• Journal of Multimedia Information System
• /
• v.7 no.1
• /
• pp.11-16
• /
• 2020

Deep Learning has become the most important technology in the field of artificial intelligence machine learning, with its high performance overwhelming existing methods in various applications. In this paper, an interactive window service based on object recognition technology is proposed. The main goal is to implement an object recognition technology using this deep learning technology to remove the existing eye tracking technology, which requires users to wear eye tracking devices themselves, and to implement an eye tracking technology that uses only usual cameras to track users' eye. We design an interactive system based on efficient eye detection and pupil tracking method that can verify the user's eye movement. To estimate the view-direction of user's eye, we initialize to make the reference (origin) coordinate. Then the view direction is estimated from the extracted eye pupils from the origin coordinate. Also, we propose a blink detection technique based on the eye apply ratio (EAR). With the extracted view direction and eye action, we provide some augmented information of interest without the existing complex and expensive eye-tracking systems with various service topics and situations. For verification, the user guiding service is implemented as a proto-type model with the school map to inform the location information of the desired location or building.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.99-104
• /
• 2011

In this paper the approach of neural network was proposed which detects a variety of defects in the molded parts. In an attempt to improve the response of the system, It is designed to minimize the use of memory via LookUp table in software. The goal of these methods was to extract the features of samples in learning of neural networks, overcoming the algorithms of defects detection and classification. Through the learning of 500 sample patterns of molded parts, defects of 3% molded parts was detected and classified as the incorrect diameter parts. We expect that proposed approach is an effective alternative to save test time and cost for defect detection of a fine pattern within the molded parts.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.4026-4040
• /
• 2019

In this paper, we present an approach for detecting slide transitions in lecture videos by introducing the spatio-temporal residual networks. Given a lecture video which records the digital slides, the speaker, and the audience by multiple cameras, our goal is to find keyframes where slide content changes. Since temporal dependency among video frames is important for detecting slide changes, 3D Convolutional Networks has been regarded as an efficient approach to learn the spatio-temporal features in videos. However, 3D ConvNet will cost much training time and need lots of memory. Hence, we utilize ResNet to ease the training of network, which is easy to optimize. Consequently, we present a novel ConvNet architecture based on 3D ConvNet and ResNet for slide transition detection in lecture videos. Experimental results show that the proposed novel ConvNet architecture achieves the better accuracy than other slide progression detection approaches.

• Korean Journal of Remote Sensing
• /
• v.35 no.5_1
• /
• pp.737-750
• /
• 2019

Information of target changes in inaccessible areas is very important in terms of national security. Fast and accurate change detection of targets is very important to respond quickly. Spaceborne synthetic aperture radar can acquire images with high accuracy regardless of weather conditions and solar altitude. With the recent increase in the number of SAR satellites, it is possible to acquire images with less than one day temporal resolution for the same area. This advantage greatly increases the availability of change detection for inaccessible areas. Commonly available information in satellite SAR is amplitude and phase information, and change detection techniques have been developed based on each technology. Those are amplitude Change Detection (ACD), Coherence Change Detection (CCD). Each algorithm differs in the preprocessing process for accurate automatic classification technique according to the difference of information characteristics and the final detection result of each algorithm. Therefore, by analyzing the academic research trends for ACD and CCD, each technologies can be complemented. The goal of this paper is identifying current issues of SAR change detection techniques by collecting research papers. This study would help to find the prerequisites for SAR change detection and use it to conduct periodic detection research on inaccessible areas.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.20 no.3
• /
• pp.277-284
• /
• 2014

This paper describes the application method of bumper area defined in the ship domain theory and it is to identify risky sectors in VTS(Vessel Traffic Services) area. The final goal of this work is to develop early warning system providing the location information with high traffic risks in Mokpo VTS area and to prevent the human errors of VTS Officer(VTSO). The current goal of this paper is to find evaluation and detection method of risky sectors. The ratio between overlapped bumper area of each vessels and the summing area of a designated sector, Ratio to Evaluate Risk(RER) ${\gamma}$ is used as one of evaluation and detection parameter. The usability of overlapped bumper area is testified through three kinds of scenarios for various traffic situations. The marine traffic data used in the experiments is collected by AIS(Automatic Identification System) receiver and then compiled in the SQL(Structured Query Language) Server. Through the analysis of passing vessel's tracks within the boundary of Mokpo VTS area, the total of 11 sectors are identified as evaluation unit sector. As experiment results from risk evaluation for the 11 sectors, it is clearly known that the proposed method with RER ${\gamma}$ can provide the location information of high risky sectors which are need to keep traffic tracks of vessel movements and to maintain traffic monitoring by VTSO.

• Journal of Communications and Networks
• /
• v.11 no.6
• /
• pp.544-555
• /
• 2009

This work continues a trend of developments aimed at exploiting the physical layer of the open systems interconnection (OSI) model to enhance wireless network security. The goal is to augment activity occurring across other OSI layers and provide improved safeguards against unauthorized access. Relative to intrusion detection and anti-spoofing, this paper provides details for a proof-of-concept investigation involving "air monitor" applications where physical equipment constraints are not overly restrictive. In this case, RF fingerprinting is emerging as a viable security measure for providing device-specific identification (manufacturer, model, and/or serial number). RF fingerprint features can be extracted from various regions of collected bursts, the detection of which has been extensively researched. Given reliable burst detection, the near-term challenge is to find robust fingerprint features to improve device distinguishability. This is addressed here using wavelet domain (WD) RF fingerprinting based on dual-tree complex wavelet transform (DT-$\mathbb{C}WT$) features extracted from the non-transient preamble response of OFDM-based 802.11a signals. Intra-manufacturer classification performance is evaluated using four like-model Cisco devices with dissimilar serial numbers. WD fingerprinting effectiveness is demonstrated using Fisher-based multiple discriminant analysis (MDA) with maximum likelihood (ML) classification. The effects of varying channel SNR, burst detection error and dissimilar SNRs for MDA/ML training and classification are considered. Relative to time domain (TD) RF fingerprinting, WD fingerprinting with DT-$\mathbb{C}WT$ features emerged as the superior alternative for all scenarios at SNRs below 20 dB while achieving performance gains of up to 8 dB at 80% classification accuracy.

• Journal of the East Asian Society of Dietary Life
• /
• v.18 no.5
• /
• pp.753-759
• /
• 2008

The principal objective of this study was to develop the optimum oligonucleotide primers for the simple detection of Campylobacter in food samples. In order to achieve this goal, a variety of oligonucleotide primers were designed via the modification of 16S rDNA, ceuE and mapA sequences of Campylobacter. Through the subsequent analysis of the specificity and sensitivity of primers, two types of oligonucleotide primers, CB4 and CJ1, were selected for Campylobacter genus-specific and C. jejuni species-specific primers, respectively. The detection limit was found to be $10^0{\sim}10^1$ cells per reaction with the prepared cell suspension, however, the sensitivity in the meat samples was less, at $10^1{\sim}10^2$. We suggested that PCR inhibitors such as hemoglobin or immunoglobulin in pork or beef influenced.

• The KIPS Transactions:PartB
• /
• v.9B no.6
• /
• pp.853-862
• /
• 2002

Face Detection can be defined as follows : Given a digitalized arbitrary or image sequence, the goal of face detection is to determine whether or not there is any human face in the image, and if present, return its location, direction, size, and so on. This technique is based on many applications such face recognition facial expression, head gesture and so on, and is one of important qualify factors. But face in an given image is considerably difficult because facial expression, pose, facial size, light conditions and so on change the overall appearance of faces, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact face detection which overcomes some restrictions by using neural network. The proposed system can be face detection irrelevant to facial expression, background and pose rapidily. For this. face detection is performed by neural network and detection response time is shortened by reducing search region and decreasing calculation time of neural network. Reduced search region is accomplished by using skin color segment and frame difference. And neural network calculation time is decreased by reducing input vector sire of neural network. Principle Component Analysis (PCA) can reduce the dimension of data. Also, pose estimates in extracted facial image and eye region is located. This result enables to us more informations about face. The experiment measured success rate and process time using the Squared Mahalanobis distance. Both of still images and sequence images was experimented and in case of skin color segment, the result shows different success rate whether or not camera setting. Pose estimation experiments was carried out under same conditions and existence or nonexistence glasses shows different result in eye region detection. The experiment results show satisfactory detection rate and process time for real time system.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.6
• /
• pp.809-817
• /
• 2008

Program plagiarism is widespread due to intelligent software and the global Internet environment. Consequently the detection of plagiarized source code and software is becoming important especially in academic field. Though numerous studies have been reported for detecting plagiarized pairs of codes, we cannot find any profound work on understanding the underlying mechanisms of plagiarism. In this paper, we study the evolutionary process of source codes regarding that the plagiarism procedure can be considered as evolutionary steps of source codes. The final goal of our paper is to reconstruct a tree depicting the evolution process in the source code. To this end, we extend the well-known bioinformatics approach, a local alignment approach, to detect a region of similar code with an adaptive scoring matrix. The asymmetric code similarity based on the local alignment can be considered as one of the main contribution of this paper. The phylogenetic tree or evolution tree of source codes can be reconstructed using this asymmetric measure. To show the effectiveness and efficiency of the phylogeny construction algorithm, we conducted experiments with more than 100 real source codes which were obtained from East-Asia ICPC(International Collegiate Programming Contest). Our experiments showed that the proposed algorithm is quite successful in reconstructing the evolutionary direction, which enables us to identify plagiarized codes more accurately and reliably. Also, the phylogeny construction algorithm is successfully implemented on top of the plagiarism detection system of an automatic program evaluation system.

• Journal of Advanced Navigation Technology
• /
• v.24 no.3
• /
• pp.192-197
• /
• 2020

Recently, the technologies related to autonomous drive has studying the goal for safe operation and prevent accidents of vehicles. There is radar and camera technologies has used to detect obstacles in these autonomous vehicle research. Now a day, the method for using LiDAR sensor has considering to detect nearby objects and accurately measure the separation distance in the autonomous navigation. It is calculates the distance by recognizing the time differences between the reflected beams and it allows precise distance measurements. But it also has the disadvantage that the recognition rate of object in the atmospheric environment can be reduced. In this paper, point cloud data by triangular functions and Line Regression model are used to implement measurement algorithm, that has improved detecting objects in real time and reduce the error of measuring separation distances based on improved reliability of raw data from LiDAR sensor. It has verified that the range of object detection errors can be improved by using the Python imaging library.