• Journal of the Korea Society of Computer and Information
• /
• v.14 no.11
• /
• pp.179-186
• /
• 2009

In this paper, we propose a head detection method based on vertical and horizontal pixel histogram analysis in order to overcome drawbacks of the previous head detection approach using Haar-like feature-based face detection. In the proposed method, we create the vertical and horizontal foreground pixel histogram images from the background subtraction image, which represent the number of foreground pixels in the same vertical or horizontal position. Then we extract feature points of a head region by applying Harris corner detection method to the foreground pixel histogram images and by analyzing corner points. The proposal method shows robust head detection results even in the face image covering forelock by hairs or the back view image in which the previous approaches cannot detect the head regions.

• Smart Media Journal
• /
• v.11 no.1
• /
• pp.46-57
• /
• 2022

In this paper, multi-region based Radial Graph Convolutional Network (MRGCN) algorithm which can perform end-to-end action recognition using the optical flow and gradient of input image is described. Because this method does not use information of skeleton that is difficult to acquire and complicated to estimate, it can be used in general CCTV environment in which only video camera is used. The novelty of MRGCN is that it expresses the optical flow and gradient of the input image as directional histograms and then converts it into six feature vectors to reduce the amount of computational load and uses a newly developed radial type network model to hierarchically propagate the deformation and shape change of the human body in spatio-temporal space. Another important feature is that the data input areas are arranged being overlapped each other, so that information is not spatially disconnected among input nodes. As a result of performing MRGCN's action recognition performance evaluation experiment for 30 actions, it was possible to obtain Top-1 accuracy of 84.78%, which is superior to the existing GCN-based action recognition method using skeleton data as an input.

• The Journal of Korean Medicine
• /
• v.44 no.3
• /
• pp.170-188
• /
• 2023

Objectives: The purpose of this study is to investigate the diagnostic factors of Damjeok in the literature. Methods: This study used the databases of five (Mediclassics, RISS, KMbase, OASIS, CNKI) to analyze diagnostic factors of Damjeok. Literatures published by May 2023 were assessed and we classified 91 literatures dealing with diagnostic factors by 5 categories, 'characteristics', 'location', 'symptom', 'pulse wave & tongue feature', and 'eating habits & lifestyle'. Results: Damjeok is mainly formed at the stomach in the form of lump or hard seed, and it can be observed in other regions or even the whole body by its trait of floating. Damjeok mainly shows symptoms of the digestive system and also causes various symptoms associated with the respiratory system and infection, musculoskeletal system, urogenital system, neuropsychiatric system and cardiovascular system. Regarding pulse wave and tongue feature, a slippery wave and greasy coated tongue are typical features of Damjeok. Additionally, bad eating habits and a lack of exercise have been described as a factor that cause and aggravate Damjeok. Conclusions: The two most important factors in the diagnosis of Damjeok are abdominal stiffness by physical examination and digestive symptoms, and these correspond to the definition of a syndrome. Diagnostic factors based on literature evidence will provide clues to the clinical diagnosis of Damjeok syndrome.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.33 no.6
• /
• pp.958-967
• /
• 2009

Just as various religions of the world have multiple systems based on their own belief system respectively, religious costumes, which are the expression of religion, are varied in forms according to different religions. Nonetheless, this research attempts to examine the universal features of the variety of religious costumes. Since the range of this research is broad and the limit of study is clear, this research confines the study objects into world's four high religions. The purposes of this research are as followings; first, the investigation of the world's high religions, second, the study of the figurative attributes of religious costume to study and discuss the universality of figurative beauty and aesthetic value. Figurative attributes are distinct in religious costume. First, the non structural feature of composition, and the manner in which the costume is worn. Second, the rich silhouette covering the body. Third, the restraint and inhibition of decoration, and fourth, the preference of achromatic color and monotones. 'The beauty of concealing', derived from the religious absolute and chastity, 'The beauty of chastity' influenced by the restraint of decoration and design, and 'The beauty of nature' as the drapery and non structural feature are the universal aesthetic values. Human beings tend to contact the divine beings by pursuing the essential thing and concealing the body through religion. The forms of concealment and chastity, mentioned above are reflected in the usual costumes, affected by religion as well as religious costume.

• The Research Journal of the Costume Culture
• /
• v.4 no.2
• /
• pp.247-263
• /
• 1996

This study focuses on a comparative study of 1960s'retro look mode in terms of the past and present in order to find out in detail how it in the past is readjusted after it was appeared in the present. For such a study, in the first place the contents of the dress and its ornament of a retro-look fashion was refined through some literature, and then, some works of the dress and its ornament of a retro-look fashion was refinded through some literature, and then, some works of eh dress and its ornament revived in 1960's mode were analysed, based on some fashion magazines at home and abroad like Bazaar, Fashion etc News in 1990s. After 1960s'retro-look mode which reappeared in 1990s was researched in terms of silhouette, detail, texture, color, and pattern, differences between those tow periods of 1960s and 1990s and their causes are summarized as follows: 1. In the aspect of silhouette, it appears that the silhouette in 1960s is that of somewhat stiff, charming image in which Body is excluded and the silhouette in 1990s is that of an soft, feminie image in which Body is emphasized. It was understood that the cause of such a delicate difference comes from the influences of the change in aesthetic senses or awareness, naturalism and neo-feminism. 2. In the aspect of detail, it appears that the detail in 1990s is of an attempt to express in diverse images, compared to that in 1960s, and new images are created new image in 1990s by means of presenting entirely ill-matched images. The major cause of that is because of Antistandard fashion. 3. In the aspect of textures, it appears that a great feature is that the texture in 1990s is of that introduced, being changed in natural and high-class looks, compared to that of 1960s. It was reviewed that the major cause of this is because of a result from the influence of naturalism and the technical growth in various fields which has brought the development of dress material. 4. In the aspect of color, it appears that the color in 1990s is of an image of primary color which is far more sensual and feminie than that of 1960s. It was studied that the major cause of ti comes from the influence of neo-feminism, etc. 5. In the aspect of pattern, it appears that the pattern in 1990s is of that of symbolism, transposition, and the ecletic feature of various modes which appear more deeply than that of 1960s. It was studied that the major cause of such changes is because of a trend of postmodernism which has brought the change of the spiritual structure different from that in the age of modernism. In conclusion, it was understood that the retro-look fashion is of an expression technic of dress and its ornament in that o dress in the pst is simply imitate, but new reconstitution is done by using the elements in the past. at the same time, ti was clarified that even though the elements in the past are revived as they were, dress and its ornament is governed by the social and cultural environments of he day, and with this proof it can be said that the fashion in each age is of a reflection of social phenomena of that age.

• Archives of design research
• /
• v.17 no.1
• /
• pp.99-108
• /
• 2004

Metal tableware of korea had been used from former days along with own to rice bowl exclusive use, this metal tableware has our country characteristic identity from the country that do rice to chief food to unique thing. This by recent publication we individual and peculiar ours create may. Hab, Yonyu, Omok, Okbalri of modeling of our country metal rice bowl are 4 kinds greatly. First is that is all lid in our country's metal rice bowl by 3 greatly to cultural meaning that is filled in modeling. Second, it is that there is man and woman old and the young official business while divide man and woman old and the young in our country's metal rice bowl, third, that size changes by other rice bowl according as age increases point. And item that cause definite effect in figurative feature of metal rice bowl is [ Existence and nonexistence of hoof ], [ Oral narration department's shape ], [ Reverence of oral narration belonging / Ratio of Body's height ], and [ Reverence of oral narration belonging / Ratio about Body maximum ] of it 4 be. This research finds identity of our country's design and it is basic research about that is wished to graft together in several Land of Supreme Happiness illuminating in several angles with our country characteristic metal rice bowl.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.4 s.304
• /
• pp.33-42
• /
• 2005

This paper proposes a classification method for gene expression data, using membership function and neural network. The gene expression is a process to produce mRNA and protains which generate a living body, and the gene expression data is important to find out the functions and correlations of genes. Such gene expression data can be obtained from DNA 칩 massively and quickly. However, thousands of gene expression data may not be useful until it is well organized. Therefore a classification method is necessary to find the characteristics of gene data acquired from the gene expression. In the proposed method, a set of gene data is extracted according to the fisher's criterion, because we assume that selected gene data is the well-classified data sample. However, the selected gene data does not guarantee well-classified data sample and we calculate feature values using membership function to reduce the influence of outliers in gene data. Feature vectors estimated from the selected feature values are used to train back propagation neural network. The experimental results show that the clustering performance of the proposed method has been improved compared to other existing methods in various gene expression data.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.1
• /
• pp.53-62
• /
• 2017

In this paper, we present the score classification accuracy of BBS(Berg Balance Scale) which is the most commonly used balance evaluation tool using machine learning. Data acquisition was performed using the Noraxon system and an inertial sensor of Noraxon system was attached to the body in 8 locations (left and right ankle, left and right upper buttocks, left and right wrists, back, forehead). Based on the 3-axis accelerometer of the inertial sensor, the feature vector STFT(Short Time Fourier Transform) and SAM(Signal Area Magnitude) were extracted. Then, the items of the BBS were divided into static movement and dynamic movement depending on the operation characteristics, and the feature vectors were selected according to the sensor attachment positions which affect the score for each item of the BBS. Feature vectors selected for each item of BBS were classified using GMM(Gaussian Mixture Model). As a result of the accuracy calculation for 40 subjects, 55.5%, 72.2%, 87.5%, 50%, 35.1%, 62.5%, 43.3%, 58.6%, 60.7%, 33.3%, 44.8%, 89.2%, 51.8%, 85.1%, respectively.

• Journal of Animal Science and Technology
• /
• v.63 no.2
• /
• pp.367-379
• /
• 2021

The objectives of this study were to evaluate convolutional neural network models and computer vision techniques for the classification of swine posture with high accuracy and to use the derived result in the investigation of the effect of dietary fiber level on the behavioral characteristics of the pregnant sow under low and high ambient temperatures during the last stage of gestation. A total of 27 crossbred sows (Yorkshire × Landrace; average body weight, 192.2 ± 4.8 kg) were assigned to three treatments in a randomized complete block design during the last stage of gestation (days 90 to 114). The sows in group 1 were fed a 3% fiber diet under neutral ambient temperature; the sows in group 2 were fed a diet with 3% fiber under high ambient temperature (HT); the sows in group 3 were fed a 6% fiber diet under HT. Eight popular deep learning-based feature extraction frameworks (DenseNet121, DenseNet201, InceptionResNetV2, InceptionV3, MobileNet, VGG16, VGG19, and Xception) used for automatic swine posture classification were selected and compared using the swine posture image dataset that was constructed under real swine farm conditions. The neural network models showed excellent performance on previously unseen data (ability to generalize). The DenseNet121 feature extractor achieved the best performance with 99.83% accuracy, and both DenseNet201 and MobileNet showed an accuracy of 99.77% for the classification of the image dataset. The behavior of sows classified by the DenseNet121 feature extractor showed that the HT in our study reduced (p < 0.05) the standing behavior of sows and also has a tendency to increase (p = 0.082) lying behavior. High dietary fiber treatment tended to increase (p = 0.064) lying and decrease (p < 0.05) the standing behavior of sows, but there was no change in sitting under HT conditions.

• Journal of Korea Water Resources Association
• /
• v.54 no.2
• /
• pp.121-133
• /
• 2021

Suspended Solids (SS) generated in rivers are mainly introduced from non-point pollutants or appear naturally in the water body, and are an important water quality factor that may cause long-term water pollution by being deposited. However, the conventional method of measuring the concentration of suspended solids is labor-intensive, and it is difficult to obtain a vast amount of data via point measurement. Therefore, in this study, a model for measuring the concentration of suspended solids based on remote sensing in the Nakdong River was developed using Sentinel-2 data that provides high-resolution multi-spectral satellite images. The proposed model considers the spectral bands and band ratios of various wavelength bands using a machine learning model, Support Vector Regression (SVR), to overcome the limitation of the existing remote sensing-based regression equations. The optimal combination of variables was derived using the Recursive Feature Elimination (RFE) and weight coefficients for each variable of SVR. The results show that the 705nm band belonging to the red-edge wavelength band was estimated as the most important spectral band, and the proposed SVR model produced the most accurate measurement compared with the previous regression equations. By using the RFE, the SVR model developed in this study reduces the variable dependence compared to the existing regression equations based on the single spectral band or band ratio and provides more accurate prediction of spatial distribution of suspended solids concentration.