• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.15 no.3
• /
• pp.172-179
• /
• 2015

Because of the development of computers and high-technology applications, all devices that we use have become more intelligent. In recent years, security and surveillance systems have become more complicated as well. Before new technologies included video surveillance systems, security cameras were used only for recording events as they occurred, and a human had to analyze the recorded data. Nowadays, computers are used for video analytics, and video surveillance systems have become more autonomous and automated. The types of security cameras have also changed, and the market offers different kinds of cameras with integrated software. Even though there is a variety of hardware, their capabilities leave a lot to be desired. Therefore, this drawback is trying to compensate by dint of computer program solutions. Image processing is a very important part of video surveillance and security systems. Capturing an image exactly as it appears in the real world is difficult if not impossible. There is always noise to deal with. This is caused by the graininess of the emulsion, low resolution of the camera sensors, motion blur caused by movements and drag, focus problems, depth-of-field issues, or the imperfect nature of the camera lens. This paper reviews image processing, pattern recognition, and image digitization techniques, which will be useful in security services, to analyze bio-images, for image restoration, and for object classification.

• International Journal of Highway Engineering
• /
• v.12 no.4
• /
• pp.47-51
• /
• 2010

A vehicle classification data is essential for traffic road planning and pavement. In this study, the vehicle height, vehicle criteria for classification applied to measure the height of the car driving has devised a way to install equipment. It is capable of measuring the vehicle height was confirmed to field experiments, the measurement system is obtained to the vehicle length and height data. In this experiment, results showed the accuracy of 88.6% compared to classification data using the discriminant function obtained from video replaying. The height of vehicle applying the classification criteria can be utilized to determine the vehicle class.

• Journal of Information Processing Systems
• /
• v.16 no.1
• /
• pp.6-29
• /
• 2020

Biometrics identification using multiple modalities has attracted the attention of many researchers as it produces more robust and trustworthy results than single modality biometrics. In this paper, we present a novel multimodal recognition system that trains a deep learning network to automatically learn features after extracting multiple biometric modalities from a single data source, i.e., facial video clips. Utilizing different modalities, i.e., left ear, left profile face, frontal face, right profile face, and right ear, present in the facial video clips, we train supervised denoising auto-encoders to automatically extract robust and non-redundant features. The automatically learned features are then used to train modality specific sparse classifiers to perform the multimodal recognition. Moreover, the proposed technique has proven robust when some of the above modalities were missing during the testing. The proposed system has three main components that are responsible for detection, which consists of modality specific detectors to automatically detect images of different modalities present in facial video clips; feature selection, which uses supervised denoising sparse auto-encoders network to capture discriminative representations that are robust to the illumination and pose variations; and classification, which consists of a set of modality specific sparse representation classifiers for unimodal recognition, followed by score level fusion of the recognition results of the available modalities. Experiments conducted on the constrained facial video dataset (WVU) and the unconstrained facial video dataset (HONDA/UCSD), resulted in a 99.17% and 97.14% Rank-1 recognition rates, respectively. The multimodal recognition accuracy demonstrates the superiority and robustness of the proposed approach irrespective of the illumination, non-planar movement, and pose variations present in the video clips even in the situation of missing modalities.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.3
• /
• pp.1348-1375
• /
• 2018

Support Vector Machine (SVM) is a well-known machine learning classification algorithm, which has been widely applied to many data mining problems, with good accuracy. However, SVM classification speed decreases with increase in dataset size. Some applications, like video surveillance and intrusion detection, requires a classifier to be trained very quickly, and on large datasets. Hence, this paper introduces two filter-based instance selection techniques for optimizing SVM training speed. Fast classification is often achieved at the expense of classification accuracy, and some applications, such as phishing and spam email classifiers, are very sensitive to slight drop in classification accuracy. Hence, this paper also introduces two wrapper-based instance selection techniques for improving SVM predictive accuracy and training speed. The wrapper and filter based techniques are inspired by Cuckoo Search Algorithm and Bat Algorithm. The proposed techniques are validated on three popular e-fraud types: credit card fraud, spam email and phishing email. In addition, the proposed techniques are validated on 20 other datasets provided by UCI data repository. Moreover, statistical analysis is performed and experimental results reveals that the filter-based and wrapper-based techniques significantly improved SVM classification speed. Also, results reveal that the wrapper-based techniques improved SVM predictive accuracy in most cases.

• Journal of Korea Multimedia Society
• /
• v.20 no.2
• /
• pp.196-204
• /
• 2017

Behavior of intelligent video surveillance system is recognized by analyzing the pattern of the object of interest by using the frame information of video inputted from the camera and analyzes the behavior. Detection of object's certain behaviors in the crowd has become a critical problem because in the event of terror strikes. Recognition of object's certain behaviors is an important but difficult problem in the area of computer vision. As the realization of big data utilizing machine learning, data mining techniques, the amount of video through the CCTV, Smart-phone and Drone's video has increased dramatically. In this paper, we propose a multiple-sliding window method to recognize the cumulative change as one piece in order to improve the accuracy of the recognition. The experimental results demonstrated the method was robust and efficient learning units in the classification of certain behaviors.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.2_1
• /
• pp.169-176
• /
• 2022

Prognostics and health management (PHM) is recently converging throughout the industry, one of the trending issue is to detect abnormal conditions at decanter centrifuge during water treatment facilities. Wastewater treatment operation produces corrosive gas which results failures on attached sensors. This scenario causes frequent sensor replacement and requires highly qualified manager's visual inspection while replacing important parts such as bearings and screws. In this paper, we propose anomaly detection by measuring the vibration of the decanter centrifuge based on the video camera images. Measuring the vibration of the screw decanter by applying the optical flow technique, the amount of movement change of the corresponding pixel is measured and fed into the LST M model. As a result, it is possible to detect the normal/warning/dangerous state based on LSTM classification. In the future work, we aim to gather more abnormal data in order to increase the further accuracy so that it can be utilized in the field of industry.

• The Korean Journal of Emergency Medical Services
• /
• v.23 no.1
• /
• pp.87-99
• /
• 2019

Purpose: The aim of this study was conducted to assess the proficiency of both direct laryngoscopy and video laryngoscopy and the usefulness of each laryngoscope, thereby provide basic data for further education using video laryngoscopy. Methods: Forty one paramedic subjects participated in this study. Usability was measured with the System usability scale. The Macintosh direct laryngoscope and $C-MAC^{(R)}$ video laryngoscope were two instruments evaluated in the study. Results: Training with video laryngoscopy showed significantly better results within the categories of dental injury (p=.004), esophageal intubation (p=.001), and proper depth placement of intubation tubes (p=.019). The results of the System usability scale questionnaire and the degrees of visibility based on the Cormack & Lehane classification were also found to be better achieved with the video laryngoscopy (p=.000). Conclusion: This study suggests enhancing education with video laryngoscopy, which could reduce the risk of complications and duration of intubation while increasing the success rate among students and emergency medical technicians with little experience, rather than the existing method of only using direct laryngoscope, which requires considerable experience and skills.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1689-1701
• /
• 2019

In recent years, personal videos have been shared online due to the popular uses of portable devices, such as smartphones and action cameras. A recent report predicted that 80% of the Internet traffic will be video content by the year 2021. Several studies have been conducted on the detection of main video events to manage a large scale of videos. These studies show fairly good performance in certain genres. However, the methods used in previous studies have difficulty in detecting events of personal video. This is because the characteristics and genres of personal videos vary widely. In a research, we found that adding a dataset with the right perspective in the study improved performance. It has also been shown that performance improves depending on how you extract keyframes from the video. we selected frame segments that can represent video considering the characteristics of this personal video. In each frame segment, object, location, food and audio features were extracted, and representative vectors were generated through a CNN-based recurrent model and a fusion module. The proposed method showed mAP 78.4% performance through experiments using LSVC data.

• Journal of Information Processing Systems
• /
• v.18 no.5
• /
• pp.677-687
• /
• 2022

We propose a detection algorithm based on tree-structured convolutional neural networks (TsCNNs) that finds pornography, propaganda, or other inappropriate content on a social media network. The algorithm sequentially applies the typical convolutional neural network (CNN) algorithm in a tree-like structure to minimize classification errors in similar classes, and thus improves accuracy. We implemented the detection system and conducted experiments on a data set comprised of 6 ordinary classes and 11 inappropriate classes collected from the Korean military social network. Each model of the proposed algorithm was trained, and the performance was then evaluated according to the images and videos identified. Experimental results with 20,005 new images showed that the overall accuracy in image identification achieved a high-performance level of 99.51%, and the effectiveness of the algorithm reduced identification errors by the typical CNN algorithm by 64.87 %. By reducing false alarms in video identification from the domain, the TsCNNs achieved optimal performance of 98.11% when using 10 minutes frame-sampling intervals. This indicates that classification through proper sampling contributes to the reduction of computational burden and false alarms.

• Proceedings of the KSPS conference
• /
• 2007.05a
• /
• pp.207-210
• /
• 2007

As the Internet is prevalent in our life, harmful contents have been increasing on the Internet, which has become a very serious problem. Among them, pornographic video is harmful as poison to our children. To prevent such an event, there are many filtering systems which are based on the keyword based methods or image based methods. The main purpose of this paper is to devise a system that classifies the pornographic videos based on the audio information. We use Mel-Cepstrum Modulation Energy (MCME) which is modulation energy calculated on the time trajectory of the Mel-Frequency cepstral coefficients (MFCC) and MFCC as the feature vector and Gaussian Mixture Model (GMM) as the classifier. With the experiments, the proposed system classified the 97.5% of pornographic data and 99.5% of non-pornographic data. We expect the proposed method can be used as a component of the more accurate classification system which uses video information and audio information simultaneously.