• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.6
• /
• pp.464-470
• /
• 2016

In this paper, we propose an improved face detection algorithm and determination method for drowsiness status of driver from the opening and closing frequency of the detected eye. For this purpose, face, eyes, nose, and mouth are detected based on conventional Viola-Jones face detection algorithm and spatial correlation of face. Here the spatial correlation of face is performed by DFP(Detect Face Part) based on seven characteristics. The experimental results on Caltect face image database revealed that the detection rates of noise particularly showed the improved performance of 13.78% in comparison to that of the previous Viola-Jones algorithm. Furthermore, we analyze the driver's drowsiness determination cumulative value of the eye closed state as a function of time based on SVM (Support Vector Machine) and PERCLOS(Percentage Closure of Eyes). The experimental results confirmed the usefulness of the proposed method by obtaining a driver's drowsiness determination rate of 93.28%.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.6
• /
• pp.70-78
• /
• 2009

In this paper, we propose a novel method for eye detection using two texture filters considering textural and structural characteristics of eye regions. The human eyes have two characteristics: 1) the eyes are horizontally long and 2) the pupas are of circular shapes. By considering these two characteristics of human eyes, two texture filters are utilized for the eye detection. One is Gabor filter for detecting eye shapes in horizontal direction. The other is ART descriptor for detecting pupils of circular shape. In order to effectively detect eye regions, the proposed method consists of four steps. The first step is to extract facial regions using AdaBoost method. The second step is to normalize the illumination by considering local information. The third step is to estimate candidate regions for eyes, by merging the results from two texture filters. The final step is to locate exact eye regions by using geometric information of the face. As experimental results, the performance of the proposed method has been improved by 2.9~4.4%, compared to the existing methods.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.4
• /
• pp.266-270
• /
• 2016

In this paper, we propose a technique of drowsiness detection using machine vision. The drowsiness of vehicle driver is often the primary cause of motor vehicle accidents. Therefore, the checking of eye images for detecting drowsiness status of driver is critical for preventing these accidents. In our suggested method, we analyze the changes of histogram and edge of eye region images which are acquired using CCD camera. We developed a drowsiness detection system using the histogram and edge change information. The experimental results show that our proposed method enhances the accuracy of detecting drowsiness nearly to 98%, and can be used for preventing vehicle accidents due to the drowsiness of drivers.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.8
• /
• pp.27-34
• /
• 2014

In this paper, we propose a pupil detection method using hybrid projection function and rank order filter. To reduce error to detect eyebrows as pupil, eyebrows are detected using hybrid projection function in face region and eye region is set to not include the eyebrows. In the eye region, potential pupil candidates are detected using rank order filter and then the positions of pupil candidates are corrected. The pupil candidates are grouped into pairs based on geometric constraints. A similarity measure is obtained for two eye of each pair using template matching, we select a pair with the smallest similarity measure as final two pupils. The experiments have been performed for 700 images of the BioID face database. The pupil detection rate is 92.4% and the proposed method improves about 21.5% over the existing method..

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.955-956
• /
• 2008

This paper presents a new method for illumination normalization in eye detection. Based on the retinex image formation model, we employ the discrete wavelet transform to remove the lighting effect in face image data. The final result based on the proposed method shows the better performance in detecting eyes compared with previous work.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.1
• /
• pp.41-49
• /
• 2022

This paper proposes a novel lane detection algorithm based on inverse perspective transformation and machine learning in lightweight embedded system. The inverse perspective transformation method is presented for obtaining a bird's-eye view of the scene from a perspective image to remove perspective effects. This method requires only the internal and external parameters of the camera without a homography matrix with 8 degrees of freedom (DoF) that maps the points in one image to the corresponding points in the other image. To improve the accuracy and speed of lane detection in complex road environments, machine learning algorithm that has passed the first classifier is used. Before using machine learning, we apply a meaningful first classifier to the lane detection to improve the detection speed. The first classifier is applied in the bird's-eye view image to determine lane regions. A lane region passed the first classifier is detected more accurately through machine learning. The system has been tested through the driving video of the vehicle in embedded system. The experimental results show that the proposed method works well in various road environments and meet the real-time requirements. As a result, its lane detection speed is about 3.85 times faster than edge-based lane detection, and its detection accuracy is better than edge-based lane detection.

• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.748-757
• /
• 2021

In this paper, we propose a gaze estimation network in which eye landmark position detection and gaze direction vector estimation are integrated into one deep learning network. The proposed network uses the Stacked Hourglass Network as a backbone structure and is largely composed of three parts: a landmark detector, a feature map extractor, and a gaze direction estimator. The landmark detector estimates the coordinates of 50 eye landmarks, and the feature map extractor generates a feature map of the eye image for estimating the gaze direction. And the gaze direction estimator estimates the final gaze direction vector by combining each output result. The proposed network was trained using virtual synthetic eye images and landmark coordinate data generated through the UnityEyes dataset, and the MPIIGaze dataset consisting of real human eye images was used for performance evaluation. Through the experiment, the gaze estimation error showed a performance of 3.9, and the estimation speed of the network was 42 FPS (Frames per second).

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.9
• /
• pp.643-650
• /
• 2013

In this paper, we propose a novel method for enhancing the detection speed and rate by reducing the computation in Hough Circle Transform on real-time iris detection of smartphone camera image. First of all, we find a face and eyes from input image to detect iris and normalize the iris region into fixed size to prevent variation of size for iris region according to distance from camera lens. Moreover, we carry out histogram equalization to get regular image in bright and dark illumination from smartphone and calculate minimal iris range that contains iris with the distance between corner of the left eye and corner of the right eye on the image. Subsequently, we can minimize the computation of iris detection by applying Hough Circle Transform on the range including the iris only. The experiment is carried out in two case with bright and dark illumination. Our proposed method represents that detection speed is 40% faster and detection rate is 14% better than existing methods.

• Proceedings of the IEEK Conference
• /
• 2000.11d
• /
• pp.25-28
• /
• 2000

Gaze detection is to find out the position on a monitor screen where a user is looking at, using the computer vision processing. This System can help the handicapped to use a computer, substitute a touch screen which is expensive, and navigate the virtual reality. There are basically two main types of the study of gaze detection. The first is to find out the location by face movement, and the second is by eye movement. In the gaze detection by eye movement, we find out the position with special devices, or the methode of image processing. In this paper, we detect not the iris but the pupil from the image captured by Head-Mounted Camera with infra-red light, and accurately locate the position where a user looking at by A(fine Transform.

• International Journal of Contents
• /
• v.2 no.3
• /
• pp.27-32
• /
• 2006

We present an effective algorithm for automatic tracing of retinal vessel structure and vascular landmark extraction of bifurcations and ending points. In this paper we deal with vascular patterns from RGB images for personal identification. Vessel tracing algorithms are of interest in a variety of biometric and medical application such as personal identification, biometrics, and ophthalmic disorders like vessel change detection. However eye surface vasculature tracing in RGB images has many problems which are subject to improper illumination, glare, fade-out, shadow and artifacts arising from reflection, refraction, and dispersion. The proposed algorithm on vascular tracing employs multi-stage processing of ten-layers as followings: Image Acquisition, Image Enhancement by gray scale retinal image enhancement, reducing background artifact and illuminations and removing interlacing minute characteristics of vessels, Vascular Structure Extraction by connecting broken vessels, extracting vascular structure using eight directional information, and extracting retinal vascular structure, and Vascular Landmark Extraction by extracting bifurcations and ending points. The results of automatic retinal vessel extraction using jive different thresholds applied 34 eye images are presented. The results of vasculature tracing algorithm shows that the suggested algorithm can obtain not only robust and accurate vessel tracing but also vascular landmarks according to thresholds.