• Journal of Digital Convergence
• /
• v.17 no.2
• /
• pp.313-318
• /
• 2019

The purpose of this study is to investigate whether there is a difference in the incidence of the black circle border of iris(skin disease) according to the iris constitution. Iris was taken for 100 adults living in Seoul. Iris was photographed using the iris camera DV-2H, a blue focus development product. Statistical significance was tested by correlation analysis, and the occurrence of black circle border of iris was low negative correlation(p<0.01). As mentioned above, we know that the occurrence of black circle border of iris differs according to the iris constitution, and by using it actively, it will help health promotion about skin. There is a need to study the changes of iris in the cause of skin disease by using a blood test to analyze the cause of the skin disease in the future.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.3
• /
• pp.371-377
• /
• 2020

Currently used iris cameras are expensive and have many limitations in their use. Existing iris cameras are inconvenient in interworking with newly developed software, and light reflections generated during iris photography are inadequate for medical use. Therefore, it is impossible to utilize the existing camera to take an image by yourself. In this paper, the iris camera is newly constructed so that the iris can be photographed by ourselves and the area of interest can be seen well. Anyone can easily wear glasses-type iris cameras to acquire images using IoT devices, and the acquired images are linked to the iris analysis program and used to read genetic weak parts. The proposed iris camera module automatically provides light reflection, shake, and accurate focus when capturing images, increasing the accuracy of image analysis to 91.49%. In addition, we have proved through experiments that one image processing time is fast as 0.007ms due to accurate image input.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.267-270
• /
• 2001

홍채인식 시스템에서 입력된 영상으로부터 정합(matching)에 사용될 홍채 영역을 추출해 내는 과정은 필수적인 과정으로 빠른 처리 속도와 정확성을 요구한다. 기존의 원형검출기나 허프(Hough) 변환을 이용한 방법 등은 홍채의 바깥쪽과 안쪽 경계를 비교적 정확하게 검출해내는 장점이 있으나 탐색영역이 커서 수행시 간이 매우 많이 걸리는 단점이 있다. 따라서 본 논문에서는 이진화와 형태학적 연산(morphology)을 이용하는 새로운 탐색 영역 단축 방법을 제안한다. 제안한 방법은 기존의 홍채영역 검출 방법에 적용할 경우 수행 시간을 효율적으로 단축시킬 수 있다. 검출된 영역에 대해서 주성분 분석법(principal component analysis, PCA)을 이용해 매칭을 수행한 결과 약 95%의 인식율을 나타내었다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.2
• /
• pp.113-118
• /
• 2011

This paper has analyzed recognizing performance depending on the size of iris codes extracting by iris recognition algorithm using scale-space filtering. The iris images were created through pre-processing, the features were extracted by scale-space filtering, and the codes of 16 sizes were generated. The generated code's performance was compared for each code to calculate FAR and FRR by matching method utilizing Hamming distance. Every code had little overlapping portion between same person and other persons group so that the proposed algorithm's superiority was proved, and the performance of iris codes was analyzed for each size focused on convenience to use when implementing in realization. In addition, the iris codes suitable to iris recognition system that is high-reliable and is able to reduce user's inconvenience due to mis-rejection has been presented considering for commercialization.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.438-456
• /
• 2010

Iris recognition uses a unique iris pattern of user to identify person. In order to enhance the performance of iris recognition, it is reported that the diameter of iris region should be greater than 200 pixels in the captured iris image. So, the previous iris system used zoom lens camera, which can increase the size and cost of system. To overcome these problems, we propose a new method of enhancing the accuracy of iris recognition on low-resolution iris images which are captured without a zoom lens. This research is novel in the following two ways compared to previous works. First, this research is the first one to analyze the performance degradation of iris recognition according to the decrease of the image resolution by excluding other factors such as image blurring and the occlusion of eyelid and eyelash. Second, in order to restore a high-resolution iris image from single low-resolution one, we propose a new method based on multiple multi-layered perceptrons (MLPs) which are trained according to the edge direction of iris patterns. From that, the accuracy of iris recognition with the restored images was much enhanced. Experimental results showed that when the iris images down-sampled by 6% compared to the original image were restored into the high resolution ones by using the proposed method, the EER of iris recognition was reduced as much as 0.133% (1.485% - 1.352%) in comparison with that by using bi-linear interpolation

• Journal of Acupuncture Research
• /
• v.21 no.2
• /
• pp.89-101
• /
• 2004

홍채학은 대체의학의 한 분야로서 홍채 침착의 불규칙성을 주시함으로써 의학적 상태를 진단한다. 홍채학적 분류에 의한 체질은 가족력을 보이고 있으며 이는 홍채체질의 유전성을 의미한다. 강력한 면역조절자이며 전 염증성 사이토카인인 종양괴사인자(tumor necrosis factor-a, TNF-${\alpha}$)는 많은 병리적 과정에서 중요한 역할을 한다. 따라서 본 연구자는 고혈압환자에서 홍채체질과 TNF-${\alpha}$ 유전자 다형성과의 관련성을 조사하였다. 87명의 고혈압 환자와 79명의 정상인을 홍채체질에 따라 분류하였으며 이들의 TNF-${\alpha}$ 유전자형을 분석하였다. 결과적으로 정상인에 비하여 TNF-${\alpha}$ GA 이형접합체의 빈도가 고혈압 환자군에서 감소하였다. 이 같은 결과는 TNF-${\alpha}$ 다형성이 고혈압에 대한 저항성과 관련 있음을 의미한다. 또한 고혈압환자에서 콜레스테롤 침착체질과 심신 결합조직 허약 체질은 42.5%로서 정상인 16.5%에 비하여 현저하게 증가하였다 (P<0.001). GG TNF-${\alpha}$ 유전자형을 갖고 있는 군에서 심신 결합조직 허약체질과 콜레스테롤 침착체질의 빈도는 정상인보다 환자에서 유의하게 높았다(P<0.001). 본 연구에서 저자는 홍채체질과 고혈압사이의 관련성을 발견함과 동시에 TNF-${\alpha}$ 유전자 다형성과 고혈압, 그리고 홍채 체질과의 관련성을 최초로 입증하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.753-754
• /
• 2016

스트레스는 매일 살아가면서 사소한 일부터 큰 충격을 받는 삶의 주요한 사건까지 다양한 요인으로 부터 온다. 이는 어느 한 시기에만 나타나는 것이 아니라 인간의 전 생애에 거쳐 나타나므로 지속적으로 스트레스를 관리할 수 있는 연구가 필요하다. 이에 본 논문은 홍채의 형태, 균열, 색깔, 고리, 주름 등의 특징들을 분석하여 환자의 병을 진단하는 홍채진단을 이용하여 스트레스 지수를 측정하는 시스템을 개발하였다. 개발한 시스템은 홍채의 특징인 스트레스 고리를 검출하고, 스트레스 설문지의 결과와 함께 분석하여 안드로이드 어플리케이션을 통해 사용자에게 스트레스 정도를 제공한다. 제안한 시스템은 사용자가 언제 어디서나 쉽게 현재 자신이 느끼고 있는 스트레스 정도를 알 수 있고 이에 상응하는 예측되는 질병에 대해 예방하여 조기 진단 및 질병 예방의 하나의 방법으로 사용할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.847-850
• /
• 2005

본 논문에서는 저차원의 홍채 특징을 추출하기 위한 방법으로 텍스쳐 분석 기법에서 사용되는 Gabor 필터, Laws 필터 및 Wavelet 변환 및 추가적인 방법으로 Direct LDA(DLDA)을 사용한 홍채 특징추출 방법을 비교 분석하였다. 실험을 통해 일반적인 평균과 분산을 이용한 텍스쳐 기반 특징 추출 방법의 홍채인식 적용 가능성과, 텍스쳐 기반 특징 추출 방법에 의해 얻어진 1차 특징추출에 대해 추가 과정을 통해 높은 식별력과 낮은 차원을 가지는 특징을 얻을 수 있음을 증명한다.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1147-1155
• /
• 2005

This paper deals with Iris recognition as one of biometric techniques which is applied to identify a person using his/her behavior or congenital characteristics. The Iris of a human eye has a texture that is unique and time invariant for each individual. First, we obtain the feature vector from the 2D Iris pattern having a property of size invariant and using the fuzzy LDA which is further through four types of 2D Gabor wavelet. At the recognition process, we compute the similarity measure based on the correlation values. Here, since we use four different matching values obtained from four different directional Gabor wavelet and select the maximum value, it is possible to minimize the recognition error rate. To show the usefulness of the proposed algorithm, we applied it to a biometric database consisting of 300 Iris Patterns extracted from 50 subjects and finally got more higher than $90\%$ recognition rate.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.421-428
• /
• 2004

There are three texture descriptors in MPEG-7 : Homogeneous Texture, Edge Histogram and Texture Browsing. In this paper, a comparative analysis is presented on the capability of MPEG-7 texture descriptors for iris recognition as part of an MPEG-7 application using descriptors. Through the experiments of comparing the clustering efficiency and error distribution of the descriptors using 560 iris images, their discriminating capabilities for different iris groups are analyzed. The results show that Homogenous Texture descriptor is the best discriminator among three descriptors to recognize the iris pattern. However, compared with the conventional iris recognition methods, it needs more efforts to enhance the results.