• The Journal of the Korea Contents Association
• /
• v.14 no.3
• /
• pp.33-39
• /
• 2014

Domestic and international researches, about intelligent systems based on a variety of location recognitions using location information, have actively proceeded. The representative location recognition method based on PTMP(Point To Multi Point) communication uses TOA(Time Of Arrival) to calculate distances to a fixed node that you want to recognize a position. The method is used to obtain the fixed node location information from three nodes location information that is applied by the triangulation method. There are disadvantages, an infrastructure should be established at a specific space and the system established cost is needed, in the location recognition method based on the PTMP communication, In this paper, the ranging based PTP(Point To Point) location recognition method is proposed to revise the disadvantage of PTMP location recognition method. And then it is compared with PTMP communication location recognition to evaluate performance. In this way, PTMP and PTP communication location recognition systems based on ranging were constructed and tested in an indoor environment. Experiment results show that the proposed PTP location recognition method could be confirmed to improve accuracy more than 3 times when it was compared with the existed PTMP location recognition method.

• Journal of Industrial Technology
• /
• v.22 no.A
• /
• pp.101-105
• /
• 2002

Counters for various kinds of bank notes require high-speed distinctive point extraction and recognition for notes. In this paper we propose a new point extraction and data extraction method from specific parts of a bank note representing the same color. The recognition algorithm uses a back-propagation neural network that has coordinate data input. The proposed algorithm is designed to minimize recognition time.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.18 no.12
• /
• pp.1256-1261
• /
• 2008

This paper proposes a way to measure the displacement of a multi-point by using a pattern recognition from video signal. Generally in measuring displacement, gab sensor, which is a displacement sensor, is used. However, it is difficult to measure displacement by using a common sensor in places where it is unsuitable to attach a sensor, such as high-temperature areas or radioactive places. In this kind of places, non-contact methods should be used to measure displacement and in this study, images of CCD camera were used. When multi-point is measure by using a pattern recognition, it is possible to measure displacement with a non-contact method. It is simple to install and multi-point displacement measuring device so that it is advantageous to solve problems of spatial constraints.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.486-493
• /
• 2023

In this paper, we propose an automatic hand gesture area extraction and recognition technique using FMCW radar-based point cloud and LSTM. The proposed technique has the following originality compared to existing methods. First, unlike methods that use 2D images as input vectors such as existing range-dopplers, point cloud input vectors in the form of time series are intuitive input data that can recognize movement over time that occurs in front of the radar in the form of a coordinate system. Second, because the size of the input vector is small, the deep learning model used for recognition can also be designed lightly. The implementation process of the proposed technique is as follows. Using the distance, speed, and angle information measured by the FMCW radar, a point cloud containing x, y, z coordinate format and Doppler velocity information is utilized. For the gesture area, the hand gesture area is automatically extracted by identifying the start and end points of the gesture using the Doppler point obtained through speed information. The point cloud in the form of a time series corresponding to the viewpoint of the extracted gesture area is ultimately used for learning and recognition of the LSTM deep learning model used in this paper. To evaluate the objective reliability of the proposed technique, an experiment calculating MAE with other deep learning models and an experiment calculating recognition rate with existing techniques were performed and compared. As a result of the experiment, the MAE value of the time series point cloud input vector + LSTM deep learning model was calculated to be 0.262 and the recognition rate was 97.5%. The lower the MAE and the higher the recognition rate, the better the results, proving the efficiency of the technique proposed in this paper.

• The Journal of the Acoustical Society of Korea
• /
• v.31 no.3
• /
• pp.161-169
• /
• 2012

This paper presents a robust speech end-point detector using double talk detection in echoic conditioned speech recognition robot. The proposed method consists of combining conventional end-point detector result and double talk detector result. We have tested the proposed method in isolated word recognition system under echoic conditioned environment. As a result, the proposed algorithm shows superior performance of 30 % to the available techniques in the points of speech recognition rates.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1439-1446
• /
• 2011

This paper describes the algorithm that lowers the dimension, maintains the object recognition and significantly reduces the eigenspace configuration time by combining the higher correlation feature information and Principle Component Analysis. Since the suggested method doesn't require a lot of computation than the method using existing geometric information or stereo image, the fact that it is very suitable for building the real-time system has been proved through the experiment. In addition, since the existing point to point method which is a simple distance calculation has many errors, in this paper to improve recognition rate the recognition error could be reduced by using several successive input images as a unit of recognition with K-Nearest Neighbor which is the improved Class to Class method.

• Journal of Korean society of Dental Hygiene
• /
• v.9 no.1
• /
• pp.45-58
• /
• 2009

The purpose of this study was to examine the recognition level related to the infection prevention in dental medical institute in dental hygienists and to offer basic data of enhancing the knowledge education in dental hygienists on the infection prevention according to it. As a result of collecting and analyzing data by using the self-administered questionnaire on April 27, 2008 targeting 230 dental hygienists who are working at hospitals and clinics in P,K region, the following conclusions were obtained. 1. Dental hygienists' recognition on hospital-virus treatment method was indicated to be averagely 1.20 out of 3-point perfection. 2. The recognition on infection was indicated to be averagely 2.64 out of 4-point perfection. The statistically significant difference was shown with the appearance of periodical health examination(t=-2.42, p<.05) and by infection-education experience(t=2.28, p<0.05). 3. The recognition on an infection disease was indicated to be averagely 4.38 out of 8-point perfection. The significant difference(t=3.52, p<0.05) was shown depending on task in charge. 4. The recognition on the infection prevention in dental treatment institute was indicated to be averagely 4.89 out of 7-point perfection. The recognition on the infection prevention of dental treatment institute in dental hygienists, who work for general hospital, was indicated to be the highest. Accordingly, it was considered to be required an effort for dental hygienists, other dental-medical practitioners, and patients to be able to treated safely by enhancing the recognition level on infection prevention in dental hygienists and by maximally reducing exposure to infection in dental medical institute.

• The Journal of the Korea Contents Association
• /
• v.9 no.8
• /
• pp.57-63
• /
• 2009

Object recognition technologies using PCA(principal component analysis) recognize objects by deciding representative features of objects in the model image, extracting feature vectors from objects in a image and measuring the distance between them and object representation. Given frequent recognition problems associated with the use of point-to-point distance approach, this study adopted the k-nearest neighbor technique(class-to-class) in which a group of object models of the same class is used as recognition unit for the images in-putted on a continual input image. However, the robustness of recognition strategies using PCA depends on several factors, including illumination. When scene constancy is not secured due to varying illumination conditions, the learning performance the feature detector can be compromised, undermining the recognition quality. This paper proposes a new PCA recognition in which database of objects can be detected under different illuminations between input images and the model images.

• Journal of Broadcast Engineering
• /
• v.17 no.5
• /
• pp.808-816
• /
• 2012

Face recognition has been actively studied and developed in various fields. In recent years, interest point extraction algorithms mainly used for object recognition were being applied to face recognition. The SURF(Speeded Up Robust Features) algorithm was used in this paper which was one of typical interest point extraction algorithms. Generally, the interest points extracted from human faces are less distinctive than the interest points extracted from objects due to the similar shapes of human faces. Thus, the accuracy of the face recognition using SURF tends to be low. In order to improve it, we propose a face recognition algorithm which performs interest point extraction by SURF and the Gabor wavelet transform to extract descriptors from the interest points. In the result, the proposed method shows around 23% better recognition accuracy than SURF-based conventional methods.

• Proceedings of the KOSOMBE Conference
• /
• v.1991 no.11
• /
• pp.129-132
• /
• 1991

This paper describes the ECG pattern recognition using the syntatic pattern recognition algorithm. The algorithm uses the BNF rule wi th the semantic evaluation which has the structural Information of the ECG. This algorithm is constructed with (1) removing the baseline drift by the Cubic spline function and exract the significant point by the line-approximation algorithm, (2) syntatic peak recognition algorithm with the extracted significant point, (3) produce the token which is used pattern recognition, (4) pattern recognition of the ECG by the syntatic pattern recognition algorithm, (5) extract the parameter with the pattern recognized ECG signal.