• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.7
• /
• pp.291-296
• /
• 2015

In this paper, we propose a new confidence measure using pixel selection for eye detection and design a hybrid eye detector. For this, we produce sub-images by applying a pixel selection method to the eye patches and construct the BDA(Biased Discriminant Analysis) feature space for measuring the confidence of the eye detection results. For a hybrid eye detector, we select HFED(Haar-like Feature based Eye Detector) and MFED(MCT Feature based Eye Detector), which are complementary to each other, as basic detectors. For a given image, each basic detector conducts eye detection and the confidence of each result is estimated in the BDA feature space by calculating the distances between the produced eye patches and the mean of positive samples in the training set. Then, the result with higher confidence is adopted as the final eye detection result and is used to the face alignment process for face recognition. The experimental results for various face databases show that the proposed method performs more accurate eye detection and consequently results in better face recognition performance compared with other methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.663-668
• /
• 2003

This paper presents a new observation system which is useful to observe the scene of the remote controlled robot vision. This system is composed of a motionless camera and head motion detector with a motion sensor. The motionless camera has a fish eye lens and is for observing a hemisphere space. The head motion detector has a motion sensor is for defining an arbitrary subspace of the hemisphere space from fish eye lens. Thus processing the angular information from the motion sensor appropriately, the direction of face is estimated. However, since the fisheye image is distorted, it is unclear image. The partial domain of a fish eye image is selected by head motion, and this is converted to perspective image. However, since this conversion enlarges the original image spatially and is based on discrete data, crevice is generated in the converted image. To solve this problem, interpolation based on an intensity of the image is performed for the crevice in the converted image (space problem). This paper provides the experimental results of the proposed observation system with the head motion detector and perspective image conversion using the proposed conversion and interpolation methods, and the adequacy and improving point of the proposed techniques are discussed.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.17 no.6
• /
• pp.79-82
• /
• 2017

In this paper, we proposed the wireless communication system using millimeter-wave envelope detector. The sub-harmonic mixer based on schottky barrier diode was used in the transmitter. The receiver was used millimeter-wave envelope detector. The transmitter was composed of schottky diode sub-harmonic mixer, frequency tripler, and horn antenna. The receiver was composed of horn antenna, millimeter-wave envelope detector, low pass filter, base band amplifier, and limiting amplifier. At 1.485 Gbps and 300 GHz, the eye-diagram showed a very good performance as measured by the error free. Communication distance is reduced compared to the heterodyne receiver, but compact and lightweight is possible.

• Journal of the Ergonomics Society of Korea
• /
• v.4 no.1
• /
• pp.7-10
• /
• 1985

Eye blinking in case of three visual tasks is studied; wall hard-copy and color monitor. The eye blinking is checked by eye-status detector. The data observed are (1) the average number of eye blinking (2) the average time of eye blinking for three minutes in case of all three visual tasks. The results are as follows: (1) The average times (or numbers) of eye blinking are different among three tasks. (2) The average time (or number) of eye blinking of wall is different from hard-copy and color monitor tasks. (3) But the average time (or number) of eye blinking of hard-copy is not different from that of color monitor.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.4
• /
• pp.1-11
• /
• 2008

In this paper, we propose the new eye detection method by using adaboost (adaptive boosting) method. Also, to reduce the false alarm rate which identifies the non-eye region as genuine eye that is the Problems of previous method using conventional adaboost, we proposed the post processing methods which used the cornea specular reflection and determined the optimized ratio of eye detecting box. Based on detected eye region by using adaboost, we performed the double circular edge detector for localizing a pupil and an iris region at the same time. Experimental results showed that the accuracy of eye detection was about 98% and the processing time was less than 1 second in mobile device.

• 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).

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.23 no.1
• /
• pp.101-113
• /
• 1986

In this paper, a real-time pitch detector LPC vocoder as implemented on a high speed digital signal processor, NEC 7720, is described. The pitch detector was based mainly on the SIFT algorithm. The SIFT pitch detector consists primarily of a digital low pass filter, inverse filter, computation of autocorrelation, a peak picker, interpolation, V/UV defcision and a final pitch smoother. In our approach, modification, mainly on the V/UV decision and a final pitch smoother, was made to estimate more accurate pitches. An 16-bit fixed-point aithmatic was employed for all necessary computation and the simulated results were compared with the eye detected pitches obtained from real speech data. The pitch detector occupies 98.8% of the instruction ROM, 37% of the data ROM, and 94% of internal RAM and takes 15.2ms to estimate a pitch when an analysis frame is consisted of 128 sampled speech data. It is observed that the tested results were well agreed with the computer simulation results.

• Journal of the Korea Convergence Society
• /
• v.9 no.8
• /
• pp.1-8
• /
• 2018

In the field of biometric security such as face and iris recognition, it is essential to extract facial features such as eyes and lips. In this paper, we have studied a method of detecting eye and lip region in face image using faster R-CNN. The faster R-CNN is an object detection method using deep running and is well known to have superior performance compared to the conventional feature-based method. In this paper, feature maps are extracted by applying convolution, linear rectification process, and max pooling process to facial images in order. The RPN(region proposal network) is learned using the feature map to detect the region proposal. Then, eye and lip detector are learned by using the region proposal and feature map. In order to examine the performance of the proposed method, we experimented with 800 face images of Korean men and women. We used 480 images for the learning phase and 320 images for the test one. Computer simulation showed that the average precision of eye and lip region detection for 50 epoch cases is 97.7% and 91.0%, respectively.

• Journal of the Korea Safety Management & Science
• /
• v.13 no.2
• /
• pp.91-96
• /
• 2011

The purpose of this study was to minimize of entrance surface dose (ESD) at the eye using high kVp technique in the computed radiography. We used REX-650R (Listem, Korea) general X-ray unit, and external detector with ESD dosimeter of Piranha 657 (RTI Electronics, Sweden). We used head of the whole body phantom. The total 64 images of X-ray anterior-posterior of skull were acquired using the film/screen (F/S) method and the digital of computed radiography method. The three radiology professor of more 10 years of clinical career evaluated a X-rays images in the same space by 5-point scale. The external detector was performed measurement of ESD of three times by same condition on the eye of the head phantom. The good image quality in the F/S method (90 kVp, 2.5 mAs) showed at the minimized ESD of 0.310 ${\pm}$ 0.001 mGy. the good image quality in the computed radiography method (90 kVp, 2.0 mAs) showed at the minimized ESD of 0.180 ${\pm}$ 0.002 mGy (P = 0.002). Finally the radiation dose could reduced about 50% in the computed radiography method more than the F/S method. In addition the eye entrance surface dose using high kVp technique with the computed radiography was reduced 92% more than conventional technique (F/S method).

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.5
• /
• pp.297-304
• /
• 2015

A multilayer gaseous detector has been developed for fast dose-verification measurements of raster-scan-mode therapeutic beams in particle therapy. The detector, which was constructed with eight thin parallel-plate ionization chambers (PPICs) and polymethyl methacrylate (PMMA) absorber plates, is closely tissue-equivalent in a beam's eye view. The gas-electron signals, collected on the strips and pad arrays of each PPIC, were amplified and processed with a continuous charge.integration mode. The detector was tested with 190-MeV raster-scan-mode beams that were provided by the Proton Therapy Facility at Samsung Medical Center, Seoul, South Korea. The detector responses of the PPICs for a 190-MeV raster-scan-mode proton beam agreed well with the dose data, measured using a 2D ionization chamber array (Octavius model, PTW). Furthermore, in this study it was confirmed that the detector simultaneously tracked the doses induced at the PPICs by the fast-oscillating beam, with a scanning speed of 2 m s-1. Thus, it is anticipated that the present detector, composed of thin PPICs and operating in charge.integration mode, will allow medical scientists to perform reliable fast dose-verification measurements for typical dynamic mode therapeutic beams.