• Korean Journal of Plant Taxonomy
• /
• v.48 no.3
• /
• pp.230-247
• /
• 2018

We conducted principal component analyses using the quantitative characteristics of the genus Sorbaria to investigate and explore morphological variation and diagnostic characteristics. The genus Sorbaria was divided into two groups based on erect or pendulous inflorescence, the existence of hairs on the ovary and follicle surfaces, the number of stamens, and the shape of the sepal. As a result of our investigation and of a morphometric analysis, these two groups could be also classified using quantitative characteristics, in this case the number of leaflets, the size of the leaflets, the width of the inflorescence, the size of the sepal, the petal, and the follicles and seeds. In the Sorbifolia group (S. grandiflora and S. sorbifolia complex), the size of lateral leaflets, number of veins, gland and stellate density on the abaxial surface of leaflets, and the petal and follicle size were found to be useful identification characteristics. The terminal and lateral leaflet size and the gland and stellate density on the abaxial surface of the leaflets were found to be characters of taxonomic value for the Kirilowii group (S. arborea complex, S. kirilowii, and S. tomentosa complex). The results of the numerical analysis conducted here can provide valuable information to those reconsidering and delimiting a taxonomic revision of the genus Sorbaria.

• Journal of Korea Game Society
• /
• v.13 no.4
• /
• pp.15-24
• /
• 2013

The game of Go, which is originated at least more than 2,500 years ago, is one of the oldest board games in the world. So far the theoretical studies concerning to the Go openings are still insufficient. We applied traditional LDA algorithm to recognize a pro player's opening to a class obtained from the training openings. Both class-independent LDA and class-dependent LDA methods are conducted with the Go game records of the Korean top 10 professional Go players. Experimental result shows that the average recognition rate of class-independent LDA is 14% and class-dependent LDA 12%, respectively. Our research result also shows that in contrary to our common sense the algorithm based on PCA outperforms the algorithm based on LDA and reveals the new fact that the Euclidean distance metric method rarely does not inferior to LDA.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.7
• /
• pp.25-32
• /
• 2009

In this paper, we propose a new handwriting verification method using pattern analysis in off-line environments. The proposed method first segments character regions in a document and extracts effective features from the segmented regions. It then estimates the similarity between the extracted non-linear features and reference ones by using dynamic time warping and principal component analysis. Our handwriting verification method extracts handwriting features effectively and enables the verification of handwriting with various lengths of features as well as ones of short patterns. The experimental results show that our method outperforms others in terms as accuracy. We expect that the proposed method will automate the manual handwriting verification tasks and provide much objectivity on handwriting identification.

• Journal of Korea Multimedia Society
• /
• v.18 no.5
• /
• pp.610-619
• /
• 2015

*In this paper, we propose a real-time face tracking system using an adaptive face detector and a tracking algorithm. An image is divided into the regions of background and face candidate by a real-time updated skin color identifying system in order to accurately detect facial features. The facial characteristics are extracted using the five types of simple Haar-like features. The extracted features are reinterpreted by Principal Component Analysis (PCA), and the interpreted principal components are processed by Support Vector Machine (SVM) that classifies into facial and non-facial areas. The movement of the face is traced by Kalman filter and Mean shift, which use the static information of the detected faces and the differences between previous and current frames. The proposed system identifies the initial skin color and updates it through a real-time color detecting system. A similar background color can be removed by updating the skin color. Also, the performance increases up to 20% when the background color is reduced in comparison to extracting features from the entire region. The increased detection rate and speed are acquired by the usage of Kalman filter and Mean shift.

• Food Science of Animal Resources
• /
• v.37 no.5
• /
• pp.626-634
• /
• 2017

This study set out to identify the changes in the nutrient contents during the chicken cooking process as basic data for the establishment of a national health nutrition policy. Samples were produced using 3 chicken parts (wing, breast, and leg) and 7 cooking methods (boiling, pan-cooking, pan-frying, deep-frying, steaming, roasting, and microwaving), and the essential amino acid contents, principal components, and retention rates were analyzed. Weight loss was observed in all chicken parts with all cooking methods. The protein and essential amino acid contents of the chicken samples differed significantly according to the part and the cooking method (p<0.01). The protein and essential amino acid contents (g/100 g) of raw and cooked chicken parts showed ranges of 16.81-32.36 and 0.44-2.45, respectively. The principal component analysis (PCA) clearly demonstrated that the cooking methods and chicken parts produced similar trends for the essential amino acid contents. The retention rates of the chicken parts varied with the cooking methods, yielding a minimum value of 83% for isoleucine in a roasted wing, 91% for protein in a steamed breast, and 77% for isoleucine and lysine in a roasted leg. Therefore, the protein and amino acid contents of the roasted breast were higher than those of the other cooked chicken parts.

• Journal of the Korean Applied Science and Technology
• /
• v.34 no.2
• /
• pp.410-417
• /
• 2017

The physical properties of perilla leaves cultivated in Geumsan province were analyzed according storage conditions. The a/b values of perilla leaves increased with increasing storage period. Electronic nose composed of 12 different metal oxide sensors was used to differentiate flavors of perilla leaves. Sensitivities(delta $R_{gas}/R_{air}$) of sensors from electronic nose were obtained by principal compound analysis(PCA). Proportion of the first principal component was 93.07% at $25^{\circ}C$ and 97.81% at $4^{\circ}C$, respectively. In our result, flavor patterns of perilla leaves can be differentiated according to the storage temperature.

• Journal of Information Technology Services
• /
• v.6 no.3
• /
• pp.241-249
• /
• 2007

This paper describes a real-time face tracking system using effective detector and Kalman filter. In the proposed system, an image is separated into a background and an object using a real-time updated face color for effective face detection. The face features are extracted using the five types of simple Haar-like features. The extracted features are reinterpreted using Principal Component Analysis (PCA), and interpreted principal components are used for Support Vector Machine (SVM) that classifies the faces and non-faces. The moving face is traced with Kalman filter, which uses the static information of the detected faces and the dynamic information of changes between previous and current frames. The proposed system sets up an initial skin color and updates a region of a skin color through a moving skin color in a real time. It is possible to remove a background which has a similar color with a skin through updating a skin color in a real time. Also, as reducing a potential-face region using a skin color, the performance is increased up to 50% when comparing to the case of extracting features from a whole region.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.6
• /
• pp.609-616
• /
• 2017

In this paper, we propose an algorithm to obtain more stable and high recognition rate by using left and right rotation information of input image in order to obtain a stable recognition rate in face recognition. The proposed algorithm uses the facial image as the input information in the web camera environment to reduce the size of the image and normalize the information about the brightness and color to obtain the improved recognition rate. We apply Principal Component Analysis (PCA) to the detected candidate regions to obtain feature vectors and classify faces. Also, In order to reduce the error rate range of the recognition rate, a set of data with the left and right $45^{\circ}$ rotation information is constructed considering the directionality of the input face image, and each feature vector is obtained with PCA. In order to obtain a stable recognition rate with the obtained feature vector, it is after scattered in the eigenspace and the final face is recognized by comparing euclidean distant distances to each feature. The PCA-based feature vector is low-dimensional data, but there is no problem in expressing the face, and the recognition speed can be fast because of the small amount of calculation. The method proposed in this paper can improve the safety and accuracy of recognition and recognition rate faster than other algorithms, and can be used for real-time recognition system.

• Journal of Plant Biotechnology
• /
• v.42 no.3
• /
• pp.257-264
• /
• 2015

To determine whether metabolite fingerprinting for whole cell extracts based on Fourier transform infrared (FT-IR) spectroscopy can be used to discriminate and compare metabolic equivalence, standard medicinal parts from four medicinal plants (Cynanchum wilfordii Hemsley, Atractylodes japonica Koidz, Polygonum multiflorum Thunberg and Astragalus membranaceus Bunge) and their in vitro-produced adventitious roots were analyzed by FT-IR spectroscopy. The principal component analysis (PCA) and partial least square discriminant analysis (PLS-DA) from the FT-IR spectral data showed that the whole metabolic pattern from Cynanchum wilfordii was highly similar to Astragalus membranaceus. However, Atractylodes japonica and Polygonum multiflorum showed significantly different metabolic patterns. Furthermore, adventitious roots from Cynanchum wilfordii and Astragalus membranaceus also showed similar metabolic patterns compared to their standard medicinal parts. These results clearly show that mass proliferation of adventitious roots may be applied to aquire novel supply of standard medicinal parts from medicinal plants. However, the whole metabolic pattern from adventitious roots of Atractylodes japonica and Polygonum multiflorum were not similar to their standard medicinal parts. Furthermore, FT-IR spectroscopy combined with multivariate analyses established in this study may be applied as an alternative tool to discriminate the whole metabolic equivalence from several standard medicinal parts. Thus, we suggest that these metabolic discrimination systems may be applied for metabolic standardization of herbal medicinal resources.

• Journal of Bio-Environment Control
• /
• v.30 no.1
• /
• pp.19-26
• /
• 2021

In this study, analysis was performed to identify three greenhouses located in the same area using principal component analysis (PCA) and linear discrimination analysis (LDA). The environmental data in the greenhouse were from 3 farms in the same area, and the values collected at 1 hour intervals for a total of 4 weeks from April 1 to April 28 were used. Before analyzing the data, it was pre-processed to normalize the data, and the analysis was performed by dividing it into 80% of the training data and 20% of the test data. As a result of PCA and LDA analysis, it was found that PCA classification accuracy was 57.51% and LDA classification was 67.06%, indicating that it can be classified by greenhouse. Based on the farmhouse data classified in advance, the data of the new environment can be classified into specific groups to determine the tendency of the data. Such data is judged to be a way to increase the utilization of data by facilitating identification.