• 한국농공학회논문집
• /
• 제58권1호
• /
• pp.91-97
• /
• 2016

The objective of this study was to classify between radish and Chinese cabbage in autumn using hyperspectral images. The hyperspectral images were acquired by Compact Airborne Spectrographic Imager (CASI) with 1m spatial resolution and 48 bands covering the visible and near infrared portions of the solar spectrum from 370 to 1044 nm with a bandwidth of 14 nm. An object-based technique is used for classification of radish and Chinese cabbage. It was found that the optimum parameter values for image segmentation were scale 400, shape 0.1, color 0.9, compactness 0.5 and smoothness 0.5. As a result, the overall accuracy of classification was 90.7 % and the kappa coefficient was 0.71. The hyperspectral images can be used to classify other crops with higher accuracy than radish and Chines cabbage because of their similar characteristic and growth time.

• 한국의류학회지
• /
• 제33권8호
• /
• pp.1262-1272
• /
• 2009

The study is classifies the figures of obese women aged 20-50 with an over 25 BMI from the data of the fifth Size Korea in 2005. As the result of conducting the factor analysis for segmenting the shape, Factor 1, Factor 2, Factor 3, and Factor 4 are respectively derived as the factor on a volume, the factor on the size of the vertical direction, the factor on the shoulder region, and the factor on the body length balance. As the result of conducting the cluster analysis using 4 factors (scores extracted from the analysis of factor analysis) the body type of obese women was classified into four types. The name of shape was specified by combining 'P' (an abbreviation of petite) that indicated the height (smaller than 155cm) among the height names of KS standard, 'R' (abbreviation of regular) that indicated the height (155cm-165cm) and the body characteristics. Type 1 had the longest length, and normal circumference, thickness, and width but with the developed shoulder. Type 1 was classified as a robust, 'Plus-RH'. Type 2 had the middle height, the shortest length of the upper part, a relatively-long length of the lower part of body. Type 2 shows the characteristics of a small body that was classified as 'Plus-PI'. The most obese body was Type 3 that had the normal length and shoulder size but showed the longest length of the upper part of the body; it was classified as 'Plus-PO'. Type 4 as the small shape had a potbelly and showed the characteristics of the shortest body classified as 'Plus-Pb'.

• 한국의류산업학회지
• /
• 제22권4호
• /
• pp.495-503
• /
• 2020

This study classified lower body shape according to thigh and waist shape to improve the fit of skinny blue jeans in adult women in their 20s. We analyzed the three-dimensional automatic measurement data, three-dimensional indirect measurement data, and index data using the three-dimensional female (20-29 years old) body scan data provided by Size Korea (6^th Korean Human Dimensional Survey Project). Factor analysis was performed to classify body type. We selected and analyzed 34 items related to thigh shape based on index items, angle items, and protrusion amount items from 99 items; consequently, seven factors were extracted and 82.39% of the total variance was explained. Cluster analysis according to factor analysis classified it into 4 types, and a post-test Duncan test was conducted to classify thigh features according to classified types. As a result, the characteristics of lower body shape according to the thigh types of women in their 20s are as follows. Lower Body Type 1 is shape with a more prominent belly and less prominent thighs. Lower Body Type 2 is a slender body figure with larger hips. Lower Body Type 3 has more prominent thighs compared to the waist and belly. Lower Body Type 4 has both a prominent belly and prominent thighs.

• 치위생과학회지
• /
• 제23권3호
• /
• pp.193-198
• /
• 2023

Background: The nose is located at the center of the face, and it is possible to determine race, sex, and the like. Research using the nasal index (NI) classification method to classify the shape of the nose is currently in progress. However, domestic research is required as most research is being conducted abroad. In this study, we used a 3D program to confirm the ratio of the nose shape of Koreans. Methods: One hundred patients (50 males and 50 females) in their 20s were evaluated (IRB approval no. DKUDH IRB 2020-01-007). Cone beam computed tomography was performed using the Mimics ver.22 (Materialise Co., Leuven, Belgium) 3D program to model the patient's skull and soft tissues into three views: coronal, sagittal, and frontal. To confirm the ratio of measurement metrics, analysis was performed using the SPSS ver. 23.0 (IBM Co., Armonk, NY, USA) program. Results: Ten leptorrhine (long and narrow) type, 76 mesorrhine (moderate shape) type, and 14 platyrrhine (broad and short) type noses were observed. In addition, as a result of sex comparison, five males had the leptorrhine (long and narrow) type, 40 mesorrhine (moderate shape), and five platyrrhine (broad and short) types. For females, five patients had the leptorrhine (long and narrow) type, 36 patients had the mesorrhine (moderate shape) type, and nine patients had the platyrrhine (broad and short) type. Conclusion: This study will be helpful when performing nose-related surgeries and procedures in clinical practice and for similar studies in the future.

• Archives of Plastic Surgery
• /
• 제45권5호
• /
• pp.411-417
• /
• 2018

Background Accessory auricles (AAs) are common congenital anomalies. We present a new classification according to location and shape, and propose a system for coding the classifications. Methods This study was conducted by reviewing the records of 502 patients who underwent surgery for AA. AAs were classified into three anatomical types: intraauricular, preauricular, and buccal. Intraauricular AAs were divided into three subtypes: intracrural, intratragal, and intralobal. Preauricular AAs were divided into five subtypes: precrural, superior pretragal, middle pretragal, inferior pretragal, and prelobal. Buccal AAs were divided into two subtypes: anterior buccal and posterior buccal. AAs were also classified according to their protrusion pattern above the surrounding surface: pedunculated, sessile, areolar, remnant, and depressed. Pedunculated and sessile AAs were subclassified as spherical, ovoid, lobed, and nodular, according to their body shape. Cartilage root presence and family history of AA were reviewed. A coding system for these classifications was also proposed. Results The total number of AAs in the 502 patients was 1,003. Among the locations, the superior pretragal subtype (27.6%) was the most common. Among the protrusion patterns and shapes, pedunculated ovoid AAs were the most common in the preauricular (27.8%) and buccal areas (28.0%), and sessile lobed AAs were the most common in the intraauricular area (48.7%). The proportion of AAs with a cartilage root was 78.4%, and 11% of patients had a family history. The most common type of preauricular AA was the superior pretragal pedunculated ovoid AA (13.2%) with a cartilage root. Conclusions This new system will serve as a guideline for classifying and coding AAs.

• 한국멀티미디어학회논문지
• /
• 제17권3호
• /
• pp.300-311
• /
• 2014

환경의 변화에 따라 급속도로 변화하는 생태계에 대한 체계적인 연구를 위해 식물의 정보를 수집 분석하기 위한 연구가 활발하게 진행되고 있다. 특히, 스마트 기기의 카메라를 이용하여 언제 어디서나 사용자가 원하는 식물의 종류를 검색할 수 있는 기술에 대한 관심이 증가하고 있다. 본 논문은 식물 인식 및 생태계 분석을 위해 다양한 식물의 잎을 종류별로 분석할 수 있는 방법에 대해 제안한다. 이를 위해, 카메라부터 입력된 식물 잎 사진의 관심 영역을 GrabCut을 통해 배경과 분리한 후, 형태 기술자 추출 방법인 SIFT(Scale-Invariant Feature Transform), HOG(Histogram of Oriented Gradient)를 이용하여 형태 기술자를 추출하고, 이것을 부호화 기법 및 공간 피라미드 방법을 이용한 분류 특징 벡터를 만든다. SVM(Support Vector Machine)을 통한 식물 잎 분류 및 인식한다. 다양한 식물 잎에 대한 실험 결과를 통해 비슷한 색상이나 형태를 가지고 있더라도 방향성 특징 기술자를 활용한 식물 잎 분류 방법이 매우 효율적임을 알 수 있다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.417-422
• /
• 1998

This paper presents a method of object classification from dynamic image based on fuzzy inference algorithm which is suitable for low speed such as, conveyor, uninhabited transportation. At first, by using feature parameters of moving object, fuzzy if - then rule that can be able to adapt the wide variety of surroundings is developed. Secondly, implication function for fuzzy inference are compared with respect the proposed algorithm. Simulation results are presented to testify the performance and applicability of the proposed system.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2012년도 한국컴퓨터종합학술대회논문집 Vol.39 No.1(B)
• /
• pp.522-524
• /
• 2012

For exact classification of the defect, good feature selection and classifier is necessary. In this paper, various features such as brightness features, shape features and statistical features are stated and Bayes classifier using Gaussian mixture model is used as classifier. Also feature extraction method based on spectral graph theory is presented. Experimental result shows that feature extraction method using graph Laplacian result in better performance than the result using PCA.

• 대한예방한의학회지
• /
• 제4권2호
• /
• pp.93-107
• /
• 2000

Korea follows the Korea standard classification of disease and causes of death according to the ICD(international classification of disease) Oriental medicine began to of officially follow the classification of disease for using the Korean classification of diseases in 1972. The classification of OM(oriental medicine) has changed in shape experiencing two amendments. The largest difficulty was to overcome the different names of diseases between OM and ICD. A one-to-one correspondence of the name of a disease between OM and ICD is impossible So in the primary stage one-to-one and one-to-many correspondence was made. During the first amendment the international disease names were re-classified on the oriental medicine disease name's basis and at the same time the classification of OM was corresponded on a one-to-one basis to the ICD . During the second amendment this changed to many-to-many correspondence . Analyzing the history of classification of OM during the first and second amendments, it was discovered that establishment of the standards of classification, the unification of oriental medical terms, and overcoming the difference of disease names between the OM and ICD is necessary Also th classification and standardazation of OM must not stop as a single round. It must go on for a long time. The hosts of this project Korean oriental medical society and AKOM(association of korean oriental medicine) need to build a independant department which will supervise the classification project and monitor any problems to come up. Also a route through which suggestions can be taken in and new solutions can be brought up needs to be secured and an atmosphere in which studies can take place about the basis of classifications needs to be developed.

• 한국멀티미디어학회논문지
• /
• 제5권5호
• /
• pp.505-514
• /
• 2002

본 논문에서는 내용기반 영상 분류를 위한 방법론으로써 신경망을 이용한 방법을 제안한다. 분류 대상 영상은 인터넷상의 다양한 영상들 중에서 전경과 배경의 구분이 있는 객체 영상이다. 전처리 과정에서 영역 분할을 이용하여 영상 내에서 배경을 제거하고 객체 영역을 추출한다. 분류를 위한 특징은 웨이블릿 변환 후 푸출된 형태 특징과 질감특징을 이용한다 추출된 특징 값들을 이용하여 영상들에 대한 학습패턴을 생성하고 신경망 분류기를 구성 한다. 신경망의 학습 알고리즘은 역전파 알고리즘을 사용한다. 가장 효과적인 질감특징을 선 택 하기 위한 실험에서는 대각 모멘트가 가장 높은 분류률을 보여 주었다. 배경을 제거 하고 대각 모멘트를 특징으로 사용하여 실험하였을 때, 30종류에서 각 10개씩 총 300개의 학습 데이터와300개의 테스트 데이터에 대하여 각각 72.3%와 67%의 정분류률을 보였다.