• ETRI Journal
• /
• v.36 no.5
• /
• pp.696-703
• /
• 2014

In this paper, we present a walking guidance system for the visually impaired for use at subway stations. This system, which is based on environmental knowledge, automatically detects and recognizes both exit numbers and arrow signs from natural outdoor scenes. The visually impaired can, therefore, utilize the system to find their own way (for example, using exit numbers and the directions provided) through a subway station. The proposed walking guidance system consists mainly of three stages: (a) sign detection using the MCT-based AdaBoost technique, (b) sign recognition using support vector machines and hidden Markov models, and (c) three verification techniques to discriminate between signs and non-signs. The experimental results indicate that our sign recognition system has a high performance with a detection rate of 98%, a recognition rate of 99.5%, and a false-positive error rate of 0.152.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1992.10a
• /
• pp.47-51
• /
• 1992

Automatic detection of tool breakage during NC machining is a key issue not only for improving productivity but to implement the unattended manufacturing system. In this paper, we develop a vibration sensor-based tool breakage detection system for NC milling processes. The system obtains the time-domain vibration signal from the sensor attached on the spindle bracket of our CNC machine and declares tool failures through the on-line monitoring schemes. For on-line detection, our approach is to use the PSC(statistical process control) methods being increasingly used for on-line process control. The main thrust of this paper is to propose and compare the performance of SPC methods including : a) X-bar control scheme, b) S control scheme, c)EWMA (exponentially weighted moving average) scheme, and d) AEWMA (adaptive exponentially weighted moving average) scheme. The performance of the control schemes are compared in terms of the type 1 and 2 error calculated from the experiment data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.6
• /
• pp.2624-2630
• /
• 2013

In LED chip packaging, die bonding is a very important process which fixes the LED chip on the lead flame to provide enough strength for the next process. During the process, inspection processes are very important to detect exact locations of dispensed epoxy dots and to determine bonding status of dies whether they are lies at exact positions with sufficient bonding strength. In this study, a useful machine vision based inspection system is proposed for the LED die bonder. In the proposed system, 2 cameras are used for epoxy dot position detection and 2 cameras are sued for die attaching status determination. New vision processing algorithm is proposed, and its efficiency is verified through required field experiments. Measured position error is less than $X:-29{\mu}m$, $Y:-32{\mu}m$ and rotation error:$3^{\circ}$ using proposed vision algorithm. It is concluded that the proposed machine vision based inspection system can be successfully implemented on the developed die bonding system.

• Journal of Biosystems Engineering
• /
• v.27 no.2
• /
• pp.143-150
• /
• 2002

Several researches for site-specific weed control have tried to increase accuracy of weed detection with machine vision technique. However, there is a problem which needs substantial time to perform site-specific spraying. Therefore, new technology for real-time precision spraying system is needed. This research was executed to develope the new technology to estimate weed density and size in real time, and to conduct a real-time site-specific spraying. It would effectively reduce herbicide amounts applied for a crop field. The real-time precision spraying system consisted of a Differential Global Positioning System (DGPS) with an error of 2 cm, a machine vision system, a geomagnetic sensor for correction of view point of CCD camera and an automatic sprayer with separately controlled nozzle. The weed density was calculated with comparison between position information and a pre-designed electronic map. The position information was obtained in real time using the DGPS and the machine vision. The electronic map contained a position database of crops automatically constructed when seeding. The developed system was tested on an experimental field of Seoul National University. Success rate of the spraying was about 61%.

• Journal of Multimedia Information System
• /
• v.3 no.2
• /
• pp.9-12
• /
• 2016

This paper is concerned with the effective and efficient identification of the gender and motion of humans. Tracking this nonverbal behavior is useful for providing clues about the interaction of different types of people and their exact motion. This system can also be useful for security in different places or for monitoring patients in hospital and many more applications. Here we describe a novel method of determining identity using machine learning with Microsoft Kinect. This method minimizes the fitting or overlapping error between an ellipsoid based skeleton.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.2
• /
• pp.71-82
• /
• 2022

In order to replace the sampling tensile test of products produced in the tab welding process, which is one of the automotive battery manufacturing processes, vision inspectors are currently being developed and used. However, the vision inspection has the problem of inspection position error and the cost of improving it. In order to solve these problems, there are recent cases of applying deep learning technology. As one such case, this paper tries to examine the usefulness of applying Faster R-CNN, one of the deep learning technologies, to existing product inspection. The images acquired through the existing vision inspection machine are used as training data and trained using the Faster R-CNN ResNet101 V1 1024x1024 model. The results of the conventional vision test and Faster R-CNN test are compared and analyzed based on the test standards of 0% non-detection and 10% over-detection. The non-detection rate is 34.5% in the conventional vision test and 0% in the Faster R-CNN test. The over-detection rate is 100% in the conventional vision test and 6.9% in Faster R-CNN. From these results, it is confirmed that deep learning technology is very useful for detecting welding error of lead tabs in automobile batteries.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.8
• /
• pp.397-402
• /
• 2007

In this paper, we apply a support vector machine(SVM) that incorporates an optimized nonlinear decision rule over different sets of feature vectors to improve the performance of statistical model-based voice activity detection(VAD). Conventional method performs VAD through setting up statistical models for each case of speech absence and presence assumption and comparing the geometric mean of the likelihood ratio (LR) for the individual frequency band extracted from input signal with the given threshold. We propose a novel VAD technique based on SVM by treating the LRs computed in each frequency bin as the elements of feature vector to minimize classification error probability instead of the conventional decision rule using geometric mean. As a result of experiments, the performance of SVM-based VAD using the proposed feature has shown better results compared with those of reported VADs in various noise environments.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.91-98
• /
• 2021

Today's information and communication technology is rapidly developing, the security of IT infrastructure is becoming more important, and at the same time, cyber attacks of various forms are becoming more advanced and sophisticated like intelligent persistent attacks (Advanced Persistent Threat). Early defense or prediction of increasingly sophisticated cyber attacks is extremely important, and in many cases, the analysis of network-based intrusion detection systems (NIDS) related data alone cannot prevent rapidly changing cyber attacks. Therefore, we are currently using data generated by intrusion detection systems to protect against cyber attacks described above through Host-based Intrusion Detection System (HIDS) data analysis. In this paper, we conducted a comparative study on machine learning algorithms using LID-DS (Leipzig Intrusion Detection-Data Set) host-based intrusion detection data including thread information, metadata, and buffer data missing from previously used data sets. The algorithms used were Decision Tree, Naive Bayes, MLP (Multi-Layer Perceptron), Logistic Regression, LSTM (Long Short-Term Memory model), and RNN (Recurrent Neural Network). Accuracy, accuracy, recall, F1-Score indicators and error rates were measured for evaluation. As a result, the LSTM algorithm had the highest accuracy.

• Smart Media Journal
• /
• v.11 no.9
• /
• pp.47-55
• /
• 2022

Quality control in the smart factory manufacturing process is an important factor. Currently, quality inspection of home appliance manufacturing parts produced by the mold process is mostly performed with the naked eye of the operator, resulting in a high error rate of inspection. In order to improve the quality competition, an automatic defect detection system was designed and implemented. The proposed system acquires an image by photographing an object with a high-performance scan camera at a specific location, and reads defective products due to scratches, dents, and foreign substances according to the vision inspection algorithm. In this study, the depth-based branch decision algorithm (DBD) was developed to increase the recognition rate of defects due to scratches, and the accuracy was improved.

• Ocean Systems Engineering
• /
• v.6 no.3
• /
• pp.217-231
• /
• 2016

This paper presents a new approach for underwater image analysis using the bi-dimensional empirical mode decomposition (BEMD) technique and the phase congruency information. The BEMD algorithm, fully unsupervised, it is mainly applied to texture extraction and image filtering, which are widely recognized as a difficult and challenging machine vision problem. The phase information is the very stability feature of image. Recent developments in analysis methods on the phase congruency information have received large attention by the image researchers. In this paper, the proposed method is called the EP model that inherits the advantages of the first two algorithms, so this model is suitable for processing underwater image. Moreover, the receiver operating characteristic (ROC) curve is presented in this paper to solve the problem that the threshold is greatly affected by personal experience when underwater image edge detection is performed using the EP model. The EP images are computed using combinations of the Canny detector parameters, and the binaryzation image results are generated accordingly. The ideal EP edge feature extractive maps are estimated using correspondence threshold which is optimized by ROC analysis. The experimental results show that the proposed algorithm is able to avoid the operation error caused by manual setting of the detection threshold, and to adaptively set the image feature detection threshold. The proposed method has been proved to be accuracy and effectiveness by the underwater image processing examples.