• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.30 no.6
• /
• pp.487-497
• /
• 2019

It is very difficult to detect ballistic missiles because of small cross-sections of the radar and the high maneuverability of the missiles. In addition, it is very difficult to recognize and intercept warheads because of the existence of debris and decoy with similar motion parameters in each flight phase. Therefore, feature vectors based on the maneuver, the micro-motion according to flight phase are needed, and the two types of features must be fused for the efficient recognition of ballistic warhead regardless of the flight phase. In this paper, we introduce feature vectors appropriate for each flight phase and an effective method to fuse them at the feature vector-level and classifier-level. According to the classification simulations using the radar signals predicted by the CAD models, the closer the warhead was to the final destination, the more improved was the classification performance. This was achieved by the classifier-level fusion, regardless of the flight phase in a noisy environment.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.9 no.2
• /
• pp.144-150
• /
• 2000

Surface roughness is one of the most important parameters to estimate quality of products. As this reason so many studies were car-ried out through various attempts that were contact or non-contact using computer vision. Even through these efforts there were few good results in this research., however texture analysis making a important role to solve these problems in various fields including universe aviation living thing and fibers. In this study feature value of co-occurrence matrix was calculated by statistic method and roughness value of worked surface was classified, of it. Experiment was carried out using input vector of neural network with characteristic value of texture calculated from worked surface image. It's found that recognition rate of 74% was obtained when adapting texture features. In order to enhance recogni-tion rate combination type in characteristics value of texture was changed into input vector. As a result high recognition rate of 92.6% was obtained through these processes.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.1181-1185
• /
• 1991

Unlike printed character, the recognition of Hand written one has various kinds of difficulties due to the existence of the huge pattern associated with the person who writes. Therefore, in general, recognition of Hand written characters requires an algorithm which takes into consideration of the individual differences. Hangul characters are basically made of straight lines and circles. They can be represented in terms of feature parameters such as the end point of the straight line, the length and the angle. Then all Hangul characters can be represented by the number of basic segments(-, /, vertical bar, O) multiplied by the feature parameters respectively. In this study we propose a method for recognizing Hand written Hangul characters in terms of fuzzy inference.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.129-140
• /
• 2022

The effectiveness of system identification, damage detection, condition assessment and other structural analyses relies heavily on the accuracy and reliability of the measured data in structural health monitoring (SHM) systems. However, data anomalies often occur in SHM systems, leading to inaccurate and untrustworthy analysis results. Therefore, anomalies in the raw data should be detected and cleansed before further analysis. Previous studies on data anomaly detection mainly focused on just single type of data anomaly for denoising or removing outliers, meanwhile, the existing methods of detecting multiple data anomalies are usually time consuming. For these reasons, recognising multiple anomaly patterns for real-time alarm and analysis in field monitoring remains a challenge. Aiming to achieve an efficient and accurate detection for multi-type data anomalies for field SHM, this study proposes a pattern-recognition-based data anomaly detection method that mainly consists of three steps: the feature extraction from the long time-series data samples, the training of a pattern recognition neural network (PRNN) using the features and finally the detection of data anomalies. The feature extraction step remarkably reduces the time cost of the network training, making the detection process very fast. The performance of the proposed method is verified on the basis of the SHM data of two practical long-span bridges. Results indicate that the proposed method recognises multiple data anomalies with very high accuracy and low calculation cost, demonstrating its applicability in field monitoring.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.1
• /
• pp.82-89
• /
• 2015

The researches of image recognition have been processed traditionally. Especially, face recognition technology has been received attractions with advance and applied to various areas according as camera sensor embedded into many devices such as smart phone. In this study, we design and develop a feature vector generation technique of face for making animation caricatures using methods for face detection which are previous stage of face recognition. At first, we detect both face region and detailed eye region of component element by Viola&Johns's realtime detection method which are called as ROI(Region Of Interest). And then, we generate feature vectors of eye region by utilizing factors as opposed to the periphery and by using appearance information of eye. At this point, we focus on the embedded information in many color spaces to overcome the problems which can be occurred by using one color space. We propose a feature vector generation method using information from many color spaces. Finally, we experiment the test of feature vector generation by the proposed method with enough quantity of sample picture data and evaluate the proposed method for factors of estimating performance such as error rate, accuracy and generation time.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4412-4428
• /
• 2018

The purpose of this work is to solve the problem of representing an entire video using Convolutional Neural Network (CNN) features for human action recognition. Recently, due to insufficient GPU memory, it has been difficult to take the whole video as the input of the CNN for end-to-end learning. A typical method is to use sampled video frames as inputs and corresponding labels as supervision. One major issue of this popular approach is that the local samples may not contain the information indicated by the global labels and sufficient motion information. To address this issue, we propose a binary hashing method to enhance the local feature extractors. First, we extract the local features and aggregate them into global features using maximum/minimum pooling. Second, we use the binary hashing method to capture the motion features. Finally, we concatenate the hashing features with global features using different normalization methods to train the classifier. Experimental results on the JHMDB and MPII-Cooking datasets show that, for these new local features, binary hashing mapping on the sparsely sampled features led to significant performance improvements.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.322-327
• /
• 2007

Researchers in the field of psychology used Electroencephalographic (EEG) to record activities of human brain lot many years. As technology develope, neural basis of functional areas of emotion processing is revealed gradually. So we measure fundamental areas of human brain that controls emotion of human by using EEG. Hands gestures such as shaking and head gesture such as nodding are often used as human body languages for communication with each other, and their recognition is important that it is a useful communication medium between human and computers. Research methods about gesture recognition are used of computer vision. Many researchers study emotion recognition method which uses one of physiological signals and gestures in the existing research. In this paper, we use together physiological signals and gestures for emotion recognition of human. And we select the driver emotion as a specific target. The experimental result shows that using of both physiological signals and gestures gets high recognition rates better than using physiological signals or gestures. Both physiological signals and gestures use Interactive Feature Selection(IFS) for the feature selection whose method is based on a reinforcement learning.

• Proceedings of the IEEK Conference
• /
• 2002.06c
• /
• pp.83-86
• /
• 2002

This paper intends to provide convenience to the disabled, losing the use of their limbs, through voice recognition technology. The voice recognition part of this system recognizes voice by DTW (Dynamic Time Warping) Which is most Widely used in Speaker dependent system. Specially, S/N rate was improved through Wiener filter in the pre-treatment phase while considering real environmental conditions; the result values of 12th order feature pattern per frame are extracted by DTW algorithm using LPC and Cepsturm in feature extraction process. Furthermore, miniaturization is pursued using TMS320C32, 71's the floating-point DSP, for the hardware part. Currently, 90% of hardware porting has been completed, but we can confirm that the recognition rate was 96% as a result of performing the DTW algorithm in PC.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.259-260
• /
• 2006

Since audio speech recognition is affected by noise in real environment, visual speech recognition is used to support speech recognition. For the visual speech recognition, this paper suggests the extraction of lip-feature using two types of image segmentation and reduced ASM. Input images are transformed to YCbCr based images and lips are segmented using the contrast of Y/Cb/Cr between lip and face. Subsequently, lip-shape model trained by PCA is placed on segmented lip region and then lip features are extracted using ASM.

• Journal of Biomedical Engineering Research
• /
• v.43 no.6
• /
• pp.441-447
• /
• 2022

In this paper, we propose a pill identification model using engraved text feature and image feature such as shape and color, and compare it with an identification model that does not use engraved text feature to verify the possibility of improving identification performance by improving recognition rate of the engraved text. The data consisted of 100 classes and used 10 images per class. The engraved text feature was acquired through Keras OCR based on deep learning and 1D CNN, and the image feature was acquired through 2D CNN. According to the identification results, the accuracy of the text recognition model was 90%. The accuracy of the comparative model and the proposed model was 91.9% and 97.6%. The accuracy, precision, recall, and F1-score of the proposed model were better than those of the comparative model in terms of statistical significance. As a result, we confirmed that the expansion of the range of feature improved the performance of the identification model.