• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.11-13
• /
• 2022

데이터 3 법을 필두로, 기업은 개인정보가 포함된 데이터를 활용하기 위해 비식별 처리가 필요하게 되었다. 기존 방식은, 비정형 텍스트 데이터에서 정규표현식을 통한 개인정보 식별은 데이터의 다양성에 의해 한계가 명확하며, 기존의 Named Entity Recognition(NER) 태스크로 해결하기에는 언어의 중의적 표현과 2 인 대화에서 나타나는 개인정보가 누구의 것인지 판단하지 못한다는 한계가 존재한다. 따라서 우리는 기존의 한계점을 극복하고 개선하기 위해 BERT 언어 모델에 화자 정보를 학습시키고, 하나의 어절에 2 개의 tag 를 labeling 하는 방법을 제안하여 정확한 개인정보 식별을 시도하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.3C
• /
• pp.125-132
• /
• 2005

This paper describes a computer vision system based on active IR illumination for real-time gaze discrimination system. Unlike most of the existing gaze discrimination techniques, which often require assuming a static head to work well and require a cumbersome calibration process for each person, our gaze discrimination system can perform robust and accurate gaze estimation without calibration and under rather significant head movement. This is made possible by a new gaze calibration procedure that identifies the mapping from pupil parameters to screen coordinates using generalized regression neural networks (GRNNs). With GRNNs, the mapping does not have to be an analytical function and head movement is explicitly accounted for by the gaze mapping function. Futhermore, the mapping function can generalize to other individuals not used in the training. To further improve the gaze estimation accuracy, we employ a reclassification scheme that deals with the classes that tend to be misclassified. This leads to a 10% improvement in classification error. The angular gaze accuracy is about 5°horizontally and 8°vertically. The effectiveness of our gaze tracker is demonstrated by experiments that involve gaze-contingent interactive graphic display.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.3 no.1
• /
• pp.38-46
• /
• 2010

This paper describes a computer vision system based on active IR illumination for real-time gaze discrimination system. Unlike most of the existing gaze discrimination techniques, which often require assuming a static head to work well and require a cumbersome calibration process for each person, our gaze discrimination system can perform robust and accurate gaze estimation without calibration and under rather significant head movement. This is made possible by a new gaze calibration procedure that identifies the mapping from pupil parameters to screen coordinates using generalized regression neural networks (GRNNs). With GRNNs, the mapping does not have to be an analytical function and head movement is explicitly accounted for by the gaze mapping function. Furthermore, the mapping function can generalize to other individuals not used in the training. To further improve the gaze estimation accuracy, we employ a reclassification scheme that deals with the classes that tend to be misclassified. This leads to a 10% improvement in classification error. The angular gaze accuracy is about $5^{\circ}$horizontally and $8^{\circ}$vertically. The effectiveness of our gaze tracker is demonstrated by experiments that involve gaze-contingent interactive graphic display.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.2
• /
• pp.322-329
• /
• 2005

This paper describes a computer vision system based on active IR illumination for real-time gaze discrimination system. Unlike most of the existing gaze discrimination techniques, which often require assuming a static head to work well and require a cumbersome calibration process for each person, our gaze discrimination system can perform robust and accurate gaze estimation without calibration and under rather significant head movement. This is made possible by a new gaze calibration procedure that identifies the mapping from pupil parameters to screen coordinates using generalized regression neural networks (GRNNS). With GRNNS, the mapping does not have to be an analytical function and head movement is explicitly accounted for by the gaze mapping function. furthermore, the mapping function can generalize to other individuals not used in the training. To further improve the gaze estimation accuracy, we employ a reclassification scheme that deals with the classes that tend to be misclassified. This leads to a 10$\%$ improvement in classification error. The angular gaze accuracy is about $5^{circ}$horizontally and $8^{circ}$vertically. The effectiveness of our gaze tracker is demonstrated by experiments that involve gaze-contingent interactive graphic display.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.3 no.2
• /
• pp.321-327
• /
• 1999

In this progressed super-impose individual recognition system, the photograph of a skull was caught by CCD-camcoder with the MPEG, and an ante-mortem photograph was read by scanner. These two images were processed and superimposed using horizontal angle and vertical angle of face using the forensic dental medicine theory. The enhancement of super-impose individual recognition by anatomical references was performed on the two superimposed images of the same angle using the facial triangle and histogram analysis scheme.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.268-271
• /
• 2019

최근 인공지능과 빅데이터 등 최첨단 기술이 빠른 속도로 의료 정보시스템에 도입됨에 따라 환자정보를 포함한 민감한 개인정보에 대한 사이버 공격이 급증하고 있다. 다양한 개인정보 비식별화에 대한 표준이 제안되었지만, 데이터의 범주에 따른 기법 적용에 대한 연구가 미비하다. 본 논문에서는 EHR 데이터를 위한 심근경색을 대상으로 하는 원격 의료 시스템을 위한 개인정보들에 대한 민감도를 4단계로 분류하고 이에 따른 비식별화 기법에 대해 제안한다. 본 논문에서 제안한 EHR 데이터에 대한 분류 및 비식별화 기법은 다양한 의료 정보 서비스를 위한 프라이버시 보호에 활용될 수 있다.

• Korean Journal of Cognitive Science
• /
• v.18 no.4
• /
• pp.445-455
• /
• 2007

We present a new biometric identification system based on multi-view features of teeth using principal components analysis(PCA). The multi-view features of teeth consist of the frontal view, the left side view and the right side view. In this paper, we try to stan the foundations of a dental biometrics for secure access in real life environment. We took the pictures of the three views teeth in the experimental environment designed specially and 42 principal components as the features for individual identification were developed. The classification for individual identification based on the nearest neighbor(NN) algorithm is created with the distance between the multi-view teeth and the multi-view teeth rotated. The identification performance after rotating two degree of test data is 95.2% on the left side view teeth and 91.3% on the right side view teeth as the average values.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.47-49
• /
• 2021

According to the revision of the Data 3 Act in 2020, personal information of medical data can be processed anonymously for statistical purposes, research, and public interest record keeping. However, unidentified data can be re-identified using genetic information, credit information, etc., and personal health information can be abused as sensitive information. In this paper, we derive the need for homomorphic encryption to protect the privacy of personal information separated by sensitive information.

• Journal of Korean Ophthalmic Optics Society
• /
• v.18 no.4
• /
• pp.549-554
• /
• 2013

Purpose: To determine the minimal illumination for visual acuity with the decimal vision chart and individual difference with varying contrast and illumination. Methods: Landolt's vision chart with 10 different grade of contrast was made. Minimal illumination was measured for 69 eyes using 100% contrast vision chart. Minimal contrast for identifying the chart was measured in conditions of the minimal illumination and 230 lx, respectively. Results: Minimal illumination was gradually increased with decrease of the chart size. Mean of minimal illumination to identify the 1.0 visual acuity was $74.39{\pm}25.90$ lx with range of 17~107 lx. In conditions of the minimal illumination and 230 lx, the minimal contrast for identifying the chart were gradually increased with decrease of the chart size in both conditions, the those deviation for 69 eyes was also increased. Conclusions: For refractive correction, examiners need to consider the individual difference for identifying the visual chart according to illumination and contrast.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.11a
• /
• pp.745-747
• /
• 2007

무선 주파수를 사용하여 객체를 자동으로 식별하는 전자 태그 기술인 RFID는 최근에 다양한 분야에서 각광을 받고 있다. 논문에서는 RFID의 식별자 기능과 CDMA 기술을 이용한 부재중 방문객 관리 시스템을 개발한다. 시스템은 RFID에 기반하여 부재중 방문객을 식별하고, CDMA를 이용하여 방문객과 피방문객간에 SMS 메시지를 통해서 간접적으로 서로 통신할 수 있게 한다. 시스템은 특징은 방문객과 피방문객이 개인 정보를 노출시키지 않고서 간접적으로 대화를 가능하게 한다는 점이다. 논문에서는 시스템을 설계, 구현하고, 그 실행 예를 보인다.