An Iris Localization Algorithm based on Morphological Processing

Kun Yu,Zeyu Xu,Lixin Xu 보안공학연구지원센터 2015 International Journal of Security and Its Applicat Vol.9 No.3

To improve the speed of iris localization, an iris localization algorithm based on the morphological processing is proposed with fast speed. Firstly, pupil area is segmented from eye image by thresholding, to remove eyelash noise and other noises from binaryzation pupil area by morphological open operation. Then, a series of structure element of radius increasing is used to make morphological erode operation on pupil area to localize roughly the inner boundary of the iris. Finally, calculus operator is employed to accurately localize the inner and outer iris boundary. 108 iris images from CASIA (Version 1.0) iris database are used to do iris localization experiments. The localization accurate rate of the proposed algorithm, calculus operator and hough transform is 97.2%, 90.3% and 92.1% respectively. Experiment results have showed that the proposed algorithm has a high performance on speed and precision with strong robustness to the different quality iris images.

The effect of cavity wall property on the shear bond strength test using iris method

Kim, Dong-Hwan,Bae, Ji-Hyun,Cho, Byeong-Hoon,Lee, In-Bog,Baek, Seung-Ho,Ryu, Hyun-Mi,Son, Ho-Hyun,Um, Chung-Moon,Kwon, Hyuck-Choon 大韓齒科保存學會 2004 Restorative Dentistry & Endodontics Vol.29 No.2

목적 : 본 연구에서는 '전단접착강도 시험법에서 cohesive failure를 줄일 수 있는 것으로 소개된 metal iris를 사용하면, 실제의 1급 와동에서보다 복합 레진과 와동벽의 결합이 없어서 C-factor 적게 작용하고 계면에 발생하는 수축응력 이 감소됨으로써, 임상에서보다 높은 결합력 값이 보고될 것이다.' 라는 가설을 검증하기 위하여 dentin iris를 사용하여 전단접착강도를 측정하였다. 방법 : 64개의 대구치를 4군으로 구분하여 metal iris와 dentin iris 군으로 구분하고, 그 각각을 ONE-STEP과 ALL-BOND 2의 두 군으로 나누었다. bonding agent를 적용하고, iris를 고정한 후, 복합 레진을 충전하여 시편을 완성하였다 이 때 dentin iris의 경우 내면에도 bonding agent를 적용하여 와동벽과의 결합이 발생하게 하였다. 전단접착강도는 24시간 후 측정하였고, 파절의 양상은 주사전자현미경과 입체광학현미경을 이용하여 결정하였다. 결과 : 전단접착강도 측정법에서 iris법을 이용함으로써 cohesive failure를 줄일 수 있다. 전단접착강도 측정법은 adhesive 두께가 얇은 경우에 와동벽의 영향을 받는다. Objectives: In the unique metal iris method, the developing interfacial gap at the cavity floor resulting from the cavity wall property during polymerizing composite resin might affect the nominal shear bond strength values. The aim of this study is to evaluate that the iris method reduces the cohesive failure in the substrates and the cavity wall property effects on the shear bond strength tests using iris method. Materials and Methods: The occlusal dentin of 64 extracted human molars were randomly divided into 4 groups to simulate two different levels of cavity wall property (metal and dentin iris) and two different materials (ONE-STEP® and ALL-BOND® 2) for each wall property. After positioning the iris on the dentin surface, composite resin was packed and light-cured. After 24 hours the shear bond strength was measured at a crosshead speed of 0.5 mm/min. Fracture analysis was performed using a microscope and SEM. The data was analyzed statistically by a two-way ANOVA and t-test. Results: The shear bond strength with metal iris was significant higher than those with dentin iris (p = 0.034). Using ONE-STEP®, the shear bond strength with metal iris was significant higher than those with dentin iris (p = 0.005), but not in ALL-BOND® 2 (p = 0.774), The incidence of cohesive failure was very lower than other shear bond strength tests that did not use iris method. Conclusions: The iris method may significantly reduce the cohesive failures in the substrates. According to the bonding agent systems, the shear bond strength was affected by the cavity wall property.

Dual Source CT에서의 IRIS(lterative Reconstruction of Image Space) 적용에 따른 화질연구와 영상진단의 유용성

김인우(In Woo Kim),유흥준(Heung Joon Yoo),추상덕(Sang Duck Choo) 대한CT영상기술학회 2011 대한CT영상기술학회지 Vol.13 No.2

목적 가장 최근에는 영상의 질 저하 없이 환자들이 선량을 줄이 방법들을 연구개발 했으며 그 결과 영상을 생산하는 게 가능해졌다. Dual Source CT를 이용한 흉부검사 CT 영상의 IRIS적용에 따른 화질연구와 영상진단의 유용성에 대해 알아보고자 한다. 대상 및 방법 CT검사에는 DSCT(Somatom definition, Siemens, Germany)를 사용하였고, 흉부 팬텀검사와 AAPM 팬텀검사는 본원에서 사용되고 있는 Dual Source Chest Protocol 조건인 120kVp, 100 mA(A-tube 50 mA, B-tube 50mA) Slice thickness는 5mm, Acq 64*0.6mm), Rotation time 0.5 sec, DE Composition 0.5 로 동일하게 적용하여 선량을 낮춰 가며 세번 스캔하였다. 팬텀 Study는 AAPM 팬텀을 측정하여 선량별로 노이즈 및 균일도와 저 대조도 분해능, 공간분해능과 직선성을 평가하여 비교 분석하였다. Lung Chest Phantom study는 스캔한 영상을 가지고 None IRIS와 IRIS영상의 노이즈를 비교 분석하였다. 결과 AAPM Phantom study에서는 노이즈와 균일도가 None IRIS와 IRIS영상이 노이즈감소 균일도는 문제점이 없었다. 대조도 분해능실험에서 IRIS를 적용한 영상은 HU값이 유의한 차이만 보일 정도로 변화가 없었다. Lung Chest Phantom study에서 Dual Source 영상에서 IRIS를 적용한 영상의 Noise(SD) 값을 Kernel 별로 각각 감소된 값을 평균값으로 계산되었을 때 R0I1(Muscle)과 ROI 2(Lung) 부위의 B30f은 2.9, B50은 5.9, B70 23.8 정도의 뚜렷한 노이즈 감소를 보였고, 같은 방법으로 A-tube를 계산했을 때 B30f는 3.6 B50f은 6.6, B70f은 23.1 정도의 감소를 보였다. A-tube의 영상이 Dual Source 영상보다 평균적으로 조금 더 감소하였다. 반면 ROI 3(Bone) 부위는 B70f 영상만 제외하고 B30f, B50f은 오히려 Noise가 각각 3.3, 0.7 증가된 것을 알 수 있었다. 결론 소프트프로그램인 IRIS의 사용은 선량을 줄여 CT촬영을 하여도 질 저하 없이 영상적 진단적가치가 있다. IRIS영상은 CT영상 재구성을 하는데 있어서 영상의 질 저하 없이 선량을 감소할 수 있는 유용한 소프트프로그램이다. IRIS을 통한 선량의 감소는 CT검사에서 나타날 수 있는 잠재적 방사선 피폭에 따른 위해를 감소시킬 수 있는 중요한 지표가 될 것이다. I. Purpose Recently, CT soft programs like IRIS that reduce the amount of exposure radiation for patients have been developed. In this study, the purpose is to figure out the utility of image diagnosis and the research of image quality of cardiac(thoracic) CT program, IRIS, which uses dual source CT(DSCT). II. Meterial and Methods DSCT(Somatom definition, Siemens, Erlangen, Gemmy) was used for CT exam, and dual source chest protocol conditions of Asan Medical Center such as 120 kVp, 100 mA(A-tube 50 mA, B-tube 50 mA), slice thickness 5 mm, acq 64*0.6 mm), rotation time 0.5 sec, DE composition 0.5 were used for AAPM and cardiac phantom exam. Also, these AAPM and cardiac phantom exam repeated three times with reducing an amount of radiation in the same exposure conditions. The phantom study evaluated noise, uniformity, low contrast resolution, partial resolution, and linearity in each different exporsure amount after AAPM phantom measurement. III. Result As a result, there was no difference of noise decrease and uniformity between none IRIS and IRIS image in the phantom study, however, low contrast resolution is better in IRIS image. In the dual source image, when decreased measures of IRIS image noise(SD) each kernel is average, the result clearly showed noise decrease such as B30f-2.9, B50f-5.9, and B70f-23.8. In addition, the measures of A-tube were B30f-3.6. B50f-6.6, B70f-23.1 in the same method of measurement, and the image is better in average than Dual source image. On the other hand, noise of ROI 3(Bone) is rather higher in B30f-3.3, B50f-0.7 except the B70f image. IV. Conclusions In conclusion, CT soft program, IRIS, is helpful to reduce image noise and to obtain high quality image without falling off in image quality even though amount of exposure radiation decreases. Through use of IRIS, patient can have less amount of radiation, and it has value to increase image diagnosis.

FRED-Net: Fully residual encoder–decoder network for accurate iris segmentation

Arsalan, Muhammad,Kim, Dong Seop,Lee, Min Beom,Owais, Muhammad,Park, Kang Ryoung Elsevier 2019 expert systems with applications Vol.122 No.-

<P><B>Abstract</B></P> <P>Iris recognition is now developed enough to recognize a person from a distance. The process of iris segmentation plays a vital role in maintaining the accuracy of the iris-based recognition systems by limiting the errors at the current stage. However, its performance is affected by non-ideal situations created by environmental light noise and user non-cooperation. The existing local feature-based segmentation methods are unable to find the true iris boundary in these non-ideal situations, and the error created at the segmentation stage traverses to all the subsequent stages, which results in reduced accuracy and reliability. In addition, it is necessary to segment the true iris boundary without the extra cost of denoising as preprocessing. To overcome these challenging issues during iris segmentation, a deep learning-based fully residual encoder–decoder network (FRED-Net) is proposed to determine the true iris region with the flow of high-frequency information from the preceding layers via residual skip connection.</P> <P>The main four impacts and significances of this study are as follows. First, FRED-Net is an end-to-end semantic segmentation network that does not use conventional image processing schemes, and does not have a preprocessing overhead. It is a standalone network in which eyelid, eyelash, and glint detections are not required to obtain the true iris boundary. Second, the proposed FRED-Net is the final resultant structure of a step-by-step development, and in each step, a new complete variant network is created for semantic segmentation considering the detailed descriptions of the networks. Third, FRED-Net uses the residual connectivity between convolutional layers by the residual shortcut for both encoder and decoder, which enables a high-frequency component to flow through the network and achieve higher accuracy with few layers. Fourth, the performance of the proposed FRED-Net is tested with five different iris datasets under visible and NIR light environments, and two general road scene segmentation datasets. To achieve fair comparisons with other studies, our trained FRED-Net models, along with the algorithms, are made publicly available through our website (Dongguk FRED-Net Model with Algorithm. accessed on 16 May 2018).</P> <P>The experiments include two datasets: Noisy Iris Challenge Evaluation – Part II (NICE-II) selected from the UBIRIS.v2 database and Mobile Iris Challenge Evaluation (MICHE-I), for the visible light environment and three datasets: Institute of Automation, Chinese Academy of Sciences (CASIA) v4.0 interval, v4.0 distance, and IIT Delhi v1.0, for the near-infrared (NIR) light environment. Moreover, to evaluate the performance of the proposed network in general segmentation, experiments with two famous road scene segmentation datasets: Cambridge-driving Labeled Video Database (CamVid) and Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago (KITTI), are included. The experimental results showed the optimum performance of the proposed FRED-Net on the above-mentioned seven datasets of iris and general road scene segmentation.</P> <P><B>Hightlights</B></P> <P> <UL> <LI> Proposed FRED-Net is an end-to-end semantic segmentation network for iris and road scene. </LI> <LI> FRED-Net is a standalone network where eyelid, eyelash, and glint detections are not required. </LI> <LI> FRED-Net is the result of step-by-step development, whose step is a complete variant network. </LI> <LI> FRED-Net uses the residual connectivity for both encoder and decoder. </LI> <LI> Our trained FRED-Net models, along with the algorithms, are made publicly available. </LI> </UL> </P>

독립 성분 분석 방법을 이용한 홍채 특징 추출

노승인,배광혁,박강령,김재희 대한전자공학회 2003 電子工學會論文誌-SP (Signal processing) Vol.40 No.6

기존에 홍채 특징 추출을 위해 가장 많이 사용하는 방법인 직교 이차원 Gabor 웨이블릿의 경우, 2개 이상의 기저 함수들을 다양한 홍채 위치에 적용시켜서 얻어진 256바이트의 홍채 코드를 이용하여 홍채 인식을 수행한다. Gabor 웨이블릿은 홍채 패턴 특성이 반영되지 않은 기저 함수들을 많은 홍채 텍스쳐 위치에 적용함으로써, 생성된 홍채 코드들 사이에 상호 의존성이 높은 불필요한 코드들이 존재하게 되며, 결과적으로 전체 홍채 코드의 크기가 너무 커진다는 문제점이 있다. 이러한 문제점을 해결하기 위해 본 논문에서는 독립 성분 분석에 의한 새로운 홍채 특징 추출 및 홍채 인식 방법을 제안한다. 제안된 독립 성분 분석 방법은 홍채 텍스쳐 자체로부터의 학습을 통하여 최적의 기저 벡터들을 얻을 수 있기 때문에, 홍채 코드의 크기가 작으면 저도 홍채 패턴의 특성을 가장 잘 반영하는 홍채 특징들을 추출할 수 있다. 또한 본 논문에서는 독립 성분 분석에 의한 홍채 특징 추출 및 홍채인식 성능을 보다 개선하기 위하여, 독립 성분 기저 벡터를 재구성하는 방법과 기저 벡터의 집합을 두 가지 이상으로 적용하는 방법을 제안한다. 개선된 독립 성분 분석은 Gabor 웨이블릿 방법과 성능을 비교하였으며, 인식 오류율은 유사한 결과를 나타내면서도 홍채 코드 크기는 4배 이상 감소되는 뛰어난 성능을 나타냈다. In a conventional method based on quadrature 2D Gator wavelets to extract iris features, the iris recognition is performed by a 256-byte iris code, which is computed by applying the Gabor wavelets to a given area of the iris. However, there is a code redundancy because the iris code is generated by basis functions without considering the characteristics of the iris texture. Therefore, the size of the iris code is increased unnecessarily. In this paper, we propose a new feature extraction algorithm based on the ICA (Independent Component Analysis) for a compact iris code. We implemented the ICA to generate optimal basis functions which could represent iris signals efficiently. In practice the coefficients of the ICA expansions are used as feature vectors. Then iris feature vectors are encoded into the iris code for storing and comparing an individual's iris patterns. Additionally, we introduce two methods to enhance the recognition performance of the ICA. The first is to reorganize the ICA bases and the second is to use a different ICA bases set. Experimental results show that our proposed method has a similar EER (Equal Error Rate) as a conventional method based on the Gator wavelets, and the iris code size of our proposed methods is four times smaller than that of the Gabor wavelets.

PET/CT 검사 시 IRIS (Iterative Reconstruction in Image Space) 적용에 따른 CT 피폭선량 감소와 PET SUV 비교 연구

도용호,송호준,이형진,이홍재,김진의,Do, Yong Ho,Song, Ho Jun,Lee, Hyung Jin,Lee, Hong Jae,Kim, Jin Eui 대한핵의학기술학회 2012 핵의학 기술 Vol.16 No.2

Siemens사의 CT 선량 감소 소프트웨어인 IRIS의 적용을 통하여 CT 선량 감소 시 노이즈 감소 효과와 해상력의 보존 그리고 ACCT에 IRIS 각 kernel의 적용 시 SUV 변화를 확인하는데 목적을 두었다. Biograph mCT 40 slice 스캐너를 이용하여 AAPM CT performance phantom, Anthropomorphic chest phantom을 관전압 120 kVp로 고정하고 100-10 mAs까지 15%감소하여 스캔 후 FBP, IRIS 각 kernel을 적용하여 재구성 하여 영상의 노이즈, 해상력, 영상 평가를 시행하였다. NEMA IEC body phantom을 이용하여 55.5 MBq를 background에 주입하고 열소와 배후 방사의 비를 8:1이 되도록 모형을 제작하였다. 120 kVp, 50 mAs 조건으로 1분, 2분, 3분, 4분 스캔하여 영상을 획득한 후 ACCT에 IRIS 각 kernel을 적용하여 기존 FBP 방식을 적용한 SUV와의 평가를 시행하였다. IRIS의 적용 시 기존 FBP 방식에 비하여 45% 선량을 감소하였음에도 불구하고 해상력 저하 없는 노이즈 감소 효과가 확인 되었으며 SUV 평가 실험에서 IRIS의 I70f kernel을 제외하고는 기존 FBP 방식을 통하여 획득된 SUV와 유의한 차이가 나타나지 않았다. 본 연구를 통하여 IRIS 적용 시 기존 FBP 방식에 비하여 CT 피폭선량 감소와 해상력 저하 없는 노이즈 감소 효과를 입증하였으며 IRIS kernel의 적절한 적용을 통하여 PET/CT 검사 시 환자 피폭선량 감소는 물론 FBP 방식에 비하여 우수한 영상의 획득이 가능할 것이라 사료된다. Purpose : Presently, hardwares and softwares for reducing radiation exposure are continually developed for PET/CT examination. Purpose of this study is to evaluate effectiveness of reducing radiation exposure dose of CT and SUV changes of PET when applied each kernel to ACCT (Attenuation Correction Computed Tomography) according to adopted IRIS (Iterative Reconstruction in Image Space) software. Materials and Methods : Biograph mCT (Siemens, Germany) was used as a PET/CT scanner. Using AAPM CT performance phantom, from standard (120 kVp, 100 mAs), 7 scans were conducted by reducing 15 mAs each. After image reconstruction by FBP (Filtered Back Projection) and IRIS, noise and spatial resolution were evaluated. The same method was applied to anthropomorphic chest phantom and acquired images were compared. NEMA IEC body phantom was used for SUV evaluation. Injected dose rate for hot sphere (hot) and background cylinder (BKG) were 1:8. CT dose condition (120 kVp, 50 mAs) was the same for each scan and PET scan durations were 1, 2, 3 and 4min. After scanning, each kernel of IRIS was applied to ACCT. And PET images were reconstructed by ACCT adopted IRIS for comparing SUV changes. Results : AAPM phantom test for noise evaluation, SD for FBP 100 mAs, IRIS 55 mAs were 8.8 and 8.9. FBP 85 mAs, IRIS 40 mAs were 9.5 and 9.7. FBP 70 mAs, IRIS 25 mAs were 11.9 and 11.1. Above mAs condition for FBP and IRIS, SD showed similar values. And for spatial resolution test, there was no significant difference. For chest phantom test, when applied the same mAs and kernel to both of FBP and IRIS, every applied kernels showed reduced noise. Lower mAs and higher kernel value showed higher noise reduction. There was no considerable difference only except for I70 very sharp kernel for SUV comparison using NEMA IEC body phantom. Conclusion : In this study, low mAs (55 mAs) applied IRIS and standard mAs (100 mAs) applied FBP showed similar noise. And only except for I70 kernel, there was no significant SUV changes. It is possible to reduce needless radiation exposure and acquire better image quality than FBP's through applying appropriate kernel of IRIS to PET/CT.

자가 진단을 위한 스마트폰 적용 LED 홍채 렌즈 연구

서경득(Kyung Deuk Seo),박교식(Kyo Shik Park),김병직(Byung Jick Kim),정국영(Guk Young Jung) 안전문화포럼 2022 안전문화연구 Vol.- No.19

디지털 헬스 서비스는 단순 건강관리 및 보조 수단을 넘어 질병 모니터링 등으로 고도화되는 경향을 보이고 있다. 당뇨, 순환계 등 특정 질병 관련 앱 이용률은 매년 급증하고 있다. 특히 홍채는 뇌와 신경계 조직에 연결되어 홍채 상에 나타난 모든 변화로부터 연관된 조직의 질병 상태를 진단할 수 있다. 선행 연구에서 홍채 안경 카메라 모듈을 개발하였지만 USB 통신방식을 이용하여 영상을 획득하는 방식으로 사용자 편의성에 한계가 있었다. 또한 스마트폰으로 홍채 촬영 시 불투명한 홍채 이미지로 질병을 판독할 경우 질병이 없다는 결과로 환자 질환을 놓칠 수 있어 선명한 홍채 이미지 획득이 중요하다. 이에 따라 본 논문에서는 고화질 홍채 이미지 Capture로 환자의 안전성 확보와 더불어 소형으로 손쉽게 들고 다니며 디자인도 고려한 홍채인식 렌즈 개발을 목표로 한다. 본 연구에서 선명한 홍채 인식을 위해 LED 홍채 렌즈를 설계 구현하였다. 개발된 LED 홍채 렌즈가 선명한 홍채 인식을 할 수 있는지 검증이 필요하다. 측정은 두 가지 방법으로 분류되는데, 스마트폰을 통한 홍채 선명도와 Test Tool을 통한 홍채 선명도 및 선명한 홍채 이미지 확보를 위한 촬영 시도 횟수가 되겠다. Test Tool의 개발언어는 Python이며 홍채의 자율신경환 검출을 위해 Average Square Shrinking 알고리즘을 적용하였다. 홍채 검증 시 CASIA(중국의 생체연구소)에서 제공하는 홍채 데이터 셋을 기준 Data로 활용하였다. 테스트 결과, 기존의 홍채질병 진단 앱은 홍채 선명도가 12% 미만으로 이것만으로는 질병 진단에 필요한 이미지 확보가 어려웠으나, 스마트폰에 LED 홍채 렌즈를 장착 후 홍채를 촬영한 결과 질병 진단에 필요한 홍채 선명도 91%를 보였다. 또한 홍채인식 소요 횟수도 종전의 방법으로는 8번의 시도가 필요했으나 본 렌즈 활용 시 1번으로 선명한 홍채를 촬영할 수 있었다. 본 연구를 통해서 LED 홍채 렌즈를 개발하여 홍채 이미지를 검증한 결과, 질병 진단 수준의 선명한 홍채 이미지를 확보할 수 있었다. 선명한 홍채는 진단 오류를 감소시켜 환자 안전에 충분히 기여할 수 있으리라 본다. 자가 진단을 위한 모바일 건강 앱에 대한 관심은 많이 있다. 그러나 실제로 자가 진단에 실효성이 있는 것은 찾기 힘들다. 본 연구를 통해 개발된 LED 홍채 렌즈 적용 후 주기적으로 정확한 홍채 건강 상태를 확인해 간다면 질병 예방에 실질적인 도움이 될 것으로 판단된다. Digital health services tend to go beyond simple health management and auxiliary means to advanced disease monitoring. The use of apps related to particular diseases such as diabetes and the circulatory system is a large increasing every year. In particular, there is connected to the brain and nervous system tissues so it is possible to diagnose the disease state of the related tissue from all the changes in the iris image. Although an iris glasses camera module was developed in the previous study, there was a limit in user convenience in the method of acquiring images using the USB communication method. In addition, if the disease is read with an opaque iris image when taking an iris photograph with a smartphone, the patient’s disease may be missed as a result of no disease, so it is important to obtain a clear iris image. This research proposed an iris recognition lens implementation of a small and can be easily carried and designed considering the safety of patients with high-definition iris image capture. In this study, an LED iris lens was designed and manufactured can iris recognition to show the crown of the autonomic nervous system. It is necessary to verify whether the developed LED iris lens can perform to show the crown of the autonomic nervous system. Measurements are classfied in two ways iris clarity through smartphones, iris clarity through Test Tool, and the number of attempts to secure a clear iris image. The development lange of the Test Tool is Python, and the Average Square Shrinking algorithm was applied to detect autonomic neuropathy in the iris. When verifying the iris, the iris data set provided by CASIA(China’s Biological Research Institute)was used as reference data. As a result of the test, The conventional app for iris recognition can obtain at most 12% of clarity which is not enough to diagnosis the diseases while using the LED iris lens on the smartphone gives 91% of the iris brightness. Additionally, the number of trials for iris recognition was only once while the conventional method needs at least 8 times to get a clear iris image. As a result of verifying the iris image by developing an LED iris lens through this study, it was possible to secure a clear iris image at the level of disease diagnosis. A clear iris reduces diagnostic errors and contributes sufficiently to patient safety. There is a lot of interest in mobile health apps for self-diagnosis. However, it is difficult to find useful App. for self-diagnosis. After applying the LED iris lens developed through this study, it is judged that it will be of practical help to disease prevention if the health status of the iris is checked periodically.

CT를 이용한 관상동맥 검사에서 관상동맥 중재시술을 시행한 환자의 스텐트내 재협착 평가 시 IRIS적용의 유용성에 관한 연구

이상현(Sang Hyeon Lee),김기정(Ki Jeong Kim),김상건(Sang Gun Kim),임근교(Keun Kyo Lim),김순배(Sun Bae Kim) 대한CT영상기술학회 2012 대한CT영상기술학회지 Vol.14 No.1

목적 CT를 이용한 CTCA에서 스텐트 내 재협착이 있는 환자를 대상으로 기존의 sent image와 이에 IRIS를 적용한 image의 비교를 통해 IRIS 적용의 유용성에 대하여 알아본다. 대상 및 방법 본 연구는 본원에 내원하여 CT coronary angiography(CTCA)와 Coronary angiography(CAG)를 모두 시행한 환자 중 그 차이가 일주일 이내이고, In-stent restenosis(ISR)질환을 확진받은 환자를 대상으로 시행하였다. 나이, 성별, 체질량지수, 스탠트의 종류, 시술 혈관별로 구분하고 기존의 Filtered Back Projection 기법만 적용된 kernel과 IRIS 기법을 적용한 Kernel을 이용해 최적의 kernel 값을 알아보고, IRIS적용후의 image가 기존보다 유의하게 좋아졌는지를 알아본다. 결과 영상의학과 전문의 2명, 전공의 2명, 방사선사 2명에게 blind test를 실시하였고, 각 영상의 노이즈와 스텐트의 내경을 측정하였다. IRIS를 적용하기 전인 B-kernel에서는 B-46 kernel이 2.91점으로 가장 좋은 평가를 받았고, IRIS를 적용한 후의 I-kernel에서는 3.06점으로 I-50 kernel이 좋은 평가를 받았다. 전체적인 알고리즘 중에서는 I-50이 가장 좋은 평가를 받았고, 그 다음으로 I-46, B-46의 순서였다. B-kernel군보다 IRIS를 적용한 I-kernel군의 Noise가 감소한 것을 확인 할 수 있었으며, I-26에서 내경이 가장 작게 측정되었고, B-70에서 내경이 가장 크게 측정되었다 결론 IRIS기법의 적용이 고식적인 관상동맥 질환의 평가에서 유용하다는 결과는 이미 보고되어 있다. 본 연구를 통해 PCI Stent 시술을 시행한 환자의 ISR평가에 있어 공간 분해능을 유지해주면서 노이즈 값을 줄여주는 IRIS기법이 유용하며, 그 중에서도 I-50 Kernel이 최적의 알고리즘임을 알 수 있었다. I. Purpose In-stent restenosis using CT in patients at CA coronary angiography existing stent image and IRIS through the comparison of applying the image with usability II. Materials and methods This research from In-stent restenosis (ISR) disease in patients who were confirmed. It’ s CT coronary angiography (CTCA) and Coronary angiography (CAG) who underwent the difference is less than a week. Filtered Back Projection Applied existing kernel and IRIS technique using Kernel learn the value of the optimal kernel used by Age, gender, body mass index (BMI), stent type, and blood vessel surgery, and IRIS after applying a crush on the image to see find out. III. Results Blind test was conducted on 2 of radiology medical specialist, 2 of residents and 2 of Radiological technologists, each of the image noise and measure the in-stent was inside diameter. Before used IRIS the B-kernel 2.91 points in the B46-kernel received the best rating, After used IRIS I-kernel 3.06 points in the I50-kernel received the best rating, The overall algorithm is I50 received the best rating. After I46, B46 was behind. Apply the I-kernel was less noise by B-kernel, I26 was smallest measured the inside diameter and B70 was largest measured the inside diameter IV. Conclusion IRIS techniques applied in useful in the evaluation of palliative coronary artery disease, the results have already been reported. This research PCI Stent surgery patients underwent with ISR assessment spatial resolution while reducing noise values, and the IRIS technique is useful, Among them, I50-Kernel could see that the optimal algorithm.

멀티미디어 처리 : 홍채영역에서의 홍채정보 보존율 향상을 위한 새로운 속눈썹 제거 방법

김성훈 ( Seong Hoon Kim ),한기태 ( Gi Tae Han ) 한국정보처리학회 2014 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.3 No.10

The iris recognition is a biometrics technology to extract and code an unique iris feature from human eye image. Also, it includes the technology to compare with other`s various iris stored in the system. On the other hand, eyelashes in iris image are a external factor to affect to recognition rate of iris. If eyelashes are not removed exactly from iris area, there are two false recognitions that recognize eyelashes to iris features or iris features to eyelashes. Eventually, these false recognitions bring out a lot of loss in iris informations. In this paper, in order to solve that problems, we removed eyelashes by gabor filter that using for analysis of frequency feature and improve preservation rate of iris informations. By novel method to extract various features on iris area using angle, frequency, and gaussian parameter on gabor filter that is one of the filters for analysing frequency feature for an image, we could remove accurately eyelashes with various lengths and shapes. As the result, proposed method represents that improve about 4% than previous methods using GMM or histogram analysis in iris preservation rate.

Real-Time Image Restoration for Iris Recognition Systems

Byung Jun Kang,Kang Ryoung Park Institute of Electrical and Electronics Engineers 2007 IEEE Transactions on Cybernetics Vol.37 No.6

<P>In the field of biometrics, it has been reported that iris recognition techniques have shown high levels of accuracy because unique patterns of the human iris, which has very many degrees of freedom, are used. However, because conventional iris cameras have small depth-of-field (DOF) areas, input iris images can easily be blurred, which can lead to lower recognition performance, since iris patterns are transformed by the blurring caused by optical defocusing. To overcome these problems, an autofocusing camera can be used. However, this inevitably increases the cost, size, and complexity of the system. Therefore, we propose a new real-time iris image-restoration method, which can increase the camera's DOF without requiring any additional hardware. This paper presents five novelties as compared to previous works: (1) by excluding eyelash and eyelid regions, it is possible to obtain more accurate focus scores from input iris images; (2) the parameter of the point spread function (PSF) can be estimated in terms of camera optics and measured focus scores; therefore, parameter estimation is more accurate than it has been in previous research; (3) because the PSF parameter can be obtained by using a predetermined equation, iris image restoration can be done in real-time; (4) by using a constrained least square (CLS) restoration filter that considers noise, performance can be greatly enhanced; and (5) restoration accuracy can also be enhanced by estimating the weight value of the noise-regularization term of the CLS filter according to the amount of image blurring. Experimental results showed that iris recognition errors when using the proposed restoration method were greatly reduced as compared to those results achieved without restoration or those achieved using previous iris-restoration methods.</P>