• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.597-600
• /
• 2012

본 연구의 목적은 눈 폐쇄 상태 검출 알고리즘을 개발하고, 그것을 바탕으로 모바일 환경의 졸음운전 감지 시스템을 구현하는 것이다. 개발한 알고리즘은 검출된 눈 영역의 이미지를 히스토그램 분석을 통해 실험적으로 얻은 문턱 값으로 이진화 시킨 후 운전자 눈의 폐쇄 상태를 판단한다. 구현한 시스템은 얼굴과 눈 검출이 완료된 상태에서 검출된 눈이 폐쇄 상태인지를 판단한다. 폐쇄 상태인 경우 이상태가 지속되면 시스템은 운전자가 졸음운전 상태임을 감지하고 경고해준다. 자원이 제한된 모바일의 특성상 이미지 처리의 정확성뿐만 아니라 처리속도의 효율성도 중요한데 이 특성에 맞는 알고리즘을 개발하였고, 이를 바탕으로 졸음운전 감지 시스템 구현에 성공하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.508-510
• /
• 2020

2015년도부터 2019년도까지 5년간 고속도로에서 1,079명의 사망자가 발생하였으며, 이중 졸음운전 및 주시 태만이 729명(67.6%)로 가장 많았다. 졸음운전 방지를 위해 휴게소, 졸음쉼터 등 노력하고 있으나 이러한 노력에도 졸음운전으로 인한 사고는 지금까지도 계속해서 발생하고 있다. 본 연구는 이러한 사고를 방지하기 위해 적외선 카메라를 이용한 영상 촬영하여 안면검출 해석과 서비스를 구현하였다. 안면검출을 통한 동공 상태의 여부와 적합한 수면 판단 기준으로 PERCLOS(Percentage of Eye Closure)을 적용하였다. 운전자의 동공의 장축과 단축의 비율이 1 : 0.35 미만 일 때, 운전자가 졸음상태라 판단하고 음성 알람을 통해 졸음방지를 개선할 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.1165-1166
• /
• 2023

본 논문에서는 YOLOPv2 를 기반으로 OpenCV 를 활용한 후처리 과정을 도입하여 차선 검출 성능을 극대화할 수 있는 알고리즘을 제안한다. 주요 단계로는 YOLOPv2 모델을 활용한 차선 인식, Bird's eye view 변환, Sobel 및 Morphology Filter 를 통한 왜곡 보정, Histogram 기반 차선 검출, 그리고 후처리 알고리즘 적용이 있다. 이 기술은 자율 주행 및 도로 정보 활용 분야에 활용 가능할 것으로 기대되며, 차선 검출 정확도를 향상시킬 수 있다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.7
• /
• pp.4516-4521
• /
• 2014

Digital watermarking for digital image authentication and integrity schemes are based on fragile watermarking and can detect any modifications in a watermark embedded image by comparing the embedded watermark with the regenerated watermark. Therefore, the digital watermark for image authentication and integrity should be erased easily when the image is changed by digital image processing, such as scaling or filtering etc. This paper proposes an effective tamper detection scheme for digital images. In the proposed scheme, the original image was divided into many non-overlapping $2{\times}2$ blocks. The digital watermark was divided into two LSB of each block and the image distortion was imperceptible to the human eye. The watermark extraction process can be used to determine if the watermarked image has been tampered. The experimental results successfully revealed the effectiveness of the proposed scheme.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.821-829
• /
• 2004

A face recognition has been used for verifying and authorizing valid users, but its applications have been restricted according to lighting conditions. In order to minimizing the restricted conditions, this paper proposes a new algorithm of detecting the face from the input image obtained under the irregular lighting condition. First, the proposed algorithm extracts an edge difference image from the input image where a skin color and a face contour are disappeared due to the background color or the lighting direction. In the next step, it extracts a face region using the histogram of the edge difference image and the intensity information. Using the intensity information, the face region is divided into the horizontal regions with feasible facial features. The each of horizontal regions is classified as three groups with the facial features(including eye, nose, and mouth) and the facial features are extracted using empirical properties of the facial features. Only when the facial features satisfy their topological rules, the face region is considered as a face. It has been proved by the experiments that the proposed algorithm can detect faces even when the large portion of face contour is lost due to the inadequate lighting condition or the image background color is similar to the skin color.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.10
• /
• pp.429-440
• /
• 2014

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.

• Textile Coloration and Finishing
• /
• v.33 no.2
• /
• pp.49-63
• /
• 2021

In this study, a convenient approach for sensitive, quick and simple detection of hazardous acids was investigated. A series of azo dyes were synthesized and applied as a chemosensor for the acid detection both on fibers and in solution. Various aniline, benzothiazole or isoxazole derivatives were used as diazo component and coupled with N-benzyl-N-ethylaniline or 2,2'-(phenylimino)bis-ethanol to give azo based dyes. The acid sensing phenomenon was observed by naked-eye and detection was further confirmed by UV-Vis spectrophotometer and hue difference(ΔH^*) evaluation. The developed sensors showed a distinct and quick color change from yellow to magenta by addition of trace amounts of the hazardous acids. The absorption maxima was shifted to a longer wavelength by 70 ~ 150nm and hue difference(ΔH^*) was 60 ~ 120°. A cotton fiber coated with Dye 1 exhibited excellent storage stability under various temperature(-30 ~ 43℃) and humidity(30 ~ 80%) conditions without discoloration and fading of the fiber sensors. Also the acid sensing properties were maintained.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.859-864
• /
• 2022

Drowsy driving, one of the biggest causes of traffic accidents every year, is accompanied by various factors. As a general method to check whether or not there is drowsiness, a method of identifying a driver's expression and driving pattern, and a method of analyzing bio-signals are being studied. This paper proposes a driver fatigue detection system using deep learning technology and bio-signal measurement technology. As the first step in the proposed method, deep learning is used to detect the driver's eye shape, yawning presence, and body movement to detect drowsiness. In the second stage, it was designed to increase the accuracy of the system by identifying the driver's fatigue state using the pulse wave signal and body temperature. As a result of the experiment, it was possible to reliably determine the driver's drowsiness and fatigue in real-time images.

• Science of Emotion and Sensibility
• /
• v.15 no.2
• /
• pp.259-268
• /
• 2012

In a P300-based concealed information test (P300 CIT), the result of the test is greatly affected by the value of the probe stimulus. With a probe stimulus of low value, the detection rate decreases. The aim of this study was to determine whether the pupil-based concealed information test (Pupil CIT) could be used in addition to the P300 CIT for the probes of low value. Participants were told to choose one card from a deck of five cards (space 2, 3, 4, 5, 6), Then a P300 CIT and a Pupil CIT for the selected card were administered. P300s were measured at 3 scalp sites (Fz, Cz, and Pz), and the pupil sizes of left and right eyes were recorded. The P300 amplitude measured at Fz, Cz, and Pz was significantly different between the probe and irrelevant stimuli. And, in the Pupil CIT, the pupil size was also different between the two stimuli for both eyes. The detection rates of the P300 CIT were 44% at Fz and Cz sites and 36% at Pz site. And the detection rates of the Pupil CIT were 52% for the left eye and 60% for the right eye. There is a trend that the detection rate of the Pupil CIT was higher than that of the P300 CIT, but the difference didn't reach significance partly because of the relatively small sample size. The correlation between the decision based on the P300 CIT and that based on the Pupil CIT was not significant. As a conclusion, it is recommended to use a Pupil CIT instead of a P300 CIT when the value of the probe is low. And a combination of the measures may be superior to either one of them in detection rate.

• Atmosphere
• /
• v.17 no.2
• /
• pp.125-133
• /
• 2007

Cloud amount calculation algorithm was developed using MTSAT-1R satellite data. The cloud amount is retrieved at 5 km ${\times}$ 5 km over the Korean Peninsula and adjacent sea area. The algorithm consists of three steps that are cloud detection, cloud type classification, and cloud amount calculation. At the first step, dynamic thresholds method was applied for detecting cloud pixels. For using objective thresholds in the algorithm, sensitivity test was performed for TBB and Albedo variation with temporal and spatial change. Detected cloud cover was classified into 3 cloud types (low-level cloud, cirrus or uncertain cloud, and cumulonimbus type high-level cloud) in second step. Finally, cloud amount was calculated by the integration method of the steradian angle of each cloud pixel over $3^{\circ}$ elevation. Calculated cloud amount was compared with measured cloud amount with eye at surface observatory for the validation. Bias, RMSE, and correlation coefficient were 0.4, 1.8, and 0.8, respectively. Validation results indicated that calculated cloud amount was a little higher than measured cloud amount but correlation was considerably high. Since calculated cloud amount has 5km ${\times}$ 5km resolution over Korean Peninsula and adjacent sea area, the satellite-driven cloud amount could show the possibility which overcomes the temporal and spatial limitation of measured cloud amount with eye at surface observatory.