• Title/Summary/Keyword: False Region

Search Result 188, Processing Time 0.029 seconds

A Study on Iris Region Localization for imprecisely taken images (부정확하게 획득된 홍채영상에 대한 홍채영역 검출 연구)

  • Hwang, Jae-Won;Park, Dong-Kwon;Park, Kang-Ryoung;Won, Chee-Sun
    • Proceedings of the IEEK Conference
    • /
    • 2008.06a
    • /
    • pp.861-862
    • /
    • 2008
  • This paper presents the results of iris region localization for imprecisely taken iris images in UBIRIS ver2. UBIRIS database consisting of 500 images of 24-bit RGB typed TIFF file. They were captured by conventional digital camera in visible light environment. Experimental result showed that FP(False Positive rate) and FN(False Negative rate) were about 2.2% and 29.1%, respectively.

  • PDF

Improved Fusion Method of Detection Features in SAR ATR System (SAR 자동표적인식 시스템에서의 탐지특징 결합 방법 개선 방안)

  • Cha, Min-Jun;Kim, Hyung-Myung
    • Journal of the Korea Institute of Military Science and Technology
    • /
    • v.13 no.3
    • /
    • pp.461-469
    • /
    • 2010
  • In this paper, we have proposed an improved fusion method of detection features which can enhance the detection probability under the given false alarm rate in the prescreening stage of SAR ATR(Synthetic Aperture Radar Automatic Target Recognition) system. Since the detection features have the positive correlation, the detection performance can be improved if the joint probability distribution of detection features is considered in the fusion process. The detection region is designed as a simple piecewise linear function which can be represented by few parameters. The parameters for the detection region can be derived by training the sample SAR images to maximize the detection probability with the given false alarm rate. Simulation result shows that the detection performance of the proposed method is improved for all combinations of detection features.

The Study of Usefulness of Metal Artifact Reduction Algorithm and Artifacts Caused by Metallic Hip Prosthesis on PET/CT (PET/CT에서의 고관절 삽입물에 의한 인공물과 Metal Artifact Reduction Algorithm의 유용성에 대한 고찰)

  • Park, Min Soo;Ham, Jun Cheol;Cho, Yong In;Kang, Chun Goo;Park, Hoon-Hee;Lim, Han Sang;Lee, Chang Ho
    • The Korean Journal of Nuclear Medicine Technology
    • /
    • v.16 no.2
    • /
    • pp.35-43
    • /
    • 2012
  • Purpose : PET/CT performed CT-based attenuation correction generates the beam hardening artifact by metallic implant. The attenuation correction causes over or underestimate of the area adjacent to metallic hip prosthetic material and change of $^{18}F$-FDG uptake. Also, the image quality and the diagnosability on genitourinary disease are reduced. Therefore, this study will evaluate the usefulness of MAR (Metal Artifact Reduction) algorithm method to improve the image quality on PET/CT. Materials and Methods : PET/CT was performed by fixing hip prosthesis in SPECT/PET phantom. In PET images with and Without MAR algorithm, the Bright streak, Dark streak, Metal region and Background area that appeared on CT were confirmed, and the change of each SUV (standardized uptake value) was analyzed. Also, in 15 patients who underwent total hip arthroplasty, each MAR algorithm and Without MAR algorithm and non attenuation correction was evaluated. Results : In PET image Without MAR algorithm, SUV of Bright streak region was $0.98{\pm}0.48$ g/ml; Dark streak region was $0.88{\pm}0.02$ g/ml; Metal region was $0.24{\pm}0.16$ g/ml, Background area was $0.91{\pm}0.18$ g/ml. In SUV of PET image with MAR algorithm, Bright streak region was $0.88{\pm}0.49$ g/ml, Dark streak region was $0.63{\pm}0.21$ g/ml, Metal region was $0.06{\pm}0.07$ g/ml, Background was $0.90{\pm}0.02$ g/ml. SUV generally decreased when applying MAR algorithm. In PET image Without MAR algorithm, SUVs of Bright region were higher than those measured in the Background, and it was false positive uptake. But, in PET image with MAR algorithm, SUVs of Bright region were similar to the Background, and false positive uptake disappeared. Conclusion : MAR algorithm could reduce an increase of $^{18}F$-FDG uptake due to attenuation correction in the hip surrounding tissue. However, decrease of SUV in Dark streak region should be considered in the future. Therefore, this study propose that the diagnostic accuracy can be improved in genitourinary diseases adjacent to metallic hip prosthesis, if provided PET images with and Without MAR algorithm, and non attenuation correction images at the same time.

  • PDF

UV/IR flame detector using Microprocessor (마이크로프로세서를 사용한 UV/IR 불곶 감지기)

  • 박성진;임병현;임종연;김명원;윤길호
    • Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
    • /
    • 2001.07a
    • /
    • pp.215-218
    • /
    • 2001
  • A flame detector responds either to radiant energy visible to the human eye or outside the range of human vision. Such a detector is sensitive to glowing embers, coals, or flames which radiate energy of sufficient intensity and spectral quality to actuate the alarm. An infra-red detectors can respond to the total IR component of the flame alone or in combination with flame flicker in the frequency range of 5 to 30 Hz. A major problem in the use of infrared detectors receiving total IR radiation is the possible interference of solar radiation in the infrared region. When detectors are located in places shielded from the sun, such as vaults. filtering or shielding the unit from the sun's rays is unnecessary. In this study, we proposed method for redue a false alarm with using filtering & sensor technology for distinguish of causes of raise a false alarm and pure flame.

  • PDF

Preprocessing Technique for Lane Detection Using Image Clustering and HSV Color Model (영상 클러스터링과 HSV 컬러 모델을 이용한 차선 검출 전처리 기법)

  • Choi, Na-Rae;Choi, Sang-Il
    • Journal of Korea Multimedia Society
    • /
    • v.20 no.2
    • /
    • pp.144-152
    • /
    • 2017
  • Among the technologies for implementing autonomous vehicles, advanced driver assistance system is a key technology to support driver's safe driving. In the technology using the vision sensor having a high utility, various preprocessing methods are used prior to feature extraction for lane detection. However, in the existing methods, the unnecessary lane candidates such as cars, lawns, and road separator in the road area are false positive. In addition, there are cases where the lane candidate itself can not be extracted in the area under the overpass, the lane within the dark shadow, the center lane of yellow, and weak lane. In this paper, we propose an efficient preprocessing method using k-means clustering for image division and the HSV color model. When the proposed preprocessing method is applied, the true positive region is maximally maintained during the lane detection and many false positive regions are removed.

INCIDENCE OF SINUS SEPTA AND ACCURACY OF PANORAMIC RADIOGRAPH (상악동 중격의 발생율과 파노라마 방사선 사진의 정확도)

  • Shin, Chang-Hoon;Kim, Hyung-Jin;Hong, Jong-Rak;Yang, Seung-Min
    • Journal of the Korean Association of Oral and Maxillofacial Surgeons
    • /
    • v.33 no.5
    • /
    • pp.504-510
    • /
    • 2007
  • Purpose: The purpose of this study was to determine the incidence of antral septa and the accuracy of panoramic radiograph in identifying maxillary sinus septa. In addition, when panoramic radiograph led to a false diagnosis of more than majority, we analyzed findings of the panoramic radiograph. Patients and methods: This study included 180 patients who were radiographically examined before the surgery was done using both panoramic and computerized tomographic radiographs(CT scan), Samsung Medical Center from April 2003 to March 2006, and examined the incidence of antral septa, the false diagnosis rate of panoramic radiograph, and radiographic characters in case of false diagnosis. Only those bone lamellae were considered as septa that showed a height of at least 3.0mm. It was thus possible to exclude the alveolar recess. One oral and maxillofacial surgeon(OMFS) determined the presence or absence of sinus septa in CT scan, and five OMFS determined the presence or absence of sinus septa in panoramic radiograph. Results: The septa were observed in 81 of 360 sinuses(22.5%). All septa were oriented in a buccopalatal plane. More or less greater prevalence was observed in the second molar region(38.2%) but no predominant location was found. Panoramic radiograph led to false diagnosed septa in 361 of 1800 cases(20.1%). In case of false diagnosis of more than majority, superimposed image on zygomatic process was 44.1%, faint image in the region not related to sinus lifting 26.5%, faint image in the region related to sinus lifting 17.6%, and misconception for superimposed image 11.8% Conclusion: In this study we could get clinico-anatomical information of septum in the maxillary sinus. Compared to CT scan, panoramic radiograph can not clearly differentiate the sinus septa, but we consider that panoramic radiograph may improve its usefulness if we take additional modified panoramic radiograph and clinical exam.

An Improved Method for Detecting Caption in image using DCT-coefficient and Transition-map Analysis (DCT계수와 천이지도 분석을 이용한 개선된 영상 내 자막영역 검출방법)

  • An, Kwon-Jae;Joo, Sung-Il;Kim, Gye-Young;Choi, Hyung-Il
    • Journal of the Korea Society of Computer and Information
    • /
    • v.16 no.4
    • /
    • pp.61-71
    • /
    • 2011
  • In this paper, we proposed the method for detecting text region on image using DCT-coefficient and transition-map analysis. The detecting rate of traditional method for detecting text region using DCT-coefficient analysis is high, but false positive detecting rate also is high and the method using transition-map often reject true text region in step of verification because of sticky threshold. To overcome these problems, we generated PTRmap(Promising Text Region map) through DCT-coefficient analysis and applied PTRmap to method for detecting text region using transition map. As the result, the false positive detecting rate decreased as compared with the method using DCT-coefficient analysis, and the detecting rate increased as compared with the method using transition map.

Real-time Face Detection Method using SVM Classifier (SW 분류기를 이용한 실시간 얼굴 검출 방법)

  • 지형근;이경희;반성범
    • Proceedings of the IEEK Conference
    • /
    • 2003.11a
    • /
    • pp.529-532
    • /
    • 2003
  • In this paper, we describe new method to detect face in real-time. We use color information, edge information, and binary information to detect candidate regions of eyes from input image, and then extract face region using the detected eye pall. We verify both eye candidate regions and face region using Support Vector Machines(SVM). It is possible to perform fast and reliable face detection because we can protect false detection through these verification processes. From the experimental results, we confirmed the proposed algorithm shows very excellent face detection performance.

  • PDF

Mobile Iris Recognition System Based on the Near Infrared Light Illuminator of Long Wavelength and Band Pass Filter and Performance Evaluations (장파장 근적외선 조명 및 밴드 패스 필터 기반 이동형 홍채 인식 시스템 및 성능 평가)

  • Cho, So-Ra;Nam, Gi-Pyo;Jeong, Dae-Sik;Shin, Kwang-Yong;Park, Kang-Ryoung;Shin, Jae-Ho
    • Journal of Korea Multimedia Society
    • /
    • v.14 no.9
    • /
    • pp.1125-1137
    • /
    • 2011
  • Recently, there have been previous research about the iris recognition in mobile device to increase portability, whose accuracy is affected by the quality of iris image. Iris image is affected by illumination environment during the image acquisition. The existing system has high accuracy in indoor environment. However the accuracy is degraded in outdoor environment, because the gray levels of iris patterns in image are changed, and ghost and eyelash shading regions are produced by the sunlight of various wavelengths into iris region. To overcome these problems, we propose new mobile iris camera system which uses the near-infrared (NIR) light illuminator of 850 nm and band pass filter (BPF) of 850 nm. To measure the performance of the proposed system, we compared it to the existing one with the iris images captured in indoor and outdoor sunlight environments in terms of the equal error rates (EER) based on false acceptance rate (FAR) and false rejection rate (FRR). The experimental result showed that the proposed system had the lower EERs than those of previous system by 0.96% (with frontal light in indoors), 4.94% (with frontal light in outdoor), 9.24% (with side light in outdoor), and 7% (with back light in outdoor), respectively.

Adaptive CFAR Algorithm using Two-Dimensional Block Estimation (이차원 블록 추정을 이용한 적응 CFAR 알고리즘)

  • Choi Beyung Gwan;Lee Min Joon;Kim Whan Woo
    • Journal of the Institute of Electronics Engineers of Korea SP
    • /
    • v.42 no.1
    • /
    • pp.101-108
    • /
    • 2005
  • Adaptive constant false alarm rate(CFAR) algorithm is used for good detection probability as well as constant false alarm rate in clutter background. Especially, filtering technique adaptive to spatial variation is necessary for improving detection quality in non stationary clutter environment which has spatial correlation and large magnitude deviation. In this paper, we propose a two-dimensional block interpolation(TBI) adaptive CFAR algorithm that calculates the node estimate in the fred two dimensional region and subsequently determines the final estimate for each resolution cell by two-dimensional interpolation. The proposed method is efficient for filtering abnormal ejection by adopting distribution median in fixed region and also has advantage of reducing required memory space by using estimation method which gets final values after calculating the block node values. Through simulations, we show that the proposed method is superior to the traditional adaptive CFAR algorithms which are transversal or recursive in aspect of the detection performance and required memory space.