Iterative 검출 기법)

  • Kim, Sang-Heon;Shin, Myeong-Cheol;Kim, Kyeong-Yeon;Lee, Chung-Yong
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.44 no.4 s.316
    • /
    • pp.117-122
    • /
    • 2007
  • For multiple antenna systems, we consider the hybrid iterative detection of the maximum a posteriori probability(MAP) detection and the linear detection such as the minimum-mean-square-error(MMSE) filtering with soft cancelation. We devise methods to obtain both the lower complexity of the linear detection and the superior performance of the MAP detection. Using the a prior probability of the coded bit which is extrinsic of the outer decoder, we compute the threshold of grouping and determine the detection scheme symbol by symbol. Through the simulation results, it is shown that the proposed receiver obtains the superior performance to the MMSE detector and the lower complexity than the MAP detector.

Chest Wall Thickness Measurement of the LLNL Phantom for Ce Detectors (Ce 검출기를위한 LLNL 팬텀의가슴벽두께측정)

  • Lee, Tae-Young;Lee, Jong-Il;Chang, Si-Young
    • Journal of Radiation Protection and Research
    • /
    • v.25 no.1
    • /
    • pp.3-9
    • /
    • 2000
  • The Korea Atomic Energy Research Institute acquired the Lawrence Livermore National Laboratory phantom for calibration of germanium detectors used for in vivo measurement of radionuclides deposited in human lungs. The manufacturer inscribed concentric circles as a phoswich detector positioning guides on the phantom's torso plate and its overlay plates, and provided the effective thickness of the chest wall for each plate measured at locations over the circles. However, since the germanium detectors are of different sizes, the areas considered for phoswich detectors were no. longer applicable for the locations of the germanium detectors on the phantom. Therefore, we re-evaluated the effective thickness of the phantom to determine if the manufacturer' s data are valid for germanium detectors in use for in vivo lung counting or if new values must be implemented. Differences no more than 3% in effective thickness were found between the germanium detector regions to be used at the Korea Atomic Energy Research Institute and the phoswich detector regions prescribed by the manufacturer.

  • PDF

Voice Activity Detection Based on SVM Classifier Using Likelihood Ratio Feature Vector (우도비 특징 벡터를 이용한 SVM 기반의 음성 검출기)

  • Jo, Q-Haing;Kang, Sang-Ki;Chang, Joon-Hyuk
    • The Journal of the Acoustical Society of Korea
    • /
    • v.26 no.8
    • /
    • pp.397-402
    • /
    • 2007
  • In this paper, we apply a support vector machine(SVM) that incorporates an optimized nonlinear decision rule over different sets of feature vectors to improve the performance of statistical model-based voice activity detection(VAD). Conventional method performs VAD through setting up statistical models for each case of speech absence and presence assumption and comparing the geometric mean of the likelihood ratio (LR) for the individual frequency band extracted from input signal with the given threshold. We propose a novel VAD technique based on SVM by treating the LRs computed in each frequency bin as the elements of feature vector to minimize classification error probability instead of the conventional decision rule using geometric mean. As a result of experiments, the performance of SVM-based VAD using the proposed feature has shown better results compared with those of reported VADs in various noise environments.

Image System Using Dual Energy Detector (이중 에너지 검출기를 이용한 영상 시스템)

  • Yeo, Hwa-Yeon
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.11 no.9
    • /
    • pp.3517-3523
    • /
    • 2010
  • Single exposure dual X-ray imaging can be used to separate soft and dense-material images for medical and industrial applications. This study keep focusing baggage inspection system(BIS) specifically. New detector modules for single exposure dual X-ray imaging are consisted of low energy detector (LED) and high energy detector (HED). First, the optimized thickness of copper filter coupled HED to separate low energy and high energy was simulated by the given X-ray energy (140 kVp, 1 mA) using Monte Carlo simulation codes, MCNPX. So as a result of simulation, the copper filter thickness is 0.7 mm. For the design of PIN photodiode, ATLAS device simulation tool was used. 16 channels PIN photodiode of 1.5 mm ${\times}$ 3.2 mm for Dual X-ray imaging detector was fabricated in the process of ETRI. And its dark current and quantum efficiency, terminal capacitance were measured. It was proven that the Lanex Fast B coupled HED were a sufficient candidate to replace the CsI(Tl) commerced in dual X-ray system, since these give a strong signal, overcoming system noise. Finally dual X-ray image was acquired through correction of the LED X-ray Image and the HED X-ray Image.

Feature Detection using Geometric Mean of Eigenvalues of Gradient Matrix (그레디언트 행렬 고유치의 기하 평균을 이용한 특징점 검출)

  • Ye, Chul-Soo
    • Korean Journal of Remote Sensing
    • /
    • v.30 no.6
    • /
    • pp.769-776
    • /
    • 2014
  • It is necessary to detect the feature points existing simultaneously in both images and then find the corresponding relationship between the detected feature points. We propose a new feature detector based on geometric mean of two eigenvalues of gradient matrix which is able to measure the change of pixel intensities. The corner response of the proposed detector is proportional to the geometric mean and also the difference of two eigenvalues in the case of same geometric mean. We analyzed the localization error of the feature detection using aerial image and artificial image with various types of corners. The localization error of the proposed detector was smaller than that of the typical corner detector, Harris detector.

Development of Dual Energy Radiation Detector (이중 에너지 방사선 검출기 개발)

  • Yeo, Hwa-Yeon
    • Journal of the Korean Society of Radiology
    • /
    • v.4 no.3
    • /
    • pp.5-11
    • /
    • 2010
  • In this paper, we are suggested development of dual-mode detector for dual-energy digital radiography. Design of dual-energy radiography module for commercial BIS (Baggage Inspection System) is used in the spectrum of the X-ray generator and detector for dual-mode features and radiological characteristics were analyzed. BIS suggestl on the image detector module being used to target X-ray tube to simulate X-ray spectrum and simulated spectrum to offer through the new radiographic characteristics of the detector modules were investigated. Using X-ray experiments with an increase in the thickness of the copper filter low energy detector (LED) and high-energy detector (HED) as the difference between the output signal increases. HED, especially in the size of the output signal decreases with increasing thickness of the copper filter was found.

Voice Activity Detection based on DBN using the Likelihood Ratio (우도비를 이용한 DBN 기반의 음성 검출기)

  • Kim, S.K.;Lee, S.M.
    • Journal of rehabilitation welfare engineering & assistive technology
    • /
    • v.8 no.3
    • /
    • pp.145-150
    • /
    • 2014
  • In this paper, we propose a novel scheme to improve the performance of a voice activity detection(VAD) which is based on the deep belief networks(DBN) with the likelihood ratio(LR). The proposed algorithm applies the DBN learning method which is trained in order to minimize the probability of detection error instead of the conventional decision rule using geometric mean. Experimental results show that the proposed algorithm yields better results compared to the conventional VAD algorithm in various noise environments.

  • PDF

A Study on the Degradation Detector for Transmission Line (송전 선로용 열화 검출기 연구)

  • Park, Geon-Ho
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2015.07a
    • /
    • pp.297-298
    • /
    • 2015
  • 본 연구에서는 기존 방식인 인력에 의한 송전 선로 점검 방식을 대체할 수 있는 로봇 기술이 적용된 열화 검출기의 제작을 위하여 송전 선로의 부식 메커니즘과 물성 변화에 대해 고찰하였다. 이를 통해 송전 선로의 열화에 의한 기계적 결함과 전기적 특성변화의 확인을 위한 과학적인 접근 방법을 제시하여 송전 선로의 열화를 포함한 외부 이상을 검출할 수 있는 열화 검출기에 대한 연구를 수행하였다.

  • PDF