• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.12
• /
• pp.107-119
• /
• 1999

There is no authentic solution in a face detection problem though it is an important part of pattern recognition and has many diverse application fields. The reason is that there are many unpredictable deformations due to facial expressions, view point, rotation, scale, gender, age, etc. To overcome these problems, we propose an algorithm based on feature-based method, which is well known to be robust to these deformations. We detect a face by calculating a similarity between the formation of real face feature and candidate feature formation which consists of eyebrow, eye, nose, and mouth. In this paper, we use a steerable filter instead of general derivative edge detector in order to get more accurate feature components. We applied deformable template to verify the detected face, which overcome the weak point of feature-based method. Considering the low detection rate because of face detection method using whole input images, we design an adaptive skin-color filter which can be applicable to a diverse skin color, minimizing target area and processing time.

• Journal of IKEEE
• /
• v.24 no.3
• /
• pp.783-790
• /
• 2020

In this paper, the human detecting radar system for indoor security applications is proposed, and its FPGA-based implementation results are presented. In order to minimize the complexity and memory requirements of the computation, the top half of the spectrogram was used to extract features, excluding the feature extraction techniques that require complex computation, feature extraction techniques were proposed considering classification performance and complexity. In addition, memory requirements were minimized by designing a pipeline structure without storing the entire spectrogram. Experiments on human, dog and robot cleaners were conducted for classification, and 96.2% accuracy performance was confirmed. The proposed system was implemented using Verilog-HDL, and we confirmed that a low-area design using 1140 logics and 6.5 Kb of memory was possible.

• The KIPS Transactions:PartD
• /
• v.13D no.2 s.105
• /
• pp.279-286
• /
• 2006

One of the widely used methods for product recommendation in Internet storefronts is matching product features against target customer profiles. When using this method, it's very important to choose a suitable subset of features for recommendation efficiency and performance, which, however, has not been rigorously researched so far. In this paper, we utilize a dataset collected from a virtual shopping experiment in a Korean Internet book shopping mall to compare several popular methods from other disciplines for selecting features for product recommendation: the vector-space model, TFIDF(Term Frequency-Inverse Document Frequency), the mutual information method, and the singular value decomposition(SVD). The application of SVD showed the best performance in the analysis results.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.834-835
• /
• 2016

In recent years, advances in technology, IT is rapidly growing. Accordingly, real time image processing and multiple platforms, providing compatibility with OpenCV for image processing technology research on actively in progress. At present, different, comparing the images to determine the similarity is low, the system will match the rate of people using the analogue figures to determine the system is for the most part. In this paper, Template Matching of OpenCV and Feature Matching utilizing different images to determine the similarity between digital values for the system. A comparison of the features of a specific point on the screen the image to extract the same feature in a different size, you can compare the features of the target image recognized as compared to three historic castle in comparison, verification. This is the voice and image recognition and analysis, check the matching rate readings than in Zhengzhou treatment techniques are available. The future of forensic and other image processing technologies for OpenCV studies will be needed to feed.

• Journal of Sensor Science and Technology
• /
• v.30 no.2
• /
• pp.76-81
• /
• 2021

In this study, we propose a machine vision system with a high object recognition rate. By utilizing a multiple-exposure image sensing technique, the proposed deep learning-based machine vision system can cover a wide light intensity range without further learning processes on the various light intensity range. If the proposed machine vision system fails to recognize object features, the system operates in a multiple-exposure sensing mode and detects the target object that is blocked in the near dark or bright region. Furthermore, short- and long-exposure images from the multiple-exposure sensing mode are synthesized to obtain accurate object feature information. That results in the generation of a wide dynamic range of image information. Even with the object recognition resources for the deep learning process with a light intensity range of only 23 dB, the prototype machine vision system with the multiple-exposure imaging method demonstrated an object recognition performance with a light intensity range of up to 96 dB.

• The KIPS Transactions:PartB
• /
• v.14B no.7
• /
• pp.531-540
• /
• 2007

In this research, we proposed a two-phase hybrid stock price forecasting model with cointegration tests and artificial neural networks. Using not only the related stocks to the target stock but also the past information as input features in neural networks, the new model showed an improved performance in forecasting than that of the usual neural networks. Firstly in order to extract stocks which have long run relationships with the target stock, we made use of Johansen's cointegration test. In stock market, some stocks are apt to vary similarly and these phenomenon can be very informative to forecast the target stock. Johansen's cointegration test provides whether variables are related and whether the relationship is statistically significant. Secondly, we learned the model which includes lagged variables of the target and related stocks in addition to other characteristics of them. Although former research usually did not incorporate those variables, it is well known that most economic time series data are depend on its past value. Also, it is common in econometric literatures to consider lagged values as dependent variables. We implemented a price direction forecasting system for KOSPI index to examine the performance of the proposed model. As the result, our model had 11.29% higher forecasting accuracy on average than the model learned without cointegration test and also showed 10.59% higher on average than the model which randomly selected stocks to make the size of the feature set same as that of the proposed model.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.10
• /
• pp.2461-2469
• /
• 1997

Target detection and recognition problems, in which neural networks are widely used, require translation invariant and real-time processing in addition to the requirements that general pattern recognition problems need. This paper presents a novel architecture that meets the requirements and explains effective methodology to train the network. The proposed neural network is an architectural extension of the shared-weight neural network that is composed of the feature extraction stage followed by the pattern recognition stage. Its feature extraction stage performs correlational operation on the input with a weight kernel, and the entire neural network can be considered a nonlinear correlation filter. Therefore, the output of the proposed neural network is correlational plane with peak values at the location of the target. The architecture of this neural network is suitable for implementing with parallel or distributed computers, and this fact allows the application to the problems which require realtime processing. Net training methodology to overcome the problem caused by unbalance of the number of targets and non-targets is also introduced. To verify the performance, the proposed network is applied to detection and recognition problem of a specific automobile driving around in a parking lot. The results show no false alarms and fast processing enough to track a target that moves as fast as about 190 km per hour.

• Journal of Intelligence and Information Systems
• /
• v.8 no.1
• /
• pp.1-13
• /
• 2002

Estimating the Value-at-Risk (VaR) of a non-listed or newly listed company in stock market is impossible due to lack of stock exchange data. This study employes Case-Based Reasoning (CBR) for estimating VaR's of those companies. CBR enables us to identify and select existing companies that have similar financial and non-financial characteristics to the unlisted target company. The VaR's of those selected companies can give estimates of VaR for the target company. We developed a system called VAS-CBR and showed how well the system estimates the VaR's of unlisted companies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4176-4197
• /
• 2020

Botnet is a type of dangerous malware. Botnet attack with a collection of bots attacking a similar target and activity pattern is called bot group activities. The detection of bot group activities using intrusion detection models can only detect single bot activities but cannot detect bots' behavioral relation on bot group attack. Detection of bot group activities could help network administrators isolate an activity or access a bot group attacks and determine the relations between bots that can measure the correlation. This paper proposed a new model to measure the similarity between bot activities using the intersections-probability concept to define bot group activities called as B-Corr Model. The B-Corr model consisted of several stages, such as extraction feature from bot activity flows, measurement of intersections between bots, and similarity value production. B-Corr model categorizes similar bots with a similar target to specify bot group activities. To achieve a more comprehensive view, the B-Corr model visualizes the similarity values between bots in the form of a similar bot graph. Furthermore, extensive experiments have been conducted using real botnet datasets with high detection accuracy in various scenarios.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.368-373
• /
• 2007

In recent year s there have been increasing interests in real-time object tracking with image information. This dissertation presents a real-time object tracking method through the object recognition based on neural networks that have robust characteristics under various illuminations. This dissertation proposes a global search and a local search method to track the object in real-time. The global search recognizes a target object among the candidate objects through the entire image search, and the local search recognizes and track only the target object through the block search. This dissertation uses the object color and feature information to achieve fast object recognition. The experiment result shows the usefulness of the proposed method is verified.