• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.12A
• /
• pp.2019-2026
• /
• 2001

In this paper, we proposed the car license plate extraction and recognition algorithm using both the dynamical thresholding method and the kohonen algorithm. In general, the areas of car license plate in the car images have distinguishing characteristics, such as the differences in intensity between the areas of characters and the background of the plates, the fixed ratio of width to height of the plates, and the higher dynamical thresholded density rate 7han the other areas, etc. Taking advantage of the characteristics, the thresholded images were created from the original images, and also the density rates were computed. A candidate area was selected, whose density rate was corresponding to the properties of the car license plate obtained from the car license plate. The contour tracking method by utilizing the Kohonen algorithm was applied to extract the specific area which included characters and numbers from an extracted plate area. The characters and numbers of the license place were recognized by using Kohonen algorithm. Kohonen algorithm was very effective o? suppressing noises scattered around the contour. In this study, 80 car images were tested. The result indicate that we proposed is superior in performance.

• 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.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.269-273
• /
• 1999

Combination of mental stress task with noise background is a traditional tool employed in psychophysiology. However, intensity of background noise is a factor affecting both performance on test and psychophysiological responses associated with stress evoked by mental load in noisy environment. In the current study on 7 subjects we analyzed the influence of white noise (WN) intensity (55, 70, and 85 dB[A] ) on psychophysiological responses during word recognition test performed on noise background. There were recorded following physiological variables: electrodermal activity (EDA) , namely, skin conductance level (SCL), skin conductance response (SCR) amplitude (SCR-A), rise time and total number of SCRs (N-SCR); cardiovascular activity, e.g., heart rate (HR), respiratory sinus arrhythmia (RSA) index, pulse transit time (PTT), finger pulse volume (PV), skin temperature (SKT) and respiratory activity, such as respiration rate (RESP-R) and inspiration wane amplitude (RESP-A) during baseline resting state and 40 s long performance on 3 similar Korean word recognition tests with different WN intensity (55, 70, and 85 dB). Electrodermal responses (SCR-A, SCL, N-SCR) demonstrated gradual increment with increased intensity of noise, and this increase of response magnitude with higher intensity of noise was typical also for r skin temperature (phasic SKT decrease) and pulse volume (phasic and tonic PV decrease). However, some cardiovascular and respiratory responses did not exhibit same tendency of gradual increase of reactivity , namely HR, as well as RESP-R and RESP-A showed decrement of response magnitudes. Important finding in terms of cardiovascular reactivity was that 55 and 70dB evoked similar profiles, while 85dB WN resulted in significantly different profile of reactions, suggesting that there exists a threshold level after which intensive auditory stimulation elicits psychophyslological responses pattern of different quality. There are discussed potential autonomic mechanism involved in mediation of observed physiological responses.

• The Journal of Society for e-Business Studies
• /
• v.21 no.4
• /
• pp.29-40
• /
• 2016

Voice User Interface (VUI) is the most familiar and comfortable interface to human. Recently, with the development of cloud and AI technologies VUI has been applied to various products. The aim of this study was to identify the problems of the current VUI and to find the direction of future study by investigating the utilization status and user perception of the VUI of smartphones. A survey was conducted with 163 college students using Google Forms. The results showed that the level of recognition of VUI is high but the rate of usage is very low, and many users feel uncomfortable about the voice recognition rate, reaction speed and operation method. Most of the survey participants tried VUI out of curiosity, but only a small portion of them found it useful to continue to use it. Many participants disliked talking to machines and also did not want others to listen. The study results will guide future research efforts for improving the utilization of VUI.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.12
• /
• pp.59-65
• /
• 2019

Hospital Information System includes a wide range of information in the medical profession, from the overall administrative work of the hospital to the medical work of doctors. In this paper, we proposed a Vision-based Authentication and Registration of Facial Identity in Hospital Information System using OpenCV. By using the proposed security module program a Vision-based Authentication and Registration of Facial Identity, the hospital information system was designed to enhance the security through registration of the face in the hospital personnel and to process the receipt, treatment, and prescription process without any secondary leakage of personal information. The implemented security module program eliminates the need for printing, exposing and recognizing the existing sticker paper tags and wristband type personal information that can be checked by the nurse in the hospital information system. In contrast to the original, the security module program is inputted with ID and password instead to improve privacy and recognition rate.

• Journal of Korea Multimedia Society
• /
• v.16 no.4
• /
• pp.430-443
• /
• 2013

The recognition of current position and road surrounding of car is very important to driver for safe driving. This paper presents the recognition technique of the road traveling environment using position information hiding and viewpoint transform that monitors the information of road furniture and signature and notifies them to driver. The proposed scheme generates the road images into which the position information are hided, from car camera and GPS module and provides the road information to driver through the viewpoint transformation and the road signature detection. The driving tests with camera and GPS module verified that the position information hiding takes about 66.5ms per frame, the detection rate of road signature is about 95.83%, and the road signature detection takes about 227.45ms per frame. Therefore, we know that the proposed scheme can recognize the road traveling environment on the road video with 15 frame rate.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.27 no.2
• /
• pp.305-314
• /
• 2017

Recently, user authentication through biometric traits such as fingerprint and iris raise more and more attention especially in mobile commerce and fin-tech fields. In particular, commercialized authentication methods using fingerprint recognition are widely utilized mainly because customers are more adopted and used to fingerprint recognition applications. In the meantime, the security issues caused by fingerprint falsification bring lots of attention. In this paper, we propose a new method to improve the performance of fake fingerprint detection using CNN(Convolutional Neural Network). It is common practice to increase the amount of learning data by using affine transformation or horizontal reflection to improve the detection rate in CNN characteristics that are influenced by learning data. However, in this paper we propose an effective data augmentation method based on the database difficulty level. The experimental results confirm the validity of proposed method.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.24 no.6
• /
• pp.627-634
• /
• 2016

In this paper, an augmented video generation method to evaluate the performance of lane departure warning system is proposed. In our system, the input is a video which have road scene with general clean lane, and the content of output video is the same but the lane is synthesized with contamination image. In order to synthesize the contamination lane image, two approaches were used. One is example-based image synthesis, and the other is background-based image synthesis. Example-based image synthesis is generated in the assumption of the situation that contamination is applied to the lane, and background-based image synthesis is for the situation that the lane is erased due to aging. In this paper, a new contamination pattern generation method using Gaussian function is also proposed in order to produce contamination with various shape and size. The contamination lane video can be generated by shifting synthesized image as lane movement amount obtained empirically. Our experiment showed that the similarity between the generated contamination lane image and real lane image is over 90 %. Futhermore, we can verify the reliability of the video generated from the proposed method through the analysis of the change of lane recognition rate. In other words, the recognition rate based on the video generated from the proposed method is very similar to that of the real contamination lane video.

• Journal of Internet Computing and Services
• /
• v.18 no.5
• /
• pp.61-67
• /
• 2017

In this paper we introduce two experimental results from classification of Instagram images and some valuable lessons from them. We have tried some experiments for evaluating the competitive power of Convolutional Neural Network(CNN) in classification of real social network images such as Instagram images. We used AlexNet and ResNet, which showed the most outstanding capabilities in ImageNet Large Scale Visual Recognition Challenge(ILSVRC) 2012 and 2015, respectively. And we used 240 Instagram images and 12 pre-defined categories for classifying social network images. Also, we performed fine-tuning using Inception V3 model, and compared those results. In the results of four cases of AlexNet, ResNet, Inception V3 and fine-tuned Inception V3, the Top-1 error rates were 49.58%, 40.42%, 30.42%, and 5.00%. And the Top-5 error rates were 35.42%, 25.00%, 20.83%, and 0.00% respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.3
• /
• pp.347-358
• /
• 2016

The paper presents a software architecture for a wearable device to measure vital signs with the real-time user's behavior recognition. Taking vital signs with a wearable device help user measuring health state related to their behavior because a wearable device is worn in daily life. Especially, when the user is running or sleeping, oxygen saturation and heart rate are used to diagnose a respiratory problems. However, in measuring vital signs, continuosly measuring like the conventional method is not reasonable because motion artifact could decrease the accuracy of vital signs. And in order to fix the distortion, a complex algorithm is not appropriate because of the limited resources of the wearable device. In this paper, we proposed the software architecture for wearable device using a simple filter and the acceleration sensor to recognize the user's behavior and measure accurate vital signs with the behavior state.