• Journal of the Korea Fashion and Costume Design Association
• /
• v.21 no.4
• /
• pp.165-179
• /
• 2019

This study used 3D body scan data to classify body shapes according to the torso shape of adult males aged 20-75 years. This data will be provided so that the apparel industry can make apparel products corresponding to body characteristics by age. The study used 1,796 adult males between the ages of 20 and 75 and the 3D body shape data of the '5th Research on National Standard Anthropometry'. For data analysis, the program SPSSWIN Ver. 17.0 was used to calculate the mean and frequency allowing for a factor analysis, cluster analysis, analysis of variance, and Duncan test. To classify body shape according to the torso shape of adult males, this study considered nine factors: 'horizontal size of torso,' 'vertical size of body,' 'curve of torso and waist-abdomen flatness ratio,' 'length of torso,' 'shape of neck area,' 'degree of lateral curve,' 'difference between front and back interscye length,' 'shoulder armscye shape,' and 'chest flatness ratio.' Based on the results of the factor analysis, the torso shapes of adult males were classified into five types. Type 1 is "upright body with flat, curvy shape", Type 2 is "curve sway back body type", Type 3 is "flat, abdominally obese body", Type 4 is "obese, crooked body" and Type 5 is "thick sway front body type." named.

• The KIPS Transactions:PartB
• /
• v.10B no.7
• /
• pp.823-828
• /
• 2003

The main objective of this paper is to provide a methodology of feature extraction using shape of image objects for content-based image retrieval. The shape of most real-life objects is irregular, and hence there is no universal approach to quantify the shape of an arbitrary object. In particular. electronic catalogs contain many image objects for their products. In this paper, we perform feature extraction based on individual objects in images rather than on the whole image itself, since our method uses a shape-based approach of objects using RLC lines within an image. Experiments show that shape parameters distinctly represented image objects and provided better classification and discrimination among image objects in an image database compared to Texture.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.2
• /
• pp.171-176
• /
• 2013

X-ray cross-sectional image-based inspection technique is one of the most useful methods to inspect the brazing joints of heat exchanger. Through X-ray cross-sectional image acquisition, image processing, and defect inspection, the defects of brazing joints can be detected. This paper presents a method to judge the type of detected defects automatically, and to display them three-dimensionally. The defect type is classified as unconnected defect, void, and so on, based on location, size, and shape information of defect. Three-dimensional display which is realized using OpenGL (Open Graphics Library) will be helpful to understand the overall situation including location, size, shape of the defects in a test object.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.19-19
• /
• 2000

This paper introduces a new scheme for neural network classifier which can describe the shape of patterns in clustered group by using a self-organizing teeming algorithm. The prototype based neural network classifier can not describe the shape of group and it has low classification performance when the data groups are complex. To improve above-mentioned problem, new neural scheme is introduced. This proposed neural network algorithm can be regarded as the extension of self-organizing feature map which can describe The experimental results shows that the proposed algorithm can describe the shape of pattern successfully.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.911-914
• /
• 2011

Detecting Hand Region is essencial technology to providing User based interface and many research has been continue. In this paper will propose Hand Region Detection method by using HSV space based on Back Projection and Hand Shape Recognition using Hu Moment. By using Back Projection, I updated reliability on Hand Region Detection by Back Projection method and, Confirmed Hand Shape could be recognized through Hu moment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.5C
• /
• pp.548-555
• /
• 2006

This paper proposes on the Sasang constitution classification method which is the most important things in the Sasang constitution medicine. Pre-existing methods of Sasang constitution classification are a shape of the body and its countenance & morpological aspect and temper. Many diagnostic methods have been developed and used including the questionnaires on personal life style and propensities(QSCC, QSCC II), and the tonal analysis of person's voice. Recently the constitutional acupunture and the herbal medicine response analyses are developed and used additionally. But these methods which is done by the doctor's intuition. In this article, I propose a methodology to classify the Sasang constitution. pitch, intensity and formants are used to classify the Sasang constitution by comparing the similarities and differencies of tonal analysis. Finally, the validity of the method is proven through the experiments.

• Journal of Biomedical Engineering Research
• /
• v.25 no.2
• /
• pp.129-135
• /
• 2004

In the home health management system, we often face the situation to handle biological signals that are frequently measured from normal subjects. In such a case, it is necessary to decide whether the signal at a certain moment is normal or abnormal. Since ECC is one of the most frequently measured biological signals, we describe algorithms that detect QRS-complex and decide whether it is normal or abnormal. The developed QRS detection algorithm is a simplified version of the conventional algorithm providing enough performance for the proposed application. The developed classification algorithm that detects abnormal from mostly normal beats is based on QRS width, R-R interval and QRS shape parameter using Karhunen-Loeve transformation. The simplified QRS detector correctly detected about 99% of all beats in the MTT/BIH ECG database. The classification algorithm correctly classified about 96% of beats as normal or abnormal. The QRS detection and classification algorithm described in this paper could be used in home health management system.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.5
• /
• pp.16-23
• /
• 2011

Muzzle flash based on gunnery is the target that has huge energy. So, gunnery target in a long range over xx km is distinguishable in the IR(infrared) images, on the other hand, is not distinguishable in the CCD images. In this paper, we propose the classification method of gunnery targets in a infrared images and in a long range. The energy from gunnery have an effect on varous pixel values in infrared images as a property of infrared image sensor, distance, and atmosphere, etc. For this reason, it is difficult to classify gunnery targets using pixel values in infrared images. In proposed method, we take the profile of pixel values using high performance infrared sensor, and classify gunnery targets using modeling GMM and shape of profile. we experiment on the proposed method with infrared images in the ground and aviation. In experimental result, the proposed method provides about 93% classification rate.

• Journal of Embryo Transfer
• /
• v.30 no.3
• /
• pp.213-218
• /
• 2015

In the study for a differentiation and development of spermatogonial cells, the researchers should commonly require a simple, fast and reasonable method that could evaluate the developmental stage of male germ cells without any damage and also relentlessly culture them so far as a cell stage aiming at experimental applications. For developing the efficient method to identify the stage of sperm cells, the morphological characteristics of sperm cells were investigated by staining the cells with blue fluorescent dye Hoechst 33258, and a criterion for male germ cell classification was elicited from results of the previous investigation, then the efficiency of the criterion was verified by applying it to assort the germ cells recovered from male mice in age from 6 to 35 days. As morphological characteristics, spermatogonia significantly differed from spermatocytes in size, appearance and fluorescent patches of nucleus, and spermatids could also be distinguished from spermatozoa by making a difference in the volume and shape of nucleus and the shape and fluorescence of tail. Aforesaid criterion was applicable for classifying in vitro cultured sperm cells by verifying its efficiency and propriety for assorting the stages of testicular germ cells. However, the fluorescent staining showed that germ cells in mouse testis should be dramatically differentiated and developed at 21 days and 35 days of age, which were known as times of sexual puberty and maturity in male mice, respectively. In conclusion, the results indicated that this simple criterion for sperm cell classification using fluorescence staining with Hoechst 33258 may be highly efficient and reasonable for spermatogenesis study.

• The Journal of the Korea Contents Association
• /
• v.17 no.9
• /
• pp.132-144
• /
• 2017

The fingerprint classification of categorizing fingerprints by classes should be used in order to improve the processing speed and accuracy in a fingerprint recognition system using a large database. The fingerprint classification methods extract features from the fingerprint ridges of a fingerprint and classify the fingerprint using learning and reasoning techniques based on the classes defined according to the flow and shape of the fingerprint ridges. In earlier days, many researches have been conducted using NIST database acquired by pressing or rolling finger against a paper. However, as automated systems using live-scan scanners for fingerprint recognition have become popular, researches using fingerprint images obtained by live-scan scanners, such as fingerprint data provided by FVC, are increasing. And these days the methods of fingerprint classification using Deep Learning have proposed. In this paper, we investigate the trends of fingerprint classification technology and compare the classification performance of the technology. We desire to assist fingerprint classification research with increasing large fingerprint database in improving the performance by mentioning the necessity of fingerprint classification research with consideration for fingerprint images based on live-scan scanners and analyzing fingerprint classification using deep learning.