• The Journal of Korea Robotics Society
• /
• v.8 no.4
• /
• pp.266-272
• /
• 2013

Facial feature extraction and tracking are essential steps in human-robot-interaction (HRI) field such as face recognition, gaze estimation, and emotion recognition. Active shape model (ASM) is one of the successful generative models that extract the facial features. However, applying only ASM is not adequate for modeling a face in actual applications, because positions of facial features are unstably extracted due to limitation of the number of iterations in the ASM fitting algorithm. The unaccurate positions of facial features decrease the performance of the emotion recognition. In this paper, we propose real-time facial feature extraction and tracking framework using ASM and LK optical flow for emotion recognition. LK optical flow is desirable to estimate time-varying geometric parameters in sequential face images. In addition, we introduce a straightforward method to avoid tracking failure caused by partial occlusions that can be a serious problem for tracking based algorithm. Emotion recognition experiments with k-NN and SVM classifier shows over 95% classification accuracy for three emotions: "joy", "anger", and "disgust".

• Economic and Environmental Geology
• /
• v.26 no.2
• /
• pp.217-226
• /
• 1993

Stream sediment samples were collected in the vicinity of the Sambo Pb-Zn-barite mine in order to investigate dispersion patterns and pollution levels of heavy metals, and to find out their mode of occurrences. Those samples were analyzed for Cd, Cu, Pb, Zn, Fe, and Mn by using partial extraction and sequential extraction methods. Stream sediments of this studied area has been contaminated severely by Pb, Zn, and Cd. Dispersion patterns of heavy metals in those sediments are different according to their pollution source and sampling distance from the mine. The stream sediment pH is generally neutral in control area, and is slightly acidic in the lower part of tailing dam. The main pollution source of stream sediments was confirmed as tailing and mine drainage. Their pollution level depends mainly on inflowed water and distance from the mine. The tolerance index ranges from -0.9 to 0.7. The mode of occurrances of heavy metals in polluted stream sediment are identified as Fe-Mn oxides, organic bounded and carbonate-bounded compound which show high potential of bioavailablity.

• Archives of Plastic Surgery
• /
• v.46 no.2
• /
• pp.147-151
• /
• 2019

Background Successful aesthetic plastic surgery is devoid of both unsightly scarring and postoperative disfigurement. Patients undergoing midface-lifting surgery are very often disconcerted by an altered side hairline, including sideburns, despite considerable amelioration of facial wrinkles. This study was conducted to identify an effective means of approaching an altered hairline and the unavoidable scarring arising from midface-lifting surgery. Methods A total of 37 patients who underwent corrective surgery with hair transplantation for hair loss or scar deformity arising from midface-lifting surgery from June 2014 to June 2017, and were observed for more than 6 months thereafter, were enrolled in the study. Prior to corrective surgery, the patients were administered a multiple-choice survey regarding their dissatisfaction arising from midface-lifting surgery. Among the 37 patients, 24, 12, and one underwent donor harvesting by the strip method, non-shaven follicular unit extraction, and partial shaving follicular unit extraction, respectively. Additionally, 33 of the 37 patients underwent hair transplantation in the frontotemporal recess area along with hairline correction surgery. The average number of transplanted grafts was 1,025. Results Surgery resulted in a natural and satisfactory appearance in all patients. The average patient and physician subjective satisfaction scores were 4.6 and 4.8, respectively. No adverse events such as folliculitis occurred. Conclusions Side-hairline correction surgery by hair transplantation can be considered an effective method of realigning an altered hairline accompanied by scars following midface-lifting surgery.

• Journal of Life Science
• /
• v.20 no.6
• /
• pp.922-928
• /
• 2010

This study was carried out to develop safe and novel anticoagulation agents from oriental medicinal herbs. From 33 medicinal herbs, 40 different ethanol extracts were prepared according to place of origin or extraction parts, and anticoagulation activities were evaluated by determination of thrombin time (TT), prothrombin time (PT) and activated partial thromboplastin time (aPTT). The average water content and average extraction ratio for the medicinal herbs were $6.85{\pm}2.26%$ and $5.27{\pm}4.25%$, respectively. Evaluation of TT at various concentrations of the extract led to the selection of Mucuna birdwoodiana, Prunus armeniaca, Cacalia ainsliaeiflora, Cinnamonum aromaticum, and Rhus javanica Linneas potent antithrombosis medicinal herbs. Evaluation of PT and aPTT showed that the extracts of R.javanica Linne, M. birdwoodiana, and P. armeniaca have strong anticoagulation activities. Determination of hemolytic activities of 40 different ethanol extracts against human red blood cells, however, showed that only M. birdwoodiana, C. ainsliaeiflora, C. aromaticum, and R. javanica Linnehas strong anticoagulation activity without hemolytic activity at a concentration of 500 mg/ml. Our results suggest that oriental medicinal herbs, which are under a mass-production system, have potentialas a safe and novel source of anticoagulants, as well being a thrombin-specific and coagulation factor-specific inhibitor.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.393-400
• /
• 2006

There are many feature extraction methods for face recognition. We need a new method to overcome the small sample problem that the number of feature variables is larger than the sample size for face image data. The paper considers partial least squares(PLS) as a new dimension reduction technique for feature vector. Principal Component Analysis(PCA), a conventional dimension reduction method, selects the components with maximum variability, irrespective of the class information. So, PCA does not necessarily extract features that are important for the discrimination of classes. PLS, on the other hand, constructs the components so that the correlation between the class variable and themselves is maximized. Therefore PLS components are more predictive than PCA components in classification. The experimental results on Manchester and ORL databases shows that PLS is to be preferred over PCA when classification is the goal and dimension reduction is needed.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.445-452
• /
• 2002

In Korean-English mixed documents, translated technical words are usually used with the attached full words or original words enclosed with parenthesis. In this paper, a collective method is presented to recognize and extract the translation phrases with using a base translation dictionary. In order to process the unregistered title words and translation words in the dictionary, a phonetic similarity matching method, a translation partial matching method, and a compound word matching method are newly proposed. The experiment result of each method was measured in F-measure(the alpha is set to 0.4) ; exact matching of dictionary terms as a baseline method showed 23.8%, the hybrid method of translation partial matching and phonetic similarity matching 75.9%, and the compound word matching method including the hybrid method 77.3%, which is 3.25 times better than the baseline method.

• Korean Journal of Medicinal Crop Science
• /
• v.24 no.2
• /
• pp.93-100
• /
• 2016

Background: A set of logical criteria that can accurately identify and verify the cultivation region of raw materials is a critical tool for the scientific management of traditional herbal medicine. Methods and Results: Volatile compounds were obtained from 19 and 32 samples of Angelica gigas Nakai cultivated in Korea and China, respectively, by using steam distillation extraction. The metabolites were identified using GC/MS by querying against the NIST reference library. Data binning was performed to normalize the number of variables used in statistical analysis. Multivariate statistical analyses, such as Principal Component Analysis (PCA), Partial Least Squares-Discriminant Analysis (PLS-DA), and Orthogonal Partial Least Squares-Discriminant Analysis (OPLS-DA) were performed using the SIMCA-P software. Significant variables with a Variable Importance in the Projection (VIP) score higher than 1.0 as obtained through OPLS-DA and those that resulted in p-values less than 0.05 through one-way ANOVA were selected to verify the marker compounds. Among the 19 variables extracted, styrene, ${\alpha}$-pinene, and ${\beta}$-terpinene were selected as markers to indicate the origin of A. gigas. Conclusions: The statistical model developed was suitable for determination of the geographical origin of A. gigas. The cultivation regions of six Korean and eight Chinese A. gigas. samples were predicted using the established OPLS-DA model and it was confirmed that 13 of the 14 samples were accurately classified.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.1
• /
• pp.91-97
• /
• 2009

This paper proposes novel FE-CBIRS that finds best position of a cut to be retrieved based on color feature distribution in digital contents of IPTV. Conventional CBIRS have used a method that utilizes both color and shape information together to classify images, as well as a method that utilizes both feature information of the entire region and feature information of a partial region that is extracted by segmentation for searching. Also, in the algorithm, average, standard deviation and skewness values are used in case of color features for each hue, saturation and intensity values respectively. Furthermore, in case of using partial regions, only a few major colors are used and in case of shape features, the invariant moment is mainly used on the extracted partial regions. Due to these reasons, some problems have been issued in CBIRS in processing time and accuracy so far. Therefore, in order to tackle these problems, this paper proposes the FE-CBIRS that makes searching speed faster by classifying and indexing the extracted color information by each class and by using several cuts that are restricted in range as comparative images.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.6 no.2
• /
• pp.95-106
• /
• 2007

This paper proposes an effective tempo feature extraction method for music information retrieval. The tempo information is modeled by the narrow-band temporal modulation components, which are decomposed into a modulation spectrum via joint frequency analysis. In implementation, the tempo feature is directly extracted from the modified discrete cosine transform coefficients, which is the output of partial MP3(MPEG 1 Layer 3) decoder. Then, different features are extracted from the amplitudes of modulation spectrum and applied to different music information retrieval tasks. The logarithmic scale modulation frequency coefficients are employed in automatic music emotion classification and music genre classification. The classification precision in both systems is improved significantly. The bit vectors derived from adaptive modulation spectrum is used in audio fingerprinting task That is proved to be able to achieve high robustness in this application. The experimental results in these tasks validate the effectiveness of the proposed tempo feature.

• The Korean Journal of Mycology
• /
• v.20 no.1
• /
• pp.72-76
• /
• 1992

The extraction and separation methods of protein-bound polysaccharides from the mycelium and culture broth of Coriolus versicolor (Fr) Quel were investigated. The use of 2% solution of surface active agent Triton X-100, was effective for extraction of the protein-bound polysaccharides from the mycelium. For the separation and partial purification of the protein-bound polysaccharides, the column chromatography using DEAE-Cellulose and DEAE-Sephadex proved to be effective.